LAION · audio annotation experiment · 4 October 2026

What does Gemini hear
in 25 S10 clips?

One complete audio clip per sequential Gemini 3.8 Flash request, using the detailed LAION voice-annotation master prompt. Compare its transcript, two captions, 40 emotions, 57 voice dimensions and timestamped vocal bursts with existing S10 annotations and the released Whisper Base/Small S10 predictions. Every player is embedded directly in this HTML.

25/25 valid Gemini responsesSingle clip per requestDE + ENReal + syntheticBase64 audio · offline playable

How to read this page

Gemini uses integer scores (EmoNet 0–4, most VoiceNet 0–6, BKGN 0–4, EXPL 0–2). Existing S10 teacher scores are the annotations already attached to the Scaling Ladder. Whisper Base/Small S10 are continuous student predictions from the released encoder-only models; their values are not probabilities. The rows below show raw scores on the same nominal scale. A dark bar means no value was available. The colored timelines show predicted burst spans; every event has explicit start and end times in seconds in the event list and on hover. Their agreement is a diagnostic, not proof of correctness.

This is a qualitative smoke test of 25 deliberately varied S10 training clips, not a held-out benchmark or human-labeled ground truth. Existing S10 burst markers are teacher annotations. The Gemini prompt sees audio only; selection labels, UIDs and existing scores are never sent to it. Scores and timestamps require listening review before reuse as training targets. One initially selected clip was repeatedly blocked by the API and replaced with another same-stratum, same-emotion candidate; the rejected clip is retained only in the local audit.

Observed: 18/25 clips have at least one Gemini burst, with 38 reported events; the existing S10 markers cover 13 clips and 19 spans. Valid responses used 634,773 prompt tokens, of which 627,125 were served from the cached master prompt, and 38,114 output tokens over 163.8 seconds of cumulative API time.

Descriptive agreement with Gemini

These are pairwise differences on this selected set, not accuracy. MAE compares raw scores in their nominal rubric units. Mean Spearman ranks dimensions within each clip. Interval F1 matches spans at IoU ≥ 0.5 and is especially sensitive to whether ordinary breathing counts as a burst.

ComparatorEmotion MAE ↓VoiceNet MAE ↓Emotion rank ρ ↑Voice rank ρ ↑Burst count MAE ↓Span F1 ↑
existing S10 teacher0.5061.0890.5380.5251.4000.035
Whisper Base S100.5061.0730.5600.5291.4490.067
Whisper Small S100.5011.0670.5680.5381.4240.035

Source: LAION Scaling Ladder DE/EN (all displayed clips CC-0 or CC-BY-4.0) · Student models: Whisper Base/Small layered audio scores · Download validated Gemini annotation sidecar · Download agreement statistics · Prompt SHA-256: 18bc5ffcb1ce9cfe4dfbe1848c447fd8081384acfcc713c50f28254df4799911.

Explore clips
S10-01 · de / real

Anger

18.9 s · Complete

Source: kartoffelphon (CC-BY-4.0) · de/real · chosen for high existing Anger score (z=3.16); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German · German with non-native/English-influenced accent

Transcript

S1: Unfall, dass der S2: Okay. S1: der Schulter wird ausgekoppelt, ja, S2: Ja. S1: und dann die die Nerven, die da damit ähm in der Schulter sind, ausgerissen. Das ist typisch. Die anderen Art, die viel häufiger ist, ist diabetische Neuropathien. So viele Leute haben diabetisches Schmerz, und das ist oft ein Schmerz und die sind alle

Audio caption

A conversational clip featuring a dominant masculine-coded speaker in the mature adult age bracket explaining medical conditions in German, with a brief, quiet interlocutor providing backchannel acknowledgments. The primary speaker demonstrates an accent indicative of non-native German, likely English-influenced, while delivering technical information with an authoritative and didactic tone. Resonance is balanced across chest and oral cavities with a comfortable baritone register. Timbre exhibits moderate warmth and natural harmonicity with minimal roughness. The delivery is spontaneous and fluid despite brief formulation pauses and minor grammatical searching. Articulation is clear and well-projected, maintaining an engaging, listener-oriented posture throughout. Emotionally, the tone is composed, objective, and intellectually engaged, devoid of overt emotional polarity. Recording quality is clear with mild room ambience and minimal background interference, capturing a completely genuine, unscripted explanatory exchange without isolated vocal bursts.

Director caption

S1 begins with an explanatory, didactic cadence in a mature baritone register, setting up a clinical scenario: "Unfall, dass der". S2 provides a quiet, polite backchannel acknowledgement: "Okay." S1 continues immediately with steady pacing and natural hand gestures implied by the forward oral focus: "der Schulter wird ausgekoppelt, ja," paused briefly as S2 confirms with a low, supportive "Ja." S1 then resumes, navigating a momentary cognitive formulation pause with an organic filler before detailing the anatomy: "und dann die die Nerven, die da damit ähm in der Schulter sind, ausgerissen." Conclude that thought with matter-of-fact certainty, slightly dropping pitch: "Das ist typisch." Transition smoothly into a comparative point, perking up with renewed pedagogical focus: "Die anderen Art, die viel häufiger ist, ist diabetische Neuropathien." Maintain an informative, authoritative conversational rhythm, emphasizing key terms clearly: "So viele Leute haben diabetisches Schmerz, und das ist oft ein Schmerz und die sind alle" before trailing off naturally as thought develops.

Gemini bursts0
Base / Small count2.11 / 2.17
Genuineness (G / B / S)5 / 4.38 / 4.36
Burst blend (G / B / S)— / 4.44 / 4.67
CPS (Base / Small)16.38 / 16.61
0 s18.9 s
Event captions and top-3 Whisper classes
  • Existing S10 marker · Start: 0.04 s · End: 0.30 s
  • Existing S10 marker · Start: 5.52 s · End: 5.86 s
  • Base proposals: Start: 0.02 s · End: 0.24 s: Ahem 0.74, Low Mumble 0.11, Chuckle 0.06; Start: 5.50 s · End: 5.92 s: Low Mumble 0.81, Ahem 0.11, Nervous Giggle 0.01
  • Small proposals: Start: 0.02 s · End: 0.24 s: Ahem 0.77, Chuckle 0.16, Low Mumble 0.01; Start: 5.50 s · End: 5.90 s: Low Mumble 0.88, Ahem 0.05, Spitting 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.404.244.34
agevvn_AGEV_reg4.004.014.264.24
focsvn_FOCS_reg4.002.322.702.60
harmvn_HARM_reg4.002.612.502.51
r oralvn_R_ORAL_reg4.002.162.502.38
s authvn_S_AUTH_reg4.002.132.492.39
s convvn_S_CONV_reg4.003.363.082.96
s techvn_S_TECH_reg4.000.381.040.91
stncvn_STNC_reg4.003.453.453.41
arouvn_AROU_reg3.002.402.512.40
arshvn_ARSH_reg3.003.043.163.03
atckvn_ATCK_reg3.002.572.592.50
bkgnvn_BKGN_reg3.002.152.332.22
brgtvn_BRGT_reg3.002.272.532.40
chnkvn_CHNK_reg3.003.343.142.84
clrtvn_CLRT_reg3.002.252.232.28
coglvn_COGL_reg3.003.303.093.19
darcvn_DARC_reg3.001.942.132.11
dfluvn_DFLU_reg3.003.413.213.37
emphvn_EMPH_reg3.003.663.503.40
esthvn_ESTH_reg3.002.362.572.51
fullvn_FULL_reg3.002.462.502.45
r chstvn_R_CHST_reg3.002.933.023.06
r maskvn_R_MASK_reg3.002.562.682.56
r mixdvn_R_MIXD_reg3.002.032.502.38
r thrtvn_R_THRT_reg3.001.832.032.05
rangvn_RANG_reg3.002.663.012.89
rcqlvn_RCQL_reg3.002.833.032.92
s casuvn_S_CASU_reg3.003.313.223.22
s formvn_S_FORM_reg3.001.632.262.21
smthvn_SMTH_reg3.002.102.312.31
struvn_STRU_reg3.001.631.881.80
tempvn_TEMP_reg3.003.313.113.12
valnvn_VALN_reg3.003.233.163.02
valsvn_VALS_reg3.003.463.413.36
vflxvn_VFLX_reg3.002.512.552.50
warmvn_WARM_reg3.003.043.092.94
metlvn_METL_reg2.001.551.461.42
r headvn_R_HEAD_reg2.002.512.472.37
r naslvn_R_NASL_reg2.003.043.173.18
respvn_RESP_reg2.002.902.402.51
rougvn_ROUG_reg2.002.142.212.33
s narrvn_S_NARR_reg2.000.801.521.57
s stryvn_S_STRY_reg2.002.142.191.95
tensvn_TENS_reg2.001.451.461.39
voltvn_VOLT_reg2.002.322.222.04
vulnvn_VULN_reg2.001.951.861.89
regsvn_REGS_reg1.000.010.180.11
s dramvn_S_DRAM_reg1.002.892.752.60
s monovn_S_MONO_reg1.002.693.083.03
s newsvn_S_NEWS_reg1.000.460.730.73
s playvn_S_PLAY_reg1.002.122.071.93
explvn_EXPL_reg0.00-0.12-0.06-0.08
s asmrvn_S_ASMR_reg0.000.480.420.46
s cartvn_S_CART_reg0.000.720.750.79
s rantvn_S_RANT_reg0.001.931.831.65
s whisvn_S_WHIS_reg0.000.530.480.62
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.263.27
eiv_extra:Arousal1.901.91
eiv_extra:Authenticity2.872.81
eiv_extra:Background_Noise0.820.88
eiv_extra:Confident_vs._Hesitant1.111.17
eiv_extra:Gender-0.95-1.01
eiv_extra:High-Pitched_vs._Low-Pitched2.102.05
eiv_extra:Monotone_vs._Expressive2.432.36
eiv_extra:Recording_Quality2.402.40
eiv_extra:Serious_vs._Humorous1.000.88
eiv_extra:Soft_vs._Harsh-0.04-0.05
eiv_extra:Submissive_vs._Dominant0.760.74
eiv_extra:Valence-0.09-0.26
eiv_extra:Vulnerable_vs._Emotionally_Detached1.901.95
eiv_extra:Warm_vs._Cold-0.17-0.21
eiv_extra:score_background_quality3.403.46
eiv_extra:score_content_enjoyment4.674.77
eiv_extra:score_overall_quality2.842.96
eiv_extra:score_speech_quality1.691.71
audiobox:CE5.005.27
audiobox:CU5.235.64
audiobox:PC2.122.09
audiobox:PQ6.796.89
dnsmos:SIG_raw4.094.08
dnsmos:BAK_raw3.463.76
dnsmos:OVRL_raw3.403.57
dnsmos:SIG3.603.59
dnsmos:BAK3.463.72
dnsmos:OVRL3.033.15
dnsmos:P808_MOS4.014.07
voiceclap_attribute:Affection0.300.15
voiceclap_attribute:Age3.203.28
voiceclap_attribute:Amusement0.330.29
voiceclap_attribute:Anger0.590.64
voiceclap_attribute:Arousal1.701.59
voiceclap_attribute:Astonishment_Surprise0.260.34
voiceclap_attribute:Authenticity2.832.82
voiceclap_attribute:Awe0.350.32
voiceclap_attribute:Background_Noise0.580.52
voiceclap_attribute:Bitterness0.570.54
voiceclap_attribute:Concentration2.142.05
voiceclap_attribute:Confident_vs._Hesitant1.301.32
voiceclap_attribute:Confusion0.270.36
voiceclap_attribute:Contemplation1.261.26
voiceclap_attribute:Contempt0.690.64
voiceclap_attribute:Contentment0.490.48
voiceclap_attribute:Disappointment0.690.69
voiceclap_attribute:Disgust0.480.49
voiceclap_attribute:Distress0.450.41
voiceclap_attribute:Doubt0.510.52
voiceclap_attribute:Elation0.820.69
voiceclap_attribute:Embarrassment0.070.01
voiceclap_attribute:Emotional_Numbness0.480.64
voiceclap_attribute:Fatigue_Exhaustion0.060.06
voiceclap_attribute:Fear0.500.43
voiceclap_attribute:Gender-1.12-0.96
voiceclap_attribute:Helplessness0.260.19
voiceclap_attribute:High-Pitched_vs._Low-Pitched2.182.11
voiceclap_attribute:Hope_Enthusiasm_Optimism1.151.11
voiceclap_attribute:Impatience_and_Irritability0.630.60
voiceclap_attribute:Infatuation-0.15-0.15
voiceclap_attribute:Interest2.792.66
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness-0.25-0.17
voiceclap_attribute:Jealousy_&_Envy0.230.33
voiceclap_attribute:Longing0.200.19
voiceclap_attribute:Malevolence_Malice0.470.50
voiceclap_attribute:Monotone_vs._Expressive2.322.08
voiceclap_attribute:Pain-0.03-0.04
voiceclap_attribute:Pleasure_Ecstasy0.260.17
voiceclap_attribute:Pride0.830.78
voiceclap_attribute:Recording_Quality2.612.76
voiceclap_attribute:Relief0.470.49
voiceclap_attribute:Sadness0.350.33
voiceclap_attribute:Serious_vs._Humorous1.190.99
voiceclap_attribute:Sexual_Lust-0.13-0.02
voiceclap_attribute:Shame0.260.23
voiceclap_attribute:Soft_vs._Harsh0.130.08
voiceclap_attribute:Sourness0.450.55
voiceclap_attribute:Submissive_vs._Dominant0.780.70
voiceclap_attribute:Teasing0.220.32
voiceclap_attribute:Thankfulness_Gratitude0.970.82
voiceclap_attribute:Triumph0.630.62
voiceclap_attribute:Valence0.530.31
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.982.16
voiceclap_attribute:Warm_vs._Cold0.190.03
voiceclap_attribute:duration18.5118.51
voiceclap_attribute:score_background_quality3.293.42
voiceclap_attribute:score_content_enjoyment4.924.96
voiceclap_attribute:score_overall_quality2.832.79
voiceclap_attribute:score_speech_quality1.851.84
voiceclap_attribute:talking_speed15.1114.35
Reproducibility and API usage

Dataset UID: tr00083_002503
Audio SHA-256: 8a8e3d79b582ebe367c1f39cace5a4e29fed36263d33c2b14fe9515b097a8dff
Gemini call: 6.60 s; input tokens 25571; cached tokens 25085; output tokens 1522.

S10-02 · de / real

Sadness

3.4 s · Complete

Source: emolia (CC-BY-4.0) · de/real · chosen for high existing Sadness score (z=3.57); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

German/English · Standard German / German-accented English

Transcript

S1: Es ist alles meine Schuld. S2: It's all my fault.

Audio caption

The audio features two consecutive spoken lines conveying self-blame, spoken first in German and then translated into English. The first line is spoken by a feminine-leaning young-adult voice with a subdued, sorrowful, and remorseful tone, using clean oral and mask resonance with controlled breathiness. The second line features a masculine-leaning young-adult voice echoing the exact meaning with gentle, regretful dejection and a slight German accent in English. Both speakers exhibit restrained pitch ranges, moderate tempo, clear articulation, and a vulnerable, submissive interpersonal posture marked by guilt and sadness. The recording quality is crisp and studio-grade with virtually no background noise, presenting a clean, dramatic confession.

Director caption

S1: Speak in German with a heavy, somber tone of personal remorse, keeping the volume controlled and slightly breathy: "Es ist alles meine Schuld." Pause briefly to let the weight of the confession settle. S2: Enter with a subdued, masculine-leaning delivery, echoing the same feeling of helpless guilt in slightly accented English, stressing the word 'all' before letting the sentence trail off into dejected resignation: "It's all my fault."

Gemini bursts0
Base / Small count0.00 / 0.00
Genuineness (G / B / S)4 / 1.58 / 1.48
Burst blend (G / B / S)— / 3.40 / 3.14
CPS (Base / Small)13.67 / 13.64
0 s3.4 s
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
bkgnvn_BKGN_reg4.003.964.164.06
clrtvn_CLRT_reg4.003.843.153.21
esthvn_ESTH_reg4.003.343.403.49
focsvn_FOCS_reg4.002.412.472.57
harmvn_HARM_reg4.003.953.043.44
r oralvn_R_ORAL_reg4.003.703.373.41
rcqlvn_RCQL_reg4.004.594.454.59
s dramvn_S_DRAM_reg4.002.892.913.13
smthvn_SMTH_reg4.001.531.942.02
struvn_STRU_reg4.003.092.803.04
vulnvn_VULN_reg4.002.052.702.64
agevvn_AGEV_reg3.001.241.301.42
arshvn_ARSH_reg3.004.363.703.87
brgtvn_BRGT_reg3.003.223.053.19
chnkvn_CHNK_reg3.001.151.441.51
darcvn_DARC_reg3.003.072.862.97
emphvn_EMPH_reg3.002.732.952.84
fullvn_FULL_reg3.001.691.971.90
r headvn_R_HEAD_reg3.002.642.782.84
r maskvn_R_MASK_reg3.003.082.652.86
r mixdvn_R_MIXD_reg3.000.891.421.32
regsvn_REGS_reg3.004.314.194.43
s casuvn_S_CASU_reg3.003.683.973.90
s convvn_S_CONV_reg3.003.153.763.53
s monovn_S_MONO_reg3.002.952.912.99
tempvn_TEMP_reg3.001.942.312.34
tensvn_TENS_reg3.002.432.442.43
valsvn_VALS_reg3.003.362.993.02
vflxvn_VFLX_reg3.003.673.523.72
warmvn_WARM_reg3.002.542.612.70
arouvn_AROU_reg2.002.902.873.02
atckvn_ATCK_reg2.004.023.523.65
gendvn_GEND_reg2.000.520.470.46
r chstvn_R_CHST_reg2.002.011.911.97
r thrtvn_R_THRT_reg2.003.593.283.21
rangvn_RANG_reg2.003.293.383.48
respvn_RESP_reg2.001.752.191.99
s formvn_S_FORM_reg2.002.141.501.62
s narrvn_S_NARR_reg2.002.492.832.85
s stryvn_S_STRY_reg2.004.184.504.50
coglvn_COGL_reg1.000.300.560.70
metlvn_METL_reg1.002.792.292.29
r naslvn_R_NASL_reg1.003.773.513.51
rougvn_ROUG_reg1.000.980.971.16
s asmrvn_S_ASMR_reg1.001.831.841.69
s authvn_S_AUTH_reg1.002.241.681.55
s techvn_S_TECH_reg1.001.941.201.05
s whisvn_S_WHIS_reg1.002.242.392.45
stncvn_STNC_reg1.003.652.592.82
valnvn_VALN_reg1.003.673.393.28
voltvn_VOLT_reg1.002.062.482.57
dfluvn_DFLU_reg0.000.410.970.85
explvn_EXPL_reg0.000.130.120.27
s cartvn_S_CART_reg0.001.721.591.98
s newsvn_S_NEWS_reg0.000.780.550.78
s playvn_S_PLAY_reg0.001.932.722.44
s rantvn_S_RANT_reg0.00-0.88-0.17-0.16
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.313.29
eiv_extra:Arousal1.591.34
eiv_extra:Authenticity3.173.14
eiv_extra:Background_Noise-0.10-0.18
eiv_extra:Confident_vs._Hesitant1.100.82
eiv_extra:Gender1.441.50
eiv_extra:High-Pitched_vs._Low-Pitched1.191.01
eiv_extra:Monotone_vs._Expressive1.491.23
eiv_extra:Recording_Quality2.742.67
eiv_extra:Serious_vs._Humorous0.650.44
eiv_extra:Soft_vs._Harsh0.470.22
eiv_extra:Submissive_vs._Dominant0.520.44
eiv_extra:Valence-0.66-0.44
eiv_extra:Vulnerable_vs._Emotionally_Detached0.920.82
eiv_extra:Warm_vs._Cold0.02-0.00
eiv_extra:score_background_quality3.583.54
eiv_extra:score_content_enjoyment4.684.82
eiv_extra:score_overall_quality2.782.81
eiv_extra:score_speech_quality1.992.04
audiobox:CE5.635.56
audiobox:CU6.426.52
audiobox:PC1.331.55
audiobox:PQ7.237.45
dnsmos:SIG_raw3.863.99
dnsmos:BAK_raw4.124.10
dnsmos:OVRL_raw3.573.65
dnsmos:SIG3.473.55
dnsmos:BAK3.983.99
dnsmos:OVRL3.163.22
dnsmos:P808_MOS3.813.69
voiceclap_attribute:Affection1.231.21
voiceclap_attribute:Age3.083.20
voiceclap_attribute:Amusement0.770.56
voiceclap_attribute:Anger0.600.86
voiceclap_attribute:Arousal1.601.43
voiceclap_attribute:Astonishment_Surprise1.341.29
voiceclap_attribute:Authenticity3.303.31
voiceclap_attribute:Awe0.790.64
voiceclap_attribute:Background_Noise-0.09-0.11
voiceclap_attribute:Bitterness0.470.50
voiceclap_attribute:Concentration0.140.26
voiceclap_attribute:Confident_vs._Hesitant1.411.28
voiceclap_attribute:Confusion0.710.67
voiceclap_attribute:Contemplation0.670.55
voiceclap_attribute:Contempt0.390.43
voiceclap_attribute:Contentment0.720.59
voiceclap_attribute:Disappointment0.871.02
voiceclap_attribute:Disgust0.610.67
voiceclap_attribute:Distress1.101.36
voiceclap_attribute:Doubt0.690.73
voiceclap_attribute:Elation1.071.01
voiceclap_attribute:Embarrassment0.740.73
voiceclap_attribute:Emotional_Numbness0.560.76
voiceclap_attribute:Fatigue_Exhaustion0.780.80
voiceclap_attribute:Fear0.610.70
voiceclap_attribute:Gender1.411.60
voiceclap_attribute:Helplessness0.981.18
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.151.23
voiceclap_attribute:Hope_Enthusiasm_Optimism1.091.17
voiceclap_attribute:Impatience_and_Irritability0.820.93
voiceclap_attribute:Infatuation1.090.99
voiceclap_attribute:Interest0.920.68
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.320.45
voiceclap_attribute:Jealousy_&_Envy0.640.56
voiceclap_attribute:Longing0.960.89
voiceclap_attribute:Malevolence_Malice0.470.52
voiceclap_attribute:Monotone_vs._Expressive1.701.50
voiceclap_attribute:Pain0.640.61
voiceclap_attribute:Pleasure_Ecstasy0.940.86
voiceclap_attribute:Pride0.810.64
voiceclap_attribute:Recording_Quality2.682.81
voiceclap_attribute:Relief1.571.67
voiceclap_attribute:Sadness1.201.27
voiceclap_attribute:Serious_vs._Humorous1.180.86
voiceclap_attribute:Sexual_Lust0.190.30
voiceclap_attribute:Shame1.021.05
voiceclap_attribute:Soft_vs._Harsh0.790.70
voiceclap_attribute:Sourness0.500.52
voiceclap_attribute:Submissive_vs._Dominant0.350.33
voiceclap_attribute:Teasing0.550.39
voiceclap_attribute:Thankfulness_Gratitude1.691.54
voiceclap_attribute:Triumph0.670.80
voiceclap_attribute:Valence0.030.19
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.840.78
voiceclap_attribute:Warm_vs._Cold0.570.51
voiceclap_attribute:duration4.815.00
voiceclap_attribute:score_background_quality3.563.53
voiceclap_attribute:score_content_enjoyment4.764.76
voiceclap_attribute:score_overall_quality2.602.63
voiceclap_attribute:score_speech_quality2.022.06
voiceclap_attribute:talking_speed13.2613.59
Reproducibility and API usage

Dataset UID: DE_B00002_S06060_W000000
Audio SHA-256: 9c2fde5525230ca2faba5079d670de57498a024ac09e4eb209d882ffaadc2717
Gemini call: 5.71 s; input tokens 25184; cached tokens 25085; output tokens 1280.

S10-03 · de / real

Amusement

18.0 s · Complete

Source: kartoffelphon (CC-BY-4.0) · de/real · chosen for high existing Amusement score (z=2.57); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German/English · Standard German / General American

Transcript

S1: Ich will das unbedingt jetzt sofort spielen! Gib her! Gib her! Gib! Gib her! Ein Tag auf die Fresse! Karre! Was? Das ist so dumm!

Audio caption

A young-adult-sounding masculine speaker reacts with intense excitement, amusement, and comedic impatience while watching a game trailer with an English voiceover playing continuously in the background. The German speaker begins with an urgent, fast-paced exclamation that escalates into high-pitched, staccato shouts demanding to play, featuring prominent throat and head resonance, hard glottal attacks, and high physiological arousal. The tone is highly playful and uninhibited, shifting from mock-greedy demand to astonished bewilderment when reacting to the trailer's absurd visual concept. Snatched gasps and a breathy snicker seamlessly punctuate the reactive speech, perfectly embedded within the organic viewing context. The overall audio reflects a live streaming or casual reaction setup, with foreground speech clearly captured above the audible trailer audio.

Director caption

Deliver the opening line in German with rapid, enthusiastic forward momentum: "Ich will das unbedingt jetzt sofort spielen!" Immediately take a sharp, high-pitched surprised gasp of excitement, then sharply shout with repetitive, demanding staccato punches, pushing into a strained high register and tight throat attack: "Gib her! Gib her! Gib! Gib her!" Drop down slightly into a gritty, aggressive, comedic bark: "Ein Tag auf die Fresse!" Listen to the commercial trailer audio running behind you, then interrupt with a sudden, punchy yell: "Karre!" Let astonishment take over with a flat, confused prompt: "Was?" As the video reveals something bizarre, take a sharp audible gasp of bewilderment, let out a breathy, stifled snicker of disbelief, and deliver the final line through laughing, relaxed articulation: "Das ist so dumm!"

Gemini bursts3
Base / Small count1.78 / 1.31
Genuineness (G / B / S)5 / 4.71 / 4.66
Burst blend (G / B / S)8 / 3.84 / 4.71
CPS (Base / Small)8.29 / 8.11
0 s18.0 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 1.48 s · End: 2.05 s · Surprised Gasp gasp
    A sharp, high-pitched surprised intake of air with an open throat and wide vowel quality occurs in the brief pause before the speaker begins shouting demanding imperatives; it sounds completely natural as a sudden spike in energetic excitement rather than an edited artifact.
  • Gemini · Start: 15.82 s · End: 16.55 s · Sharp Inhale gasp
    A quick, breathy gasp-like inhalation of astonishment occurs in reaction to seeing video footage; it features high airflow and sharp throat onset, naturally preceding the burst of disbelieving laughter and spoken commentary.
  • Gemini · Start: 16.55 s · End: 17.15 s · Snicker laugh_soft
    A breathy, stifled snickering chuckle with a prominent nasal and dental hiss escapes immediately following the gasp; it directly colors the subsequent phrase 'Das ist so dumm!' and shows natural physiological continuity with residual laughter.
  • Existing S10 marker · Start: 9.84 s · End: 9.98 s
  • Existing S10 marker · Start: 16.60 s · End: 16.86 s
  • Base proposals: Start: 0.02 s · End: 0.20 s: Ahem 0.91, Surprised Gasp 0.01, Nervous Giggle 0.01; Start: 9.82 s · End: 10.02 s: Ahem 0.91, Snicker 0.01, Spitting 0.01; Start: 16.56 s · End: 16.96 s: Surprised Gasp 0.60, Childlike Giggle 0.25, Trembling Whimper 0.03
  • Small proposals: Start: 0.00 s · End: 0.18 s: Ahem 0.88, Surprised Gasp 0.02, Spitting 0.01; Start: 9.86 s · End: 10.00 s: Ahem 0.95, Spitting 0.00, Nervous Giggle 0.00; Start: 16.58 s · End: 16.88 s: Surprised Gasp 0.95, Sharp Inhale 0.01, Spitting 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.004.064.344.14
atckvn_ATCK_reg5.004.123.793.90
emphvn_EMPH_reg5.004.274.024.12
gendvn_GEND_reg5.004.534.724.63
rangvn_RANG_reg5.003.914.043.92
s casuvn_S_CASU_reg5.005.895.695.62
s playvn_S_PLAY_reg5.003.673.983.71
stncvn_STNC_reg5.004.343.933.94
arshvn_ARSH_reg4.003.013.473.30
brgtvn_BRGT_reg4.001.821.901.83
clrtvn_CLRT_reg4.001.911.951.92
darcvn_DARC_reg4.005.395.725.51
focsvn_FOCS_reg4.003.623.133.28
r headvn_R_HEAD_reg4.002.032.492.06
r oralvn_R_ORAL_reg4.002.132.051.81
r thrtvn_R_THRT_reg4.001.902.031.84
respvn_RESP_reg4.003.523.133.42
s convvn_S_CONV_reg4.002.943.853.41
s dramvn_S_DRAM_reg4.004.594.444.53
tempvn_TEMP_reg4.003.673.243.43
tensvn_TENS_reg4.003.203.273.26
valnvn_VALN_reg4.002.713.272.81
valsvn_VALS_reg4.002.282.782.27
vflxvn_VFLX_reg4.002.102.001.66
voltvn_VOLT_reg4.004.043.874.04
agevvn_AGEV_reg3.001.882.082.02
esthvn_ESTH_reg3.001.081.451.33
fullvn_FULL_reg3.001.621.911.85
harmvn_HARM_reg3.001.612.071.87
metlvn_METL_reg3.003.053.092.93
r maskvn_R_MASK_reg3.002.472.812.29
r mixdvn_R_MIXD_reg3.000.851.091.08
r naslvn_R_NASL_reg3.003.093.643.23
rcqlvn_RCQL_reg3.001.291.441.33
rougvn_ROUG_reg3.003.593.523.41
s authvn_S_AUTH_reg3.000.660.400.59
s cartvn_S_CART_reg3.003.954.013.70
s rantvn_S_RANT_reg3.002.421.791.91
dfluvn_DFLU_reg2.003.123.673.45
r chstvn_R_CHST_reg2.001.551.831.63
regsvn_REGS_reg2.001.251.291.23
smthvn_SMTH_reg2.001.511.511.44
vulnvn_VULN_reg2.001.091.651.52
warmvn_WARM_reg2.001.691.871.76
bkgnvn_BKGN_reg1.001.461.791.79
chnkvn_CHNK_reg1.002.611.972.12
coglvn_COGL_reg1.000.871.021.08
explvn_EXPL_reg1.000.790.850.81
s monovn_S_MONO_reg1.00-0.080.420.27
struvn_STRU_reg1.001.501.411.49
s asmrvn_S_ASMR_reg0.000.010.090.10
s formvn_S_FORM_reg0.00-0.29-0.16-0.24
s narrvn_S_NARR_reg0.00-0.16-0.13-0.18
s newsvn_S_NEWS_reg0.000.040.080.07
s stryvn_S_STRY_reg0.002.942.992.77
s techvn_S_TECH_reg0.00-0.420.500.27
s whisvn_S_WHIS_reg0.001.071.351.25
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.822.72
eiv_extra:Arousal2.662.83
eiv_extra:Authenticity2.702.80
eiv_extra:Background_Noise1.071.07
eiv_extra:Confident_vs._Hesitant1.371.31
eiv_extra:Gender-0.54-0.56
eiv_extra:High-Pitched_vs._Low-Pitched1.921.89
eiv_extra:Monotone_vs._Expressive2.802.99
eiv_extra:Recording_Quality1.691.91
eiv_extra:Serious_vs._Humorous2.022.02
eiv_extra:Soft_vs._Harsh0.180.10
eiv_extra:Submissive_vs._Dominant0.480.68
eiv_extra:Valence0.781.17
eiv_extra:Vulnerable_vs._Emotionally_Detached1.191.22
eiv_extra:Warm_vs._Cold0.230.34
eiv_extra:score_background_quality3.012.98
eiv_extra:score_content_enjoyment4.634.77
eiv_extra:score_overall_quality2.472.46
eiv_extra:score_speech_quality1.731.69
audiobox:CE4.624.95
audiobox:CU5.255.83
audiobox:PC3.272.71
audiobox:PQ6.556.81
dnsmos:SIG_raw3.593.72
dnsmos:BAK_raw2.522.62
dnsmos:OVRL_raw2.542.68
dnsmos:SIG3.283.38
dnsmos:BAK2.802.88
dnsmos:OVRL2.442.55
dnsmos:P808_MOS3.403.30
voiceclap_attribute:Affection0.640.83
voiceclap_attribute:Age1.902.02
voiceclap_attribute:Amusement2.232.13
voiceclap_attribute:Anger1.751.88
voiceclap_attribute:Arousal2.883.16
voiceclap_attribute:Astonishment_Surprise1.741.77
voiceclap_attribute:Authenticity2.852.85
voiceclap_attribute:Awe0.670.64
voiceclap_attribute:Background_Noise0.981.02
voiceclap_attribute:Bitterness0.710.80
voiceclap_attribute:Concentration0.370.27
voiceclap_attribute:Confident_vs._Hesitant1.341.35
voiceclap_attribute:Confusion0.960.95
voiceclap_attribute:Contemplation0.110.06
voiceclap_attribute:Contempt1.181.25
voiceclap_attribute:Contentment0.640.47
voiceclap_attribute:Disappointment0.730.88
voiceclap_attribute:Disgust0.880.98
voiceclap_attribute:Distress0.971.05
voiceclap_attribute:Doubt0.370.47
voiceclap_attribute:Elation1.641.55
voiceclap_attribute:Embarrassment0.700.66
voiceclap_attribute:Emotional_Numbness-0.11-0.05
voiceclap_attribute:Fatigue_Exhaustion0.280.24
voiceclap_attribute:Fear0.740.79
voiceclap_attribute:Gender-0.14-0.27
voiceclap_attribute:Helplessness0.510.54
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.861.83
voiceclap_attribute:Hope_Enthusiasm_Optimism1.341.35
voiceclap_attribute:Impatience_and_Irritability2.012.22
voiceclap_attribute:Infatuation0.500.52
voiceclap_attribute:Interest2.152.24
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness1.121.17
voiceclap_attribute:Jealousy_&_Envy0.540.61
voiceclap_attribute:Longing0.110.12
voiceclap_attribute:Malevolence_Malice1.171.24
voiceclap_attribute:Monotone_vs._Expressive2.932.99
voiceclap_attribute:Pain0.430.34
voiceclap_attribute:Pleasure_Ecstasy1.211.06
voiceclap_attribute:Pride0.730.69
voiceclap_attribute:Recording_Quality1.841.89
voiceclap_attribute:Relief0.770.74
voiceclap_attribute:Sadness0.260.29
voiceclap_attribute:Serious_vs._Humorous2.242.12
voiceclap_attribute:Sexual_Lust0.931.02
voiceclap_attribute:Shame0.360.29
voiceclap_attribute:Soft_vs._Harsh0.11-0.12
voiceclap_attribute:Sourness0.821.00
voiceclap_attribute:Submissive_vs._Dominant0.810.99
voiceclap_attribute:Teasing1.691.82
voiceclap_attribute:Thankfulness_Gratitude0.760.62
voiceclap_attribute:Triumph1.181.00
voiceclap_attribute:Valence0.40-0.01
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.041.05
voiceclap_attribute:Warm_vs._Cold0.340.10
voiceclap_attribute:duration17.3518.76
voiceclap_attribute:score_background_quality2.942.87
voiceclap_attribute:score_content_enjoyment4.844.85
voiceclap_attribute:score_overall_quality2.412.43
voiceclap_attribute:score_speech_quality1.891.84
voiceclap_attribute:talking_speed5.895.70
Reproducibility and API usage

Dataset UID: DE_0_QK1qUi_jM_W000007
Audio SHA-256: 2b81a697c6e2764125ff87d5ceea986171e8b7c6091e579d2c0dd7a54059a122
Gemini call: 7.51 s; input tokens 25550; cached tokens 25085; output tokens 1738.

S10-04 · de / real

Fear

6.5 s · Complete

Source: kartoffelphon (CC-BY-4.0) · de/real · chosen for high existing Fear score (z=4.72); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Ich sah an ihren blitzenden Augen, dass sie sich in Eifer geredet hatte. Sie durfte nicht wieder zu sich kommen, nahm ich mir vor.

Audio caption

A feminine-coded voice with a young adult presentation delivers a clear, composed literary narration in Standard German. The timbre is clean, bright, and resonant with predominantly oral and forward mask placement, backed by light chest warmth and smooth, low-roughness harmonicity. Articulation is crisp and precise, maintaining professional audiobook standards with steady, moderate tempo and clause-level breath chunking. Arousal is controlled and low-to-moderate, with neutral-to-reflective valence conveying focus, contemplation, and subtle narrative suspense. Between the descriptive observation and the internal tactical resolve, a discreet sharp inhalation marks the phrasing break. The recording is dry and clean with negligible background noise, resulting in a polished and genuine performance.

Director caption

Deliver this as an intimate, disciplined literary voiceover with focused, narrative clarity. Begin with a steady, descriptive pace, stressing the observation with controlled curiosity: "Ich sah an ihren blitzenden Augen, dass sie sich in Eifer geredet hatte." Insert a brief, quiet, but distinct sharp intake of breath to reset and build tension. Then drop into a slightly firmer, internally determined register, emphasizing the resolve without raising volume: "Sie durfte nicht wieder zu sich kommen, nahm ich mir vor."

Gemini bursts1
Base / Small count0.01 / 0.00
Genuineness (G / B / S)5 / 1.31 / 1.16
Burst blend (G / B / S)8 / 0.59 / 0.76
CPS (Base / Small)20.30 / 19.77
0 s6.5 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 3.48 s · End: 3.75 s · Sharp Inhale gasp
    A quick, soft, and focused sharp inhale through the mouth occurs during the pause between sentences, serving as a preparatory intake of breath and dramatic punctuation before the narrator outlines her next calculated intention; it is cleanly integrated into the flow of speech without disrupting the composed storytelling rhythm.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
clrtvn_CLRT_reg5.003.563.433.62
esthvn_ESTH_reg5.003.593.663.81
s narrvn_S_NARR_reg5.003.253.523.78
struvn_STRU_reg5.002.832.972.93
bkgnvn_BKGN_reg4.003.733.823.82
brgtvn_BRGT_reg4.002.982.933.00
focsvn_FOCS_reg4.002.422.782.87
harmvn_HARM_reg4.002.742.602.51
r mixdvn_R_MIXD_reg4.003.453.123.35
r oralvn_R_ORAL_reg4.003.042.842.94
rcqlvn_RCQL_reg4.004.024.264.17
regsvn_REGS_reg4.003.923.923.78
s formvn_S_FORM_reg4.002.873.323.35
s monovn_S_MONO_reg4.004.043.693.84
s stryvn_S_STRY_reg4.003.173.693.74
smthvn_SMTH_reg4.003.393.403.38
agevvn_AGEV_reg3.003.954.283.84
arshvn_ARSH_reg3.002.552.622.72
atckvn_ATCK_reg3.002.082.202.21
chnkvn_CHNK_reg3.002.582.772.62
darcvn_DARC_reg3.001.911.832.03
emphvn_EMPH_reg3.003.083.203.27
fullvn_FULL_reg3.002.962.802.89
r headvn_R_HEAD_reg3.002.812.852.90
r maskvn_R_MASK_reg3.002.302.362.48
rangvn_RANG_reg3.002.692.752.75
s authvn_S_AUTH_reg3.002.952.982.96
s dramvn_S_DRAM_reg3.002.643.023.15
stncvn_STNC_reg3.002.833.043.15
tempvn_TEMP_reg3.002.502.462.35
valnvn_VALN_reg3.002.332.052.13
valsvn_VALS_reg3.002.202.302.21
vflxvn_VFLX_reg3.002.582.602.53
warmvn_WARM_reg3.003.073.082.94
arouvn_AROU_reg2.002.462.602.54
r chstvn_R_CHST_reg2.002.902.872.75
r naslvn_R_NASL_reg2.002.852.942.99
r thrtvn_R_THRT_reg2.003.843.763.87
s convvn_S_CONV_reg2.003.433.213.28
s techvn_S_TECH_reg2.002.072.292.08
tensvn_TENS_reg2.001.682.012.12
coglvn_COGL_reg1.002.822.372.22
gendvn_GEND_reg1.001.251.281.29
metlvn_METL_reg1.001.781.701.64
respvn_RESP_reg1.002.742.792.68
rougvn_ROUG_reg1.001.691.831.74
s asmrvn_S_ASMR_reg1.003.943.363.46
s casuvn_S_CASU_reg1.003.222.972.84
s newsvn_S_NEWS_reg1.001.551.911.72
s playvn_S_PLAY_reg1.001.341.401.34
voltvn_VOLT_reg1.001.741.841.73
vulnvn_VULN_reg1.002.051.891.90
dfluvn_DFLU_reg0.002.441.791.75
explvn_EXPL_reg0.000.300.310.27
s cartvn_S_CART_reg0.000.950.861.28
s rantvn_S_RANT_reg0.00-0.210.400.55
s whisvn_S_WHIS_reg0.002.682.362.46
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.413.38
eiv_extra:Arousal1.291.29
eiv_extra:Authenticity2.912.84
eiv_extra:Background_Noise0.240.20
eiv_extra:Confident_vs._Hesitant1.321.20
eiv_extra:Gender1.301.63
eiv_extra:High-Pitched_vs._Low-Pitched1.571.49
eiv_extra:Monotone_vs._Expressive1.881.75
eiv_extra:Recording_Quality2.222.25
eiv_extra:Serious_vs._Humorous1.031.05
eiv_extra:Soft_vs._Harsh0.480.39
eiv_extra:Submissive_vs._Dominant0.150.16
eiv_extra:Valence-0.44-0.14
eiv_extra:Vulnerable_vs._Emotionally_Detached1.401.46
eiv_extra:Warm_vs._Cold0.020.01
eiv_extra:score_background_quality3.773.74
eiv_extra:score_content_enjoyment4.804.74
eiv_extra:score_overall_quality3.062.94
eiv_extra:score_speech_quality1.972.00
audiobox:CE5.405.63
audiobox:CU5.735.94
audiobox:PC1.661.68
audiobox:PQ6.897.13
dnsmos:SIG_raw4.094.09
dnsmos:BAK_raw4.174.21
dnsmos:OVRL_raw3.763.79
dnsmos:SIG3.593.61
dnsmos:BAK3.994.00
dnsmos:OVRL3.283.29
dnsmos:P808_MOS4.104.14
voiceclap_attribute:Affection1.040.87
voiceclap_attribute:Age3.333.41
voiceclap_attribute:Amusement0.090.13
voiceclap_attribute:Anger0.951.03
voiceclap_attribute:Arousal1.431.51
voiceclap_attribute:Astonishment_Surprise0.580.67
voiceclap_attribute:Authenticity3.103.08
voiceclap_attribute:Awe0.440.45
voiceclap_attribute:Background_Noise0.040.05
voiceclap_attribute:Bitterness0.570.61
voiceclap_attribute:Concentration1.321.23
voiceclap_attribute:Confident_vs._Hesitant1.321.31
voiceclap_attribute:Confusion1.081.06
voiceclap_attribute:Contemplation1.181.15
voiceclap_attribute:Contempt0.610.69
voiceclap_attribute:Contentment0.390.33
voiceclap_attribute:Disappointment1.061.02
voiceclap_attribute:Disgust0.630.69
voiceclap_attribute:Distress1.221.35
voiceclap_attribute:Doubt0.870.83
voiceclap_attribute:Elation0.240.31
voiceclap_attribute:Embarrassment0.270.31
voiceclap_attribute:Emotional_Numbness0.930.84
voiceclap_attribute:Fatigue_Exhaustion0.650.73
voiceclap_attribute:Fear0.740.88
voiceclap_attribute:Gender0.971.43
voiceclap_attribute:Helplessness0.890.95
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.581.59
voiceclap_attribute:Hope_Enthusiasm_Optimism0.360.41
voiceclap_attribute:Impatience_and_Irritability1.011.08
voiceclap_attribute:Infatuation0.530.42
voiceclap_attribute:Interest1.441.44
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.060.07
voiceclap_attribute:Jealousy_&_Envy0.700.80
voiceclap_attribute:Longing0.870.84
voiceclap_attribute:Malevolence_Malice0.510.56
voiceclap_attribute:Monotone_vs._Expressive1.551.66
voiceclap_attribute:Pain0.550.61
voiceclap_attribute:Pleasure_Ecstasy0.370.38
voiceclap_attribute:Pride0.460.49
voiceclap_attribute:Recording_Quality2.572.54
voiceclap_attribute:Relief1.471.57
voiceclap_attribute:Sadness1.301.22
voiceclap_attribute:Serious_vs._Humorous0.430.54
voiceclap_attribute:Sexual_Lust-0.060.03
voiceclap_attribute:Shame1.021.08
voiceclap_attribute:Soft_vs._Harsh0.500.51
voiceclap_attribute:Sourness0.560.56
voiceclap_attribute:Submissive_vs._Dominant0.280.38
voiceclap_attribute:Teasing0.190.25
voiceclap_attribute:Thankfulness_Gratitude1.671.57
voiceclap_attribute:Triumph0.540.61
voiceclap_attribute:Valence-0.72-0.55
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.511.42
voiceclap_attribute:Warm_vs._Cold0.070.03
voiceclap_attribute:duration7.168.74
voiceclap_attribute:score_background_quality3.603.76
voiceclap_attribute:score_content_enjoyment4.734.73
voiceclap_attribute:score_overall_quality2.892.99
voiceclap_attribute:score_speech_quality1.991.99
voiceclap_attribute:talking_speed18.3318.16
Reproducibility and API usage

Dataset UID: tr00204_003188
Audio SHA-256: c5f3e047490af4aaf064cfcb8272418a20cd0c52eaf447586b948abef87e27fb
Gemini call: 5.90 s; input tokens 25262; cached tokens 25085; output tokens 1419.

S10-05 · de / real

Contentment

20.6 s · Complete

Source: kartoffelphon (CC-BY-4.0) · de/real · chosen for high existing Contentment score (z=3.08); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · Eastern European

Transcript

S1: Other than that, it's really great to meet the fans here. They've been so, so nice. I I never know what to expect when I come to a new country. I I don't know if to expect if the fans know me or not, but everyone that has approached me and asked for a picture or even wanted to talk to me, they've all been so nice. So I'm very thankful to the German fans, and I hope that you guys enjoy the tournament here. S2: Thank you very much.

Audio caption

A press interview recording features a young-adult feminine-coded primary speaker speaking English with a distinct Eastern European accent, followed by a brief masculine-coded interviewer at the end. The primary speaker presents a bright, youthful, forward-placed tone centered in oral, mask, and upper-head resonance, balanced by warm and natural vocal clarity. The cadence is moderately brisk yet conversational, displaying natural slight hesitations and self-repairs while reflecting genuine spontaneous thought. Emotionally, the delivery radiates warm gratitude, contentment, and polite modesty, colored by an underlying smile voice as she describes interactions with fans. The background captures noticeable open-room ambient noise consistent with a stadium, arena, or press zone, but speech remains prominent and clear. At the very conclusion, a polite subdued chuckle seamlessly wraps up the exchange.

Director caption

Maintain an engaging, friendly, and modest interview persona with an audible smile. Start with an upbeat, open tone: "Other than that, it's really great to meet the fans here. They've been so, so nice." Slight hesitation and small natural syllable repetitions should show spontaneous reflection: "I I never know what to expect when I come to a new country. I I don't know if to expect if the fans know me or not..." Pick up momentum with genuine appreciation, keeping the melody bright and conversational: "...but everyone that has approached me and asked for a picture or even wanted to talk to me, they've all been so nice." Emphasize heartfelt gratitude and close warmly toward the audience: "So I'm very thankful to the German fans, and I hope that you guys enjoy the tournament here." As the interviewer concludes with "Thank you very much," let a soft, polite chuckle escape naturally right as the phrase ends.

Gemini bursts1
Base / Small count2.24 / 2.35
Genuineness (G / B / S)5 / 3.02 / 2.89
Burst blend (G / B / S)8 / 7.49 / 6.82
CPS (Base / Small)20.46 / 20.78
0 s20.6 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 20.35 s · End: 20.80 s · Chuckle laugh_soft
    A brief, light, closed-mouth chuckle and breathy laugh pulse occurs right at the tail of the interviewer's closing words 'Thank you very much', expressing polite affiliative warmth and closure in an organic press-scrum environment.
  • Existing S10 marker · Start: 0.02 s · End: 0.22 s
  • Existing S10 marker · Start: 4.26 s · End: 4.54 s
  • Base proposals: Start: 0.00 s · End: 0.22 s: Childlike Giggle 0.43, Ahem 0.33, Breathy Giggle 0.09; Start: 4.24 s · End: 4.52 s: Surprised Gasp 0.94, Ahem 0.01, Scream 0.00; Start: 12.00 s · End: 12.18 s: Ahem 0.76, Surprised Gasp 0.09, Breathy Giggle 0.02; Start: 15.66 s · End: 15.80 s: Ahem 0.93, Spitting 0.01, Snicker 0.00
  • Small proposals: Start: 0.00 s · End: 0.22 s: Childlike Giggle 0.47, Breathy Giggle 0.26, Ahem 0.17; Start: 4.26 s · End: 4.54 s: Surprised Gasp 0.92, Ahem 0.02, Scream 0.00; Start: 20.34 s · End: 20.52 s: Surprised Gasp 0.62, Ahem 0.29, Low Mumble 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
esthvn_ESTH_reg5.002.882.582.69
s convvn_S_CONV_reg5.003.673.393.61
valnvn_VALN_reg5.004.984.334.52
brgtvn_BRGT_reg4.003.513.173.32
clrtvn_CLRT_reg4.002.362.502.52
focsvn_FOCS_reg4.003.463.553.75
harmvn_HARM_reg4.003.022.692.85
r headvn_R_HEAD_reg4.002.782.762.81
r maskvn_R_MASK_reg4.002.762.772.89
r mixdvn_R_MIXD_reg4.001.381.091.18
r oralvn_R_ORAL_reg4.002.272.212.35
rangvn_RANG_reg4.003.653.463.67
regsvn_REGS_reg4.004.023.843.95
s casuvn_S_CASU_reg4.004.363.974.09
smthvn_SMTH_reg4.002.962.972.92
struvn_STRU_reg4.002.722.482.71
warmvn_WARM_reg4.002.161.881.96
agevvn_AGEV_reg3.001.752.102.07
arouvn_AROU_reg3.003.543.493.62
arshvn_ARSH_reg3.002.912.692.86
atckvn_ATCK_reg3.003.113.303.27
chnkvn_CHNK_reg3.005.085.054.87
darcvn_DARC_reg3.001.691.932.04
emphvn_EMPH_reg3.003.003.463.37
fullvn_FULL_reg3.001.881.871.90
rcqlvn_RCQL_reg3.002.772.382.51
s playvn_S_PLAY_reg3.003.953.733.62
stncvn_STNC_reg3.003.263.093.19
tempvn_TEMP_reg3.004.394.524.52
valsvn_VALS_reg3.003.993.803.88
vflxvn_VFLX_reg3.003.513.893.81
vulnvn_VULN_reg3.002.012.362.29
bkgnvn_BKGN_reg2.002.752.442.50
coglvn_COGL_reg2.000.861.021.05
dfluvn_DFLU_reg2.002.322.752.69
metlvn_METL_reg2.002.102.302.28
r chstvn_R_CHST_reg2.002.132.072.00
r naslvn_R_NASL_reg2.003.584.013.77
r thrtvn_R_THRT_reg2.001.381.451.58
respvn_RESP_reg2.002.843.202.94
s authvn_S_AUTH_reg2.001.441.511.59
s formvn_S_FORM_reg2.000.750.760.90
s narrvn_S_NARR_reg2.00-0.03-0.040.05
s stryvn_S_STRY_reg2.003.132.772.91
tensvn_TENS_reg2.001.622.232.14
voltvn_VOLT_reg2.003.043.143.14
gendvn_GEND_reg1.000.620.770.75
rougvn_ROUG_reg1.001.391.911.80
s asmrvn_S_ASMR_reg1.000.310.480.45
s cartvn_S_CART_reg1.002.462.642.74
s dramvn_S_DRAM_reg1.003.623.653.67
s monovn_S_MONO_reg1.002.492.021.95
s newsvn_S_NEWS_reg1.000.03-0.040.01
s techvn_S_TECH_reg1.001.901.291.51
explvn_EXPL_reg0.000.360.290.30
s rantvn_S_RANT_reg0.002.272.282.27
s whisvn_S_WHIS_reg0.000.840.760.75
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.842.91
eiv_extra:Arousal2.222.13
eiv_extra:Authenticity3.043.06
eiv_extra:Background_Noise0.810.76
eiv_extra:Confident_vs._Hesitant1.371.46
eiv_extra:Gender1.321.48
eiv_extra:High-Pitched_vs._Low-Pitched1.601.66
eiv_extra:Monotone_vs._Expressive2.762.70
eiv_extra:Recording_Quality2.492.70
eiv_extra:Serious_vs._Humorous1.351.36
eiv_extra:Soft_vs._Harsh0.700.75
eiv_extra:Submissive_vs._Dominant0.470.45
eiv_extra:Valence2.342.23
eiv_extra:Vulnerable_vs._Emotionally_Detached1.161.13
eiv_extra:Warm_vs._Cold1.081.18
eiv_extra:score_background_quality3.072.95
eiv_extra:score_content_enjoyment4.804.81
eiv_extra:score_overall_quality2.712.61
eiv_extra:score_speech_quality1.741.77
audiobox:CE5.025.19
audiobox:CU4.765.79
audiobox:PC2.501.98
audiobox:PQ5.766.07
dnsmos:SIG_raw3.753.97
dnsmos:BAK_raw2.883.65
dnsmos:OVRL_raw2.863.34
dnsmos:SIG3.403.54
dnsmos:BAK3.073.67
dnsmos:OVRL2.663.01
dnsmos:P808_MOS3.223.30
voiceclap_attribute:Affection1.511.12
voiceclap_attribute:Age2.882.69
voiceclap_attribute:Amusement1.170.91
voiceclap_attribute:Anger0.360.36
voiceclap_attribute:Arousal2.082.05
voiceclap_attribute:Astonishment_Surprise0.510.57
voiceclap_attribute:Authenticity3.253.13
voiceclap_attribute:Awe0.230.16
voiceclap_attribute:Background_Noise0.640.58
voiceclap_attribute:Bitterness0.230.26
voiceclap_attribute:Concentration0.841.04
voiceclap_attribute:Confident_vs._Hesitant1.271.14
voiceclap_attribute:Confusion0.300.37
voiceclap_attribute:Contemplation0.390.42
voiceclap_attribute:Contempt0.280.30
voiceclap_attribute:Contentment1.451.30
voiceclap_attribute:Disappointment0.620.63
voiceclap_attribute:Disgust0.390.34
voiceclap_attribute:Distress0.360.59
voiceclap_attribute:Doubt0.350.45
voiceclap_attribute:Elation1.661.53
voiceclap_attribute:Embarrassment0.760.54
voiceclap_attribute:Emotional_Numbness0.280.34
voiceclap_attribute:Fatigue_Exhaustion0.440.32
voiceclap_attribute:Fear0.420.34
voiceclap_attribute:Gender1.681.43
voiceclap_attribute:Helplessness0.230.24
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.501.49
voiceclap_attribute:Hope_Enthusiasm_Optimism2.292.42
voiceclap_attribute:Impatience_and_Irritability0.490.49
voiceclap_attribute:Infatuation0.530.40
voiceclap_attribute:Interest2.442.38
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.480.32
voiceclap_attribute:Jealousy_&_Envy0.690.51
voiceclap_attribute:Longing0.500.27
voiceclap_attribute:Malevolence_Malice0.470.48
voiceclap_attribute:Monotone_vs._Expressive2.942.48
voiceclap_attribute:Pain-0.030.12
voiceclap_attribute:Pleasure_Ecstasy1.221.00
voiceclap_attribute:Pride0.931.00
voiceclap_attribute:Recording_Quality2.872.97
voiceclap_attribute:Relief1.060.92
voiceclap_attribute:Sadness0.390.33
voiceclap_attribute:Serious_vs._Humorous1.661.26
voiceclap_attribute:Sexual_Lust0.230.32
voiceclap_attribute:Shame0.570.51
voiceclap_attribute:Soft_vs._Harsh0.780.60
voiceclap_attribute:Sourness0.520.64
voiceclap_attribute:Submissive_vs._Dominant0.290.40
voiceclap_attribute:Teasing0.910.84
voiceclap_attribute:Thankfulness_Gratitude1.941.47
voiceclap_attribute:Triumph0.700.74
voiceclap_attribute:Valence1.861.52
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.181.23
voiceclap_attribute:Warm_vs._Cold1.641.10
voiceclap_attribute:duration17.1319.65
voiceclap_attribute:score_background_quality3.123.09
voiceclap_attribute:score_content_enjoyment4.974.98
voiceclap_attribute:score_overall_quality2.712.66
voiceclap_attribute:score_speech_quality1.841.86
voiceclap_attribute:talking_speed15.8712.03
Reproducibility and API usage

Dataset UID: DE_oXdLYUahWdE_W000012
Audio SHA-256: ebb302143631be9dcb339fb9b2ff3b82013d0892760cce6f465a4bbc07710e75
Gemini call: 6.95 s; input tokens 25615; cached tokens 25085; output tokens 1611.

S10-06 · de / real

Disgust

3.6 s · Complete

Source: commonvoice (CC-0) · de/real · chosen for high existing Disgust score (z=6.72); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

German/English · Standard German / German-accented English

Transcript

Ekelhaft. Disgusting.

Audio caption

A single young-adult to mature masculine-coded voice articulates two isolated words—first in German, followed by its English equivalent—with precise, clipped diction. The vocal delivery sits in a low baritone register with notable throat and pharyngeal resonance, marked by moderate vocal tension and slight dry fry or roughness. Both words are uttered with a deliberate, cold affective tone centered on disgust, contempt, and sour disapproval, delivered without rushing or dramatic shouting. The pacing is segmented and measured, separating the terms with a wide pause. Articulation is sharp with firm consonant releases, typical of language-learning or dictionary prompt recordings. The technical acoustic space is clean and acoustically dry with minimal background interference.

Director caption

Deliver two isolated vocabulary items with cold, clinical revulsion and crisp diction. Set a grounded baritone register with firm pharyngeal tension. Speak the German word first with sharp, deliberate plosives: "Ekelhaft." Pause completely for roughly one and a half seconds, holding an expression of distaste without breaking into audible breathing or sighs. Then deliver the English translation with measured, low-arousal contempt, emphasizing the first syllable with a slightly pressed attack: "Disgusting."

Gemini bursts0
Base / Small count0.01 / 0.00
Genuineness (G / B / S)3 / 0.72 / 0.59
Burst blend (G / B / S)— / 2.91 / 2.84
CPS (Base / Small)3.75 / 4.66
0 s3.6 s
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
clrtvn_CLRT_reg5.004.835.145.06
gendvn_GEND_reg5.000.690.700.62
atckvn_ATCK_reg4.002.922.952.92
bkgnvn_BKGN_reg4.004.254.164.20
emphvn_EMPH_reg4.001.631.361.58
focsvn_FOCS_reg4.001.901.781.84
r thrtvn_R_THRT_reg4.002.612.492.68
rcqlvn_RCQL_reg4.004.874.824.82
s authvn_S_AUTH_reg4.002.302.142.29
s monovn_S_MONO_reg4.002.792.752.59
s techvn_S_TECH_reg4.003.053.333.35
stncvn_STNC_reg4.002.222.652.51
tensvn_TENS_reg4.001.301.391.47
agevvn_AGEV_reg3.001.881.991.93
arshvn_ARSH_reg3.002.832.973.18
brgtvn_BRGT_reg3.001.731.791.72
darcvn_DARC_reg3.002.572.462.52
esthvn_ESTH_reg3.002.892.922.93
fullvn_FULL_reg3.001.961.821.94
harmvn_HARM_reg3.003.033.083.18
metlvn_METL_reg3.001.141.231.23
r chstvn_R_CHST_reg3.001.661.711.83
r mixdvn_R_MIXD_reg3.001.661.621.78
r oralvn_R_ORAL_reg3.002.472.492.61
rougvn_ROUG_reg3.000.880.690.68
s dramvn_S_DRAM_reg3.001.351.221.36
s formvn_S_FORM_reg3.002.832.812.79
smthvn_SMTH_reg3.002.642.592.53
struvn_STRU_reg3.001.952.062.21
valsvn_VALS_reg3.002.762.592.59
vflxvn_VFLX_reg3.003.202.942.95
arouvn_AROU_reg2.001.761.811.68
r maskvn_R_MASK_reg2.002.132.242.41
r naslvn_R_NASL_reg2.003.032.892.87
rangvn_RANG_reg2.001.721.671.60
respvn_RESP_reg2.001.141.321.03
s narrvn_S_NARR_reg2.002.111.982.13
tempvn_TEMP_reg2.001.411.311.36
warmvn_WARM_reg2.002.652.672.63
chnkvn_CHNK_reg1.000.190.080.13
r headvn_R_HEAD_reg1.002.152.252.30
regsvn_REGS_reg1.003.653.533.93
s cartvn_S_CART_reg1.000.860.800.87
s casuvn_S_CASU_reg1.002.432.182.30
s convvn_S_CONV_reg1.001.441.661.33
s newsvn_S_NEWS_reg1.000.850.970.93
s rantvn_S_RANT_reg1.00-0.42-0.56-0.46
s stryvn_S_STRY_reg1.001.431.371.54
valnvn_VALN_reg1.002.982.843.08
voltvn_VOLT_reg1.000.720.550.70
vulnvn_VULN_reg1.001.731.911.77
coglvn_COGL_reg0.000.700.870.58
dfluvn_DFLU_reg0.000.250.250.02
explvn_EXPL_reg0.000.300.300.32
s asmrvn_S_ASMR_reg0.003.343.433.12
s playvn_S_PLAY_reg0.001.882.001.99
s whisvn_S_WHIS_reg0.003.403.023.33
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.233.19
eiv_extra:Arousal0.961.08
eiv_extra:Authenticity3.053.06
eiv_extra:Background_Noise-0.24-0.27
eiv_extra:Confident_vs._Hesitant0.640.71
eiv_extra:Gender0.871.39
eiv_extra:High-Pitched_vs._Low-Pitched1.161.09
eiv_extra:Monotone_vs._Expressive0.840.92
eiv_extra:Recording_Quality2.672.76
eiv_extra:Serious_vs._Humorous0.600.52
eiv_extra:Soft_vs._Harsh0.340.35
eiv_extra:Submissive_vs._Dominant0.280.28
eiv_extra:Valence-0.51-0.27
eiv_extra:Vulnerable_vs._Emotionally_Detached1.191.18
eiv_extra:Warm_vs._Cold0.120.13
eiv_extra:score_background_quality3.763.58
eiv_extra:score_content_enjoyment4.614.66
eiv_extra:score_overall_quality2.832.78
eiv_extra:score_speech_quality2.001.97
audiobox:CE5.005.19
audiobox:CU6.486.46
audiobox:PC1.241.47
audiobox:PQ7.347.47
dnsmos:SIG_raw3.824.03
dnsmos:BAK_raw4.334.39
dnsmos:OVRL_raw3.593.74
dnsmos:SIG3.433.60
dnsmos:BAK4.094.13
dnsmos:OVRL3.163.28
dnsmos:P808_MOS3.833.81
voiceclap_attribute:Affection0.580.74
voiceclap_attribute:Age3.143.26
voiceclap_attribute:Amusement0.130.27
voiceclap_attribute:Anger0.130.36
voiceclap_attribute:Arousal0.110.53
voiceclap_attribute:Astonishment_Surprise0.390.49
voiceclap_attribute:Authenticity2.953.05
voiceclap_attribute:Awe0.290.54
voiceclap_attribute:Background_Noise-0.04-0.04
voiceclap_attribute:Bitterness0.170.27
voiceclap_attribute:Concentration0.610.53
voiceclap_attribute:Confident_vs._Hesitant0.720.55
voiceclap_attribute:Confusion0.520.33
voiceclap_attribute:Contemplation0.330.38
voiceclap_attribute:Contempt0.090.17
voiceclap_attribute:Contentment0.490.61
voiceclap_attribute:Disappointment0.280.40
voiceclap_attribute:Disgust0.330.41
voiceclap_attribute:Distress0.390.77
voiceclap_attribute:Doubt0.570.59
voiceclap_attribute:Elation0.230.40
voiceclap_attribute:Embarrassment0.210.18
voiceclap_attribute:Emotional_Numbness1.130.94
voiceclap_attribute:Fatigue_Exhaustion0.640.62
voiceclap_attribute:Fear0.380.42
voiceclap_attribute:Gender0.971.27
voiceclap_attribute:Helplessness0.880.87
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.031.00
voiceclap_attribute:Hope_Enthusiasm_Optimism0.350.42
voiceclap_attribute:Impatience_and_Irritability0.130.43
voiceclap_attribute:Infatuation0.510.60
voiceclap_attribute:Interest0.510.58
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.190.21
voiceclap_attribute:Jealousy_&_Envy0.120.14
voiceclap_attribute:Longing0.480.57
voiceclap_attribute:Malevolence_Malice0.270.27
voiceclap_attribute:Monotone_vs._Expressive0.570.85
voiceclap_attribute:Pain0.340.40
voiceclap_attribute:Pleasure_Ecstasy0.360.39
voiceclap_attribute:Pride0.410.35
voiceclap_attribute:Recording_Quality2.962.88
voiceclap_attribute:Relief1.041.36
voiceclap_attribute:Sadness0.560.75
voiceclap_attribute:Serious_vs._Humorous0.450.79
voiceclap_attribute:Sexual_Lust0.130.19
voiceclap_attribute:Shame0.400.63
voiceclap_attribute:Soft_vs._Harsh0.690.60
voiceclap_attribute:Sourness0.100.25
voiceclap_attribute:Submissive_vs._Dominant0.040.23
voiceclap_attribute:Teasing0.230.23
voiceclap_attribute:Thankfulness_Gratitude0.661.13
voiceclap_attribute:Triumph0.280.31
voiceclap_attribute:Valence-0.030.27
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.471.39
voiceclap_attribute:Warm_vs._Cold0.250.34
voiceclap_attribute:duration5.054.76
voiceclap_attribute:score_background_quality3.633.71
voiceclap_attribute:score_content_enjoyment4.714.75
voiceclap_attribute:score_overall_quality2.682.76
voiceclap_attribute:score_speech_quality2.042.03
voiceclap_attribute:talking_speed6.808.49
Reproducibility and API usage

Dataset UID: DE_B00000_S09828_W000040
Audio SHA-256: 71a4d0da3e8fdcf6a038483d8805fed9fce4e658dc9930a52acc3d4d0bf26fd8
Gemini call: 5.21 s; input tokens 25189; cached tokens 25085; output tokens 1272.

S10-07 · de / real

Elation

13.6 s · Complete

Source: kartoffelphon (CC-BY-4.0) · de/real · chosen for high existing Elation score (z=3.12); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German · German (Standard/Colloquial)

Transcript

Ja, nächster Anime, der dritte in dieser Runde und diesmal geht es um Blumen. Hey, endlich mal ein unverbrauchtes Szenario, es geht um einen Blumenladen. Der Anime heißt Natsuyuki Rendezvous.

Audio caption

A single young adult masculine speaker delivers a lively, engaging commentary in German with standard conversational pronunciation. The vocal register sits comfortably in a warm, resonant baritone with balanced chest and oral presence, exhibiting moderate harmonicity and light organic roughness without distracting tension. The tempo is brisk yet well-controlled, maintaining natural chunking, crisp articulation, and dynamic, upbeat emphasis suited to an enthusiastic YouTube-style review or podcast format. Emotionally, the delivery carries prominent amusement, playful sarcasm, and positive interest, marked by cheerful inflections on words like 'Blumen' and 'Hey'. A slight studio room reflection and subtle room tone are audible in the background, but the overall technical fidelity is clean, professional, and well-balanced. No distinct non-speech paralinguistic vocal bursts occur.

Director caption

Open with an energetic, drawn-out call, letting your pitch rise in an enthusiastic, broadcast-like greeting: "Ja, nächster Anime, der dritte in dieser Runde und diesmal geht es um Blumen." Keep the pacing brisk and conversational, then exaggerate your cheerfulness on the interjection with an ironic, slightly amused bite: "Hey, endlich mal ein unverbrauchtes Szenario, es geht um einen Blumenladen." Transition smoothly into an informative, explanatory tone, dropping slightly in pitch while maintaining clear articulation and steady projection as you conclude: "Der Anime heißt Natsuyuki Rendezvous."

Gemini bursts0
Base / Small count1.22 / 1.19
Genuineness (G / B / S)5 / 4.48 / 4.26
Burst blend (G / B / S)— / 2.74 / 2.67
CPS (Base / Small)14.49 / 14.68
0 s13.6 s
Event captions and top-3 Whisper classes
  • Existing S10 marker · Start: 0.30 s · End: 0.84 s
  • Base proposals: Start: 0.28 s · End: 0.66 s: Ahem 0.84, Low Mumble 0.08, Surprised Gasp 0.01; Start: 0.56 s · End: 0.90 s: Surprised Gasp 0.81, Ahem 0.08, Scream 0.01; Start: 0.68 s · End: 1.00 s: Surprised Gasp 0.68, Exhausted Groan 0.14, Ahem 0.09; Start: 0.80 s · End: 1.06 s: Exhausted Groan 0.28, Ahem 0.27, Surprised Gasp 0.20; Start: 0.86 s · End: 1.10 s: Ahem 0.58, Surprised Gasp 0.11, Exhausted Groan 0.10; Start: 0.98 s · End: 1.20 s: Low Mumble 0.55, Ahem 0.33, Exhausted Groan 0.03
  • Small proposals: Start: 0.30 s · End: 0.70 s: Ahem 0.60, Surprised Gasp 0.19, Low Mumble 0.15; Start: 0.62 s · End: 0.88 s: Surprised Gasp 0.72, Ahem 0.19, Scream 0.01; Start: 0.68 s · End: 0.92 s: Surprised Gasp 0.68, Ahem 0.16, Exhausted Groan 0.05; Start: 0.74 s · End: 1.02 s: Surprised Gasp 0.39, Exhausted Groan 0.33, Ahem 0.11; Start: 0.80 s · End: 1.06 s: Exhausted Groan 0.29, Ahem 0.21, Low Mumble 0.17; Start: 0.94 s · End: 1.14 s: Low Mumble 0.45, Ahem 0.36, Exhausted Groan 0.07; Start: 1.00 s · End: 1.18 s: Low Mumble 0.66, Ahem 0.22, Exhausted Groan 0.04
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.005.284.845.05
arouvn_AROU_reg4.003.593.413.56
atckvn_ATCK_reg4.003.143.193.23
clrtvn_CLRT_reg4.001.661.771.63
emphvn_EMPH_reg4.004.393.794.02
esthvn_ESTH_reg4.001.902.112.05
focsvn_FOCS_reg4.002.642.752.65
fullvn_FULL_reg4.001.191.731.66
harmvn_HARM_reg4.002.912.702.81
r chstvn_R_CHST_reg4.003.142.943.07
r mixdvn_R_MIXD_reg4.001.201.361.28
r oralvn_R_ORAL_reg4.002.562.542.44
rangvn_RANG_reg4.004.804.314.22
rcqlvn_RCQL_reg4.001.811.992.00
s casuvn_S_CASU_reg4.006.065.295.48
s convvn_S_CONV_reg4.004.504.644.28
s playvn_S_PLAY_reg4.005.004.704.65
smthvn_SMTH_reg4.001.861.961.92
stncvn_STNC_reg4.003.543.313.34
struvn_STRU_reg4.001.532.031.93
tempvn_TEMP_reg4.003.182.923.05
valnvn_VALN_reg4.005.074.874.83
warmvn_WARM_reg4.002.322.262.43
agevvn_AGEV_reg3.002.882.632.86
arshvn_ARSH_reg3.002.723.143.00
bkgnvn_BKGN_reg3.002.212.112.08
brgtvn_BRGT_reg3.001.371.451.50
chnkvn_CHNK_reg3.002.682.502.64
darcvn_DARC_reg3.003.102.782.80
r maskvn_R_MASK_reg3.003.103.103.09
r thrtvn_R_THRT_reg3.003.443.353.57
s authvn_S_AUTH_reg3.000.520.861.13
s narrvn_S_NARR_reg3.00-0.04-0.040.08
valsvn_VALS_reg3.004.464.454.47
vflxvn_VFLX_reg3.001.241.591.66
r headvn_R_HEAD_reg2.002.612.852.80
r naslvn_R_NASL_reg2.003.873.724.06
respvn_RESP_reg2.002.241.451.94
rougvn_ROUG_reg2.002.722.602.75
s cartvn_S_CART_reg2.003.263.013.25
s dramvn_S_DRAM_reg2.004.383.714.17
s stryvn_S_STRY_reg2.003.613.233.37
s techvn_S_TECH_reg2.000.170.460.37
tensvn_TENS_reg2.001.601.401.86
voltvn_VOLT_reg2.003.413.193.31
coglvn_COGL_reg1.001.601.511.37
dfluvn_DFLU_reg1.003.373.393.36
metlvn_METL_reg1.003.053.033.11
regsvn_REGS_reg1.001.000.981.00
s formvn_S_FORM_reg1.00-0.16-0.12-0.11
s monovn_S_MONO_reg1.001.671.621.80
s newsvn_S_NEWS_reg1.00-0.09-0.16-0.08
s rantvn_S_RANT_reg1.001.521.211.54
vulnvn_VULN_reg1.002.552.472.36
explvn_EXPL_reg0.000.550.460.42
s asmrvn_S_ASMR_reg0.000.220.040.08
s whisvn_S_WHIS_reg0.000.690.470.68
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.782.84
eiv_extra:Arousal2.612.61
eiv_extra:Authenticity2.852.86
eiv_extra:Background_Noise0.880.92
eiv_extra:Confident_vs._Hesitant1.281.24
eiv_extra:Gender-0.62-0.79
eiv_extra:High-Pitched_vs._Low-Pitched1.751.79
eiv_extra:Monotone_vs._Expressive2.932.83
eiv_extra:Recording_Quality2.082.12
eiv_extra:Serious_vs._Humorous2.062.08
eiv_extra:Soft_vs._Harsh0.480.30
eiv_extra:Submissive_vs._Dominant0.730.81
eiv_extra:Valence2.051.99
eiv_extra:Vulnerable_vs._Emotionally_Detached1.251.20
eiv_extra:Warm_vs._Cold0.960.64
eiv_extra:score_background_quality3.203.30
eiv_extra:score_content_enjoyment4.744.73
eiv_extra:score_overall_quality2.692.79
eiv_extra:score_speech_quality1.841.84
audiobox:CE5.004.93
audiobox:CU5.275.20
audiobox:PC1.681.74
audiobox:PQ7.157.14
dnsmos:SIG_raw3.944.03
dnsmos:BAK_raw2.963.39
dnsmos:OVRL_raw3.003.30
dnsmos:SIG3.513.56
dnsmos:BAK3.113.42
dnsmos:OVRL2.762.96
dnsmos:P808_MOS3.943.94
voiceclap_attribute:Affection1.261.16
voiceclap_attribute:Age2.482.91
voiceclap_attribute:Amusement1.781.88
voiceclap_attribute:Anger0.490.33
voiceclap_attribute:Arousal2.282.21
voiceclap_attribute:Astonishment_Surprise0.910.96
voiceclap_attribute:Authenticity2.852.83
voiceclap_attribute:Awe0.670.62
voiceclap_attribute:Background_Noise0.860.83
voiceclap_attribute:Bitterness0.200.20
voiceclap_attribute:Concentration0.350.47
voiceclap_attribute:Confident_vs._Hesitant1.751.60
voiceclap_attribute:Confusion0.930.74
voiceclap_attribute:Contemplation0.490.42
voiceclap_attribute:Contempt0.370.43
voiceclap_attribute:Contentment1.241.15
voiceclap_attribute:Disappointment0.240.20
voiceclap_attribute:Disgust0.470.45
voiceclap_attribute:Distress0.250.09
voiceclap_attribute:Doubt0.400.37
voiceclap_attribute:Elation1.761.93
voiceclap_attribute:Embarrassment0.730.76
voiceclap_attribute:Emotional_Numbness0.030.16
voiceclap_attribute:Fatigue_Exhaustion0.350.31
voiceclap_attribute:Fear0.380.26
voiceclap_attribute:Gender-0.72-0.85
voiceclap_attribute:Helplessness0.15-0.03
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.791.97
voiceclap_attribute:Hope_Enthusiasm_Optimism1.761.81
voiceclap_attribute:Impatience_and_Irritability0.510.31
voiceclap_attribute:Infatuation0.980.84
voiceclap_attribute:Interest2.392.36
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness1.181.18
voiceclap_attribute:Jealousy_&_Envy0.310.26
voiceclap_attribute:Longing0.420.38
voiceclap_attribute:Malevolence_Malice0.440.41
voiceclap_attribute:Monotone_vs._Expressive3.042.80
voiceclap_attribute:Pain0.05-0.00
voiceclap_attribute:Pleasure_Ecstasy1.261.34
voiceclap_attribute:Pride0.910.94
voiceclap_attribute:Recording_Quality2.062.15
voiceclap_attribute:Relief0.990.94
voiceclap_attribute:Sadness0.090.02
voiceclap_attribute:Serious_vs._Humorous2.502.35
voiceclap_attribute:Sexual_Lust0.860.81
voiceclap_attribute:Shame0.320.32
voiceclap_attribute:Soft_vs._Harsh0.520.35
voiceclap_attribute:Sourness0.350.33
voiceclap_attribute:Submissive_vs._Dominant0.620.65
voiceclap_attribute:Teasing1.221.40
voiceclap_attribute:Thankfulness_Gratitude1.631.64
voiceclap_attribute:Triumph0.911.02
voiceclap_attribute:Valence2.011.97
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.911.12
voiceclap_attribute:Warm_vs._Cold1.210.96
voiceclap_attribute:duration13.7414.65
voiceclap_attribute:score_background_quality3.153.30
voiceclap_attribute:score_content_enjoyment4.844.88
voiceclap_attribute:score_overall_quality2.682.80
voiceclap_attribute:score_speech_quality1.891.87
voiceclap_attribute:talking_speed8.388.65
Reproducibility and API usage

Dataset UID: tr00131_003661
Audio SHA-256: 83781862df8c629693be7704f77e5539ca76ddd1c289579ed26cf5866d28d238
Gemini call: 6.03 s; input tokens 25440; cached tokens 25085; output tokens 1352.

S10-08 · en / real

Awe

3.9 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Awe score (z=6.67); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

That looks wonderful. Wow.

Audio caption

A single young-adult feminine-coded speaker delivers a short, warmly impressed reaction in standard General American English. The timbre is clean, resonant, and balanced with bright head and mask placement, supported by smooth low-mid warmth and virtually no grain. Pacing is slow and relaxed, featuring deliberate phrasing that highlights 'wonderful' with a rising and floating melodic contour. An organic pause filled with an appreciative, breathy sigh and a subtle preparatory intake precedes a hushed, breathy exclamation of wonder. The recording is technically crisp and free of background noise, conveying genuine, unforced admiration and quiet awe.

Director caption

Deliver the phrase with genuine, admiring warmth and an audible smile in the tone. Start in an open, bright mezzo range: "That looks wonderful," stretching out the syllables of 'wonderful' with an expressive, melodic lift that gently glides downward at the end. After finishing the word, let out a soft, relaxed Contented Sigh, followed immediately by a delicate Sharp Inhale through slightly parted lips. Then, drop into a hushed, breathy, awestruck half-whisper to utter: "Wow."

Gemini bursts2
Base / Small count0.01 / 0.00
Genuineness (G / B / S)5 / 3.85 / 3.78
Burst blend (G / B / S)8 / 5.52 / 5.00
CPS (Base / Small)6.78 / 6.59
0 s3.9 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 2.22 s · End: 2.65 s · Contented Sigh sigh_pos
    An audible, breathy contented sigh occurs in the pause immediately following 'wonderful,' exhaling smoothly with gentle vocal cord relaxation before transitioning toward the concluding expression of wonder.
  • Gemini · Start: 2.66 s · End: 3.02 s · Sharp Inhale gasp
    A quick, soft intake of breath follows the sigh in the silence right before 'Wow', reflecting preparatory anticipation and awed intake of air with clear breathy texture.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
esthvn_ESTH_reg5.002.321.912.00
valnvn_VALN_reg5.002.262.412.16
bkgnvn_BKGN_reg4.002.652.562.62
brgtvn_BRGT_reg4.002.261.941.94
clrtvn_CLRT_reg4.001.110.870.87
emphvn_EMPH_reg4.001.781.731.53
focsvn_FOCS_reg4.001.241.261.34
harmvn_HARM_reg4.001.762.371.97
r headvn_R_HEAD_reg4.002.662.042.22
r maskvn_R_MASK_reg4.002.101.751.71
r mixdvn_R_MIXD_reg4.000.770.640.98
r oralvn_R_ORAL_reg4.002.101.871.94
rangvn_RANG_reg4.003.883.483.53
rcqlvn_RCQL_reg4.002.512.392.43
regsvn_REGS_reg4.003.412.842.73
s casuvn_S_CASU_reg4.005.545.255.35
s convvn_S_CONV_reg4.004.664.074.69
smthvn_SMTH_reg4.001.651.471.45
struvn_STRU_reg4.001.390.710.90
warmvn_WARM_reg4.002.302.112.32
agevvn_AGEV_reg3.002.041.832.25
arouvn_AROU_reg3.001.411.621.45
atckvn_ATCK_reg3.001.491.851.51
fullvn_FULL_reg3.001.581.061.21
s dramvn_S_DRAM_reg3.003.743.663.62
s playvn_S_PLAY_reg3.003.673.383.71
stncvn_STNC_reg3.001.731.561.61
valsvn_VALS_reg3.001.862.442.28
vulnvn_VULN_reg3.004.163.854.01
arshvn_ARSH_reg2.002.382.492.44
chnkvn_CHNK_reg2.001.190.470.81
darcvn_DARC_reg2.002.182.592.59
r chstvn_R_CHST_reg2.001.181.251.15
r naslvn_R_NASL_reg2.002.933.303.20
r thrtvn_R_THRT_reg2.002.272.152.20
respvn_RESP_reg2.003.873.853.86
s asmrvn_S_ASMR_reg2.000.250.290.22
s narrvn_S_NARR_reg2.001.641.301.34
s stryvn_S_STRY_reg2.004.063.403.55
s whisvn_S_WHIS_reg2.003.012.392.79
tempvn_TEMP_reg2.000.540.690.48
tensvn_TENS_reg2.000.950.890.93
vflxvn_VFLX_reg2.002.492.932.86
voltvn_VOLT_reg2.003.303.283.41
coglvn_COGL_reg1.003.362.753.17
gendvn_GEND_reg1.000.460.420.60
metlvn_METL_reg1.000.951.131.04
rougvn_ROUG_reg1.002.062.362.14
s authvn_S_AUTH_reg1.000.280.210.03
s cartvn_S_CART_reg1.002.563.222.86
s formvn_S_FORM_reg1.000.200.270.06
s monovn_S_MONO_reg1.002.552.492.32
s techvn_S_TECH_reg1.000.27-0.000.09
dfluvn_DFLU_reg0.003.062.833.06
explvn_EXPL_reg0.000.370.340.31
s newsvn_S_NEWS_reg0.000.24-0.000.20
s rantvn_S_RANT_reg0.001.111.121.17
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.103.07
eiv_extra:Arousal1.971.85
eiv_extra:Authenticity3.013.08
eiv_extra:Background_Noise0.380.50
eiv_extra:Confident_vs._Hesitant1.261.34
eiv_extra:Gender1.041.30
eiv_extra:High-Pitched_vs._Low-Pitched1.521.58
eiv_extra:Monotone_vs._Expressive2.362.40
eiv_extra:Recording_Quality2.402.49
eiv_extra:Serious_vs._Humorous1.611.43
eiv_extra:Soft_vs._Harsh0.921.10
eiv_extra:Submissive_vs._Dominant0.390.25
eiv_extra:Valence2.382.35
eiv_extra:Vulnerable_vs._Emotionally_Detached1.171.01
eiv_extra:Warm_vs._Cold1.131.17
eiv_extra:score_background_quality2.933.10
eiv_extra:score_content_enjoyment4.544.37
eiv_extra:score_overall_quality2.222.36
eiv_extra:score_speech_quality1.901.83
audiobox:CE4.274.27
audiobox:CU4.294.45
audiobox:PC1.641.59
audiobox:PQ4.885.06
dnsmos:SIG_raw3.303.17
dnsmos:BAK_raw3.313.37
dnsmos:OVRL_raw2.762.70
dnsmos:SIG3.123.07
dnsmos:BAK3.433.45
dnsmos:OVRL2.592.56
dnsmos:P808_MOS2.963.07
voiceclap_attribute:Affection1.221.33
voiceclap_attribute:Age2.332.66
voiceclap_attribute:Amusement1.211.18
voiceclap_attribute:Anger0.250.46
voiceclap_attribute:Arousal1.791.77
voiceclap_attribute:Astonishment_Surprise2.072.18
voiceclap_attribute:Authenticity3.053.03
voiceclap_attribute:Awe1.281.37
voiceclap_attribute:Background_Noise0.370.46
voiceclap_attribute:Bitterness0.270.43
voiceclap_attribute:Concentration0.050.02
voiceclap_attribute:Confident_vs._Hesitant1.751.88
voiceclap_attribute:Confusion0.751.10
voiceclap_attribute:Contemplation0.320.63
voiceclap_attribute:Contempt0.400.49
voiceclap_attribute:Contentment0.880.92
voiceclap_attribute:Disappointment0.600.64
voiceclap_attribute:Disgust0.550.62
voiceclap_attribute:Distress1.081.07
voiceclap_attribute:Doubt0.690.57
voiceclap_attribute:Elation1.041.05
voiceclap_attribute:Embarrassment0.540.66
voiceclap_attribute:Emotional_Numbness0.390.31
voiceclap_attribute:Fatigue_Exhaustion0.710.63
voiceclap_attribute:Fear0.720.66
voiceclap_attribute:Gender0.961.07
voiceclap_attribute:Helplessness1.010.91
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.321.43
voiceclap_attribute:Hope_Enthusiasm_Optimism0.820.79
voiceclap_attribute:Impatience_and_Irritability0.800.91
voiceclap_attribute:Infatuation0.950.93
voiceclap_attribute:Interest1.091.21
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.520.81
voiceclap_attribute:Jealousy_&_Envy0.360.57
voiceclap_attribute:Longing0.780.82
voiceclap_attribute:Malevolence_Malice0.390.42
voiceclap_attribute:Monotone_vs._Expressive2.212.31
voiceclap_attribute:Pain0.580.61
voiceclap_attribute:Pleasure_Ecstasy1.020.98
voiceclap_attribute:Pride-0.10-0.07
voiceclap_attribute:Recording_Quality2.172.08
voiceclap_attribute:Relief1.611.78
voiceclap_attribute:Sadness1.031.17
voiceclap_attribute:Serious_vs._Humorous1.721.78
voiceclap_attribute:Sexual_Lust0.680.72
voiceclap_attribute:Shame0.390.52
voiceclap_attribute:Soft_vs._Harsh1.040.95
voiceclap_attribute:Sourness0.430.41
voiceclap_attribute:Submissive_vs._Dominant0.170.14
voiceclap_attribute:Teasing0.881.03
voiceclap_attribute:Thankfulness_Gratitude1.181.15
voiceclap_attribute:Triumph-0.010.19
voiceclap_attribute:Valence0.610.32
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.680.79
voiceclap_attribute:Warm_vs._Cold0.820.78
voiceclap_attribute:duration3.324.21
voiceclap_attribute:score_background_quality3.133.13
voiceclap_attribute:score_content_enjoyment4.594.56
voiceclap_attribute:score_overall_quality2.272.33
voiceclap_attribute:score_speech_quality1.991.97
voiceclap_attribute:talking_speed5.495.23
Reproducibility and API usage

Dataset UID: EN_3wUfLJvu-PY_W000571
Audio SHA-256: fcbd3a6d0f4b5b5cb140e200cab850d436cf4e110a3468e455435208b4205483
Gemini call: 5.89 s; input tokens 25197; cached tokens 25085; output tokens 1448.

S10-09 · en / real

Confusion

14.6 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Confusion score (z=5.67); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

S1: have a call right now. S2: Yeah, yeah, I I I know. Well, I can't for some reason, I can't remember the specifics of why or how that went down there, and I'm I'm going to pull it up as we sit here just because I'm going, wait, what the heck did happen there? What am I missing here? So, I'm going to get

Audio caption

The recording features two speakers, dominated by an adult masculine-coded speaker delivering a spontaneous, conversational explanation with a General American accent. The dominant speaker possesses a baritone pitch center with rich chest and oral resonance, moderate warmth, and solid acoustic fullness. Articulation is crisp and clear despite the conversational pace, featuring organic disfluencies, false starts, and real-time cognitive searching pauses. The rhythm is brisk yet conversational, marked by moderate pitch excursions and natural emphatic stress. Affectively, the performance conveys active interest, slight confusion, and thoughtful curiosity, lightened by mild amusement. A short introductory burst from another speaker trails off just as the main speaker interjects with a brief chuckle of recognition. The studio-quality recording maintains clean background isolation and high fidelity, exhibiting an authentic, unscripted conversational flow.

Director caption

Start by interrupting quickly over the other voice with a short suppressed chuckle of acknowledgment, keeping energy brisk and responsive: "Yeah, yeah, I I I know." Speak with rapid forward momentum and natural hesitation, lowering into a thoughtful, slightly perplexed tone: "Well, I can't for some reason, I can't remember the specifics of why or how that went down there,". Re-engage with an active, problem-solving cadence, emphasizing the intention to check facts: "and I'm I'm going to pull it up as we sit here just because I'm going,". Elevate the pitch dynamically into an animated, self-directed rhetorical question with clear vocal emphasis and mild exasperated wonder: "wait, what the heck did happen there? What am I missing here?". Conclude smoothly by returning to a grounded, pragmatic pace: "So, I'm going to get" before trailing off.

Gemini bursts1
Base / Small count0.33 / 0.96
Genuineness (G / B / S)5 / 4.83 / 4.90
Burst blend (G / B / S)8 / 9.39 / 9.57
CPS (Base / Small)16.83 / 16.61
0 s14.6 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.45 s · End: 0.75 s · Chuckle laugh_soft
    A brief, low-pitched chuckle occurs right as the primary speaker interrupts and begins speaking over the trailing end of the previous prompt, expressing good-natured acknowledgment and mild amusement before transitioning into conversational stuttered speech.
  • Existing S10 marker · Start: 1.74 s · End: 1.92 s
  • Base proposals: Start: 1.74 s · End: 1.92 s: Ahem 0.88, Chuckle 0.01, Nervous Giggle 0.01
  • Small proposals: Start: 1.74 s · End: 1.92 s: Ahem 0.93, Spitting 0.01, Snicker 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.724.584.50
s convvn_S_CONV_reg5.004.864.975.02
arouvn_AROU_reg4.003.793.693.76
atckvn_ATCK_reg4.002.542.622.42
bkgnvn_BKGN_reg4.002.222.432.43
brgtvn_BRGT_reg4.002.042.172.10
clrtvn_CLRT_reg4.002.792.962.79
emphvn_EMPH_reg4.003.283.333.26
esthvn_ESTH_reg4.002.382.632.53
focsvn_FOCS_reg4.003.513.603.42
fullvn_FULL_reg4.003.253.183.12
harmvn_HARM_reg4.002.782.652.66
r chstvn_R_CHST_reg4.002.372.602.67
r mixdvn_R_MIXD_reg4.002.602.402.26
r oralvn_R_ORAL_reg4.002.282.212.17
rangvn_RANG_reg4.003.463.313.22
rcqlvn_RCQL_reg4.003.133.253.31
s casuvn_S_CASU_reg4.005.044.784.82
stncvn_STNC_reg4.003.393.433.38
tempvn_TEMP_reg4.002.862.892.99
warmvn_WARM_reg4.002.392.512.59
agevvn_AGEV_reg3.003.142.933.03
arshvn_ARSH_reg3.003.363.483.59
chnkvn_CHNK_reg3.003.203.173.15
coglvn_COGL_reg3.002.061.942.01
darcvn_DARC_reg3.001.962.091.98
dfluvn_DFLU_reg3.003.533.553.51
r maskvn_R_MASK_reg3.002.572.712.60
r thrtvn_R_THRT_reg3.001.961.651.64
s authvn_S_AUTH_reg3.002.202.032.18
s playvn_S_PLAY_reg3.003.453.573.65
s stryvn_S_STRY_reg3.003.033.002.99
smthvn_SMTH_reg3.002.692.812.89
struvn_STRU_reg3.002.462.422.48
valnvn_VALN_reg3.003.183.443.53
valsvn_VALS_reg3.003.023.073.14
vflxvn_VFLX_reg3.002.452.362.48
metlvn_METL_reg2.001.851.791.71
r headvn_R_HEAD_reg2.002.342.312.27
r naslvn_R_NASL_reg2.002.332.192.24
respvn_RESP_reg2.001.561.271.23
rougvn_ROUG_reg2.002.232.112.01
s dramvn_S_DRAM_reg2.003.183.042.88
s narrvn_S_NARR_reg2.000.360.240.29
s newsvn_S_NEWS_reg2.000.010.130.02
s techvn_S_TECH_reg2.001.901.391.39
tensvn_TENS_reg2.001.241.071.07
voltvn_VOLT_reg2.002.742.832.73
vulnvn_VULN_reg2.002.292.532.58
regsvn_REGS_reg1.001.361.441.21
s formvn_S_FORM_reg1.000.830.710.73
s monovn_S_MONO_reg1.001.251.331.11
s rantvn_S_RANT_reg1.002.702.582.69
explvn_EXPL_reg0.000.190.160.13
s asmrvn_S_ASMR_reg0.000.040.13-0.08
s cartvn_S_CART_reg0.001.000.580.51
s whisvn_S_WHIS_reg0.000.790.260.42
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.083.17
eiv_extra:Arousal1.901.84
eiv_extra:Authenticity2.872.89
eiv_extra:Background_Noise0.840.80
eiv_extra:Confident_vs._Hesitant1.971.95
eiv_extra:Gender-0.52-0.63
eiv_extra:High-Pitched_vs._Low-Pitched1.831.81
eiv_extra:Monotone_vs._Expressive2.712.88
eiv_extra:Recording_Quality2.312.29
eiv_extra:Serious_vs._Humorous1.321.29
eiv_extra:Soft_vs._Harsh0.270.19
eiv_extra:Submissive_vs._Dominant0.420.49
eiv_extra:Valence-0.07-0.18
eiv_extra:Vulnerable_vs._Emotionally_Detached1.241.07
eiv_extra:Warm_vs._Cold0.190.37
eiv_extra:score_background_quality3.533.45
eiv_extra:score_content_enjoyment4.944.97
eiv_extra:score_overall_quality3.032.92
eiv_extra:score_speech_quality1.811.82
audiobox:CE5.906.13
audiobox:CU6.647.03
audiobox:PC1.921.94
audiobox:PQ7.467.66
dnsmos:SIG_raw4.254.37
dnsmos:BAK_raw3.574.03
dnsmos:OVRL_raw3.593.88
dnsmos:SIG3.713.76
dnsmos:BAK3.613.90
dnsmos:OVRL3.173.36
dnsmos:P808_MOS4.024.14
voiceclap_attribute:Affection0.400.28
voiceclap_attribute:Age3.153.08
voiceclap_attribute:Amusement0.990.84
voiceclap_attribute:Anger0.590.74
voiceclap_attribute:Arousal1.971.99
voiceclap_attribute:Astonishment_Surprise1.441.38
voiceclap_attribute:Authenticity3.012.98
voiceclap_attribute:Awe0.600.49
voiceclap_attribute:Background_Noise0.670.54
voiceclap_attribute:Bitterness0.370.42
voiceclap_attribute:Concentration0.741.08
voiceclap_attribute:Confident_vs._Hesitant2.302.46
voiceclap_attribute:Confusion1.421.37
voiceclap_attribute:Contemplation1.051.26
voiceclap_attribute:Contempt0.340.51
voiceclap_attribute:Contentment0.520.34
voiceclap_attribute:Disappointment0.840.87
voiceclap_attribute:Disgust0.460.47
voiceclap_attribute:Distress0.800.82
voiceclap_attribute:Doubt0.991.04
voiceclap_attribute:Elation1.090.86
voiceclap_attribute:Embarrassment0.870.81
voiceclap_attribute:Emotional_Numbness0.440.47
voiceclap_attribute:Fatigue_Exhaustion0.500.49
voiceclap_attribute:Fear0.680.58
voiceclap_attribute:Gender-0.58-0.31
voiceclap_attribute:Helplessness0.580.72
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.671.63
voiceclap_attribute:Hope_Enthusiasm_Optimism1.511.21
voiceclap_attribute:Impatience_and_Irritability1.011.13
voiceclap_attribute:Infatuation0.440.43
voiceclap_attribute:Interest2.362.29
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.260.14
voiceclap_attribute:Jealousy_&_Envy0.640.52
voiceclap_attribute:Longing0.500.49
voiceclap_attribute:Malevolence_Malice0.230.34
voiceclap_attribute:Monotone_vs._Expressive3.022.84
voiceclap_attribute:Pain0.270.32
voiceclap_attribute:Pleasure_Ecstasy0.620.52
voiceclap_attribute:Pride0.790.67
voiceclap_attribute:Recording_Quality2.312.40
voiceclap_attribute:Relief1.110.91
voiceclap_attribute:Sadness0.560.65
voiceclap_attribute:Serious_vs._Humorous1.891.48
voiceclap_attribute:Sexual_Lust0.310.39
voiceclap_attribute:Shame0.550.58
voiceclap_attribute:Soft_vs._Harsh0.330.26
voiceclap_attribute:Sourness0.450.50
voiceclap_attribute:Submissive_vs._Dominant0.460.54
voiceclap_attribute:Teasing0.600.61
voiceclap_attribute:Thankfulness_Gratitude1.020.87
voiceclap_attribute:Triumph0.670.63
voiceclap_attribute:Valence0.540.01
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.891.01
voiceclap_attribute:Warm_vs._Cold0.640.23
voiceclap_attribute:duration12.2012.08
voiceclap_attribute:score_background_quality3.483.34
voiceclap_attribute:score_content_enjoyment4.974.90
voiceclap_attribute:score_overall_quality2.972.76
voiceclap_attribute:score_speech_quality1.921.89
voiceclap_attribute:talking_speed18.5717.81
Reproducibility and API usage

Dataset UID: EN_B00010_S05798_W000032
Audio SHA-256: 3806d4ade862e1328b0fd56ec640a85c745bc05defc923f3ad2368914bf299de
Gemini call: 7.17 s; input tokens 25464; cached tokens 25085; output tokens 1573.

S10-10 · en / real

Distress

7.1 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Distress score (z=4.71); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American (uncertain)

Transcript

What the fuck? What the fuck? What the fuck?

Audio caption

A single speaker with a young-adult, somewhat feminine-leaning to androgynous vocal presentation delivers three iterations of an explicit phrase in General American English, overwhelmed by genuine shock, confusion, and uncontrollable amusement. The vocal production is highly unstable, characterized by elevated arousal, moderate roughness, and bright head-dominant resonance that periodically fractures into breathiness and wheezing laughter. Articulation is loose and disfluent due to laughter physically interrupting the lexical stream, particularly on the repeated expletives. Each repetition of the phrase is heavily colored by breathy giggling, culminating in wheezing laughter pulses and an audible recovery inhalation. The recording is relatively clean and close-mic'd with minimal room reflection and low background noise, conveying an authentic, unscripted moment of hysterical disbelief.

Director caption

Deliver the phrase with a mixture of utter disbelief, shock, and mounting hilarity that you cannot physically suppress. Start with an incredulous, pitch-lifted question: "What the fuck?", letting the final word break into a tight, staccato chuckle that spills out on the exhale. Without pausing to regain full composure, repeat the phrase louder and with more acute astonishment: "What the fuck?", this time letting the final word shatter entirely into an open, wheezy laugh that takes all of your breath. Pause to take a distinct, audible open-mouth recovery breath, and then utter the final repetition in a lower, stunned, breathy half-whisper of lingering disbelief: "What the fuck?".

Gemini bursts3
Base / Small count0.11 / 0.02
Genuineness (G / B / S)5 / 2.74 / 2.65
Burst blend (G / B / S)9 / 2.33 / 1.87
CPS (Base / Small)5.08 / 4.24
0 s7.1 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.85 s · End: 2.15 s · Chuckle laugh_soft
    A tight, high-pitched staccato chuckle and giggly exhalation directly overlaps the tail of the expletive phrase 'What the fuck?', trailing off into breathless amusement while demonstrating clear physiological continuity with the spoken words.
  • Gemini · Start: 3.45 s · End: 4.65 s · Guffaw laugh_loud
    An open, pitch-lifted, wheezy laugh burst erupts on the final syllable of the second 'What the fuck?', fracturing articulation and continuing into a breathless, wheezing exhalation that sounds entirely spontaneous and physiologically connected.
  • Gemini · Start: 5.05 s · End: 6.05 s · Deep Breath breath_calm
    A prominent, audible open-mouth inhalation occurs during the pause following the intense burst of laughter, serving as a physiological recovery breath to restore air before the third vocalization.
  • Base proposals: Start: 0.54 s · End: 0.84 s: Breathy Giggle 0.60, Childlike Giggle 0.27, Surprised Gasp 0.07; Start: 0.68 s · End: 0.92 s: Childlike Giggle 0.73, Surprised Gasp 0.12, Breathy Giggle 0.07; Start: 0.74 s · End: 0.96 s: Childlike Giggle 0.66, Surprised Gasp 0.23, Breathy Giggle 0.03; Start: 1.30 s · End: 1.46 s: Surprised Gasp 0.97, Breathy Giggle 0.00, Nervous Giggle 0.00; Start: 3.38 s · End: 3.66 s: Breathy Giggle 0.92, Surprised Gasp 0.02, Childlike Giggle 0.01; Start: 3.58 s · End: 3.74 s: Surprised Gasp 0.75, Breathy Giggle 0.20, Hum 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.004.014.163.93
emphvn_EMPH_reg5.001.931.811.96
s casuvn_S_CASU_reg5.006.096.055.98
s playvn_S_PLAY_reg5.003.953.603.73
atckvn_ATCK_reg4.003.633.193.31
brgtvn_BRGT_reg4.001.741.711.91
focsvn_FOCS_reg4.000.960.911.08
r headvn_R_HEAD_reg4.001.591.612.05
rangvn_RANG_reg4.004.504.224.28
respvn_RESP_reg4.005.505.134.87
s convvn_S_CONV_reg4.002.882.493.02
s dramvn_S_DRAM_reg4.004.914.845.03
tensvn_TENS_reg4.003.693.583.55
valnvn_VALN_reg4.000.240.430.62
voltvn_VOLT_reg4.005.235.214.96
vulnvn_VULN_reg4.006.386.276.16
agevvn_AGEV_reg3.001.141.251.56
bkgnvn_BKGN_reg3.002.342.162.34
esthvn_ESTH_reg3.000.720.690.95
fullvn_FULL_reg3.001.912.151.92
metlvn_METL_reg3.001.681.851.81
r maskvn_R_MASK_reg3.000.930.891.36
r mixdvn_R_MIXD_reg3.001.241.081.17
r oralvn_R_ORAL_reg3.001.121.081.71
r thrtvn_R_THRT_reg3.001.391.281.39
rcqlvn_RCQL_reg3.001.611.501.63
regsvn_REGS_reg3.003.573.113.32
rougvn_ROUG_reg3.004.053.943.72
s cartvn_S_CART_reg3.003.823.253.62
s rantvn_S_RANT_reg3.003.542.883.15
stncvn_STNC_reg3.001.731.551.62
valsvn_VALS_reg3.000.951.001.12
arshvn_ARSH_reg2.001.081.211.27
clrtvn_CLRT_reg2.000.170.150.30
coglvn_COGL_reg2.003.323.023.13
darcvn_DARC_reg2.004.644.384.27
dfluvn_DFLU_reg2.004.944.894.67
explvn_EXPL_reg2.000.220.200.30
gendvn_GEND_reg2.002.632.322.34
harmvn_HARM_reg2.002.912.632.69
r chstvn_R_CHST_reg2.000.850.891.01
r naslvn_R_NASL_reg2.002.081.852.39
s monovn_S_MONO_reg2.000.570.710.63
tempvn_TEMP_reg2.002.182.192.11
vflxvn_VFLX_reg2.003.573.333.10
warmvn_WARM_reg2.001.301.121.28
chnkvn_CHNK_reg1.00-0.25-0.270.17
s authvn_S_AUTH_reg1.00-0.20-0.32-0.18
smthvn_SMTH_reg1.000.18-0.050.31
struvn_STRU_reg1.00-0.41-0.210.00
s asmrvn_S_ASMR_reg0.000.700.450.40
s formvn_S_FORM_reg0.00-0.14-0.20-0.05
s narrvn_S_NARR_reg0.000.02-0.030.15
s newsvn_S_NEWS_reg0.000.120.310.28
s stryvn_S_STRY_reg0.002.312.312.46
s techvn_S_TECH_reg0.00-0.32-0.47-0.58
s whisvn_S_WHIS_reg0.001.451.701.77
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.311.69
eiv_extra:Arousal2.372.30
eiv_extra:Authenticity2.963.01
eiv_extra:Background_Noise0.900.95
eiv_extra:Confident_vs._Hesitant2.422.56
eiv_extra:Gender-0.150.62
eiv_extra:High-Pitched_vs._Low-Pitched1.601.48
eiv_extra:Monotone_vs._Expressive2.432.44
eiv_extra:Recording_Quality1.511.56
eiv_extra:Serious_vs._Humorous1.070.80
eiv_extra:Soft_vs._Harsh0.881.07
eiv_extra:Submissive_vs._Dominant-0.16-0.16
eiv_extra:Valence-1.65-1.25
eiv_extra:Vulnerable_vs._Emotionally_Detached0.520.48
eiv_extra:Warm_vs._Cold-0.28-0.13
eiv_extra:score_background_quality2.952.73
eiv_extra:score_content_enjoyment3.883.97
eiv_extra:score_overall_quality2.422.08
eiv_extra:score_speech_quality1.751.80
audiobox:CE4.454.15
audiobox:CU4.955.02
audiobox:PC2.022.12
audiobox:PQ6.166.23
dnsmos:SIG_raw2.962.62
dnsmos:BAK_raw2.652.42
dnsmos:OVRL_raw2.242.02
dnsmos:SIG2.882.60
dnsmos:BAK2.952.72
dnsmos:OVRL2.232.04
dnsmos:P808_MOS2.772.60
voiceclap_attribute:Affection0.901.08
voiceclap_attribute:Age1.911.74
voiceclap_attribute:Amusement2.722.46
voiceclap_attribute:Anger0.350.44
voiceclap_attribute:Arousal2.752.43
voiceclap_attribute:Astonishment_Surprise1.461.89
voiceclap_attribute:Authenticity3.063.14
voiceclap_attribute:Awe0.540.75
voiceclap_attribute:Background_Noise0.640.73
voiceclap_attribute:Bitterness0.370.36
voiceclap_attribute:Concentration-0.01-0.10
voiceclap_attribute:Confident_vs._Hesitant2.142.02
voiceclap_attribute:Confusion1.121.31
voiceclap_attribute:Contemplation0.110.06
voiceclap_attribute:Contempt0.290.17
voiceclap_attribute:Contentment0.350.61
voiceclap_attribute:Disappointment1.021.01
voiceclap_attribute:Disgust0.350.43
voiceclap_attribute:Distress2.061.97
voiceclap_attribute:Doubt0.670.54
voiceclap_attribute:Elation1.311.13
voiceclap_attribute:Embarrassment1.551.28
voiceclap_attribute:Emotional_Numbness0.320.34
voiceclap_attribute:Fatigue_Exhaustion0.620.64
voiceclap_attribute:Fear1.101.11
voiceclap_attribute:Gender0.580.76
voiceclap_attribute:Helplessness1.441.42
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.341.38
voiceclap_attribute:Hope_Enthusiasm_Optimism0.890.72
voiceclap_attribute:Impatience_and_Irritability0.921.06
voiceclap_attribute:Infatuation0.720.74
voiceclap_attribute:Interest1.061.08
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness1.121.15
voiceclap_attribute:Jealousy_&_Envy0.390.43
voiceclap_attribute:Longing0.660.71
voiceclap_attribute:Malevolence_Malice0.460.45
voiceclap_attribute:Monotone_vs._Expressive2.662.70
voiceclap_attribute:Pain1.301.19
voiceclap_attribute:Pleasure_Ecstasy1.311.12
voiceclap_attribute:Pride-0.03-0.28
voiceclap_attribute:Recording_Quality1.601.62
voiceclap_attribute:Relief1.051.34
voiceclap_attribute:Sadness1.771.68
voiceclap_attribute:Serious_vs._Humorous2.102.07
voiceclap_attribute:Sexual_Lust0.520.71
voiceclap_attribute:Shame0.700.76
voiceclap_attribute:Soft_vs._Harsh0.981.08
voiceclap_attribute:Sourness0.310.19
voiceclap_attribute:Submissive_vs._Dominant-0.22-0.13
voiceclap_attribute:Teasing1.151.31
voiceclap_attribute:Thankfulness_Gratitude1.171.01
voiceclap_attribute:Triumph0.430.37
voiceclap_attribute:Valence0.04-0.20
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.510.60
voiceclap_attribute:Warm_vs._Cold0.620.61
voiceclap_attribute:duration6.029.00
voiceclap_attribute:score_background_quality3.063.05
voiceclap_attribute:score_content_enjoyment4.454.51
voiceclap_attribute:score_overall_quality2.262.21
voiceclap_attribute:score_speech_quality1.961.93
voiceclap_attribute:talking_speed6.336.05
Reproducibility and API usage

Dataset UID: EN_VqvnKOYZTl4_W000006
Audio SHA-256: 8f972bd3558b20da219a50355eb85705791906572fefd8919dae028b5254311a
Gemini call: 6.39 s; input tokens 25278; cached tokens 25085; output tokens 1658.

S10-11 · en / real

Hope Enthusiasm Optimism

21.6 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Hope Enthusiasm Optimism score (z=5.11); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

everybody's in here. Uh, Eddie, uh good to see you in here from Alabama. All right. Welcome in, welcome in. All right, I hope you enjoy our workout that we have available for you today. So, uh before we get started, let's go ahead and jump into our dynamic stretching team, all right? We want to we always want to make sure that our bodies are warmed up and prepared to work. So, let's start off with

Audio caption

A young adult male speaker delivers an upbeat, highly interactive fitness instructor intro in General American English. The acoustic profile features a balanced baritone register with warm chest resonance, forward oral clarity, and bright projection suited for coaching. The pacing is brisk and energetic with natural conversational phrasing and minor spontaneous hesitations as he greets incoming stream participants. His stance is assertive and welcoming, maintaining high interpersonal focus with an encouraging, optimistic, and slightly amused demeanor. Respiration is audible but controlled, reflecting light physical readiness. Near the conclusion, a brief two-stroke throat clear smoothly bridges an instructional phrase without disrupting the dynamic forward momentum. The recording exhibits moderate room reverberation typical of a large studio or gym space, but the vocal capture remains clean, clear, and highly intelligible throughout.

Director caption

Open with high-energy livestream instructor presence, speaking in a bright, friendly, and brisk tone as if checking live chat: "everybody's in here. Uh, Eddie, uh good to see you in here from Alabama. All right." Keep the delivery buoyant and welcoming with quick phrasing: "Welcome in, welcome in. All right, I hope you enjoy our workout that we have available for you today." Transition smoothly into coach mode with motivated forward drive: "So, uh before we get started, let's go ahead and jump into our dynamic stretching team, all right?" Add instructional warmth and rhythmic emphasis: "We want to we always want to make sure that our bodies are warmed up and prepared to work." Slow down slightly to introduce the first exercise, pausing to give a quick, light, two-pulse throat clear [clears throat] before picking up immediately on the final word: "So, let's start off with".

Gemini bursts1
Base / Small count4.28 / 4.00
Genuineness (G / B / S)5 / 3.43 / 3.12
Burst blend (G / B / S)8 / 9.23 / 9.17
CPS (Base / Small)18.37 / 18.20
0 s21.6 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 20.85 s · End: 21.36 s · Clears Throat throat
    A quick, two-pulse throat clearing occurs in a brief mid-sentence pause right between 'let's start off' and 'with'; it has a dry, percussive pharyngeal rasp used to reset vocal clarity before giving the next instruction, naturally integrating into the active coaching delivery without interrupting momentum.
  • Existing S10 marker · Start: 1.08 s · End: 1.32 s
  • Existing S10 marker · Start: 1.92 s · End: 2.14 s
  • Existing S10 marker · Start: 9.38 s · End: 9.60 s
  • Existing S10 marker · Start: 20.76 s · End: 21.02 s
  • Base proposals: Start: 1.08 s · End: 1.30 s: Ahem 0.90, Surprised Gasp 0.02, Spitting 0.01; Start: 1.90 s · End: 2.14 s: Ahem 0.93, Nervous Giggle 0.01, Spitting 0.01; Start: 9.38 s · End: 9.60 s: Ahem 0.92, Spitting 0.01, Nervous Giggle 0.01; Start: 20.74 s · End: 21.00 s: Ahem 0.89, Low Mumble 0.02, Nervous Giggle 0.01
  • Small proposals: Start: 1.08 s · End: 1.32 s: Ahem 0.92, Surprised Gasp 0.01, Nervous Giggle 0.01; Start: 1.90 s · End: 2.16 s: Ahem 0.94, Snicker 0.01, Nervous Giggle 0.01; Start: 9.38 s · End: 9.60 s: Ahem 0.93, Spitting 0.01, Nervous Giggle 0.01; Start: 20.76 s · End: 21.00 s: Ahem 0.93, Nervous Giggle 0.00, Snicker 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
focsvn_FOCS_reg5.003.693.503.55
gendvn_GEND_reg5.004.484.794.55
s casuvn_S_CASU_reg5.004.574.614.50
s convvn_S_CONV_reg5.004.394.474.55
valnvn_VALN_reg5.004.664.454.55
arouvn_AROU_reg4.004.004.204.18
atckvn_ATCK_reg4.002.823.132.99
brgtvn_BRGT_reg4.003.413.033.07
clrtvn_CLRT_reg4.001.732.081.99
emphvn_EMPH_reg4.003.674.023.71
esthvn_ESTH_reg4.002.202.182.18
harmvn_HARM_reg4.002.662.812.72
r chstvn_R_CHST_reg4.002.462.662.74
r mixdvn_R_MIXD_reg4.001.310.931.10
r oralvn_R_ORAL_reg4.001.761.741.70
rangvn_RANG_reg4.003.463.363.39
s playvn_S_PLAY_reg4.003.473.543.75
s techvn_S_TECH_reg4.001.381.621.78
smthvn_SMTH_reg4.002.452.292.17
stncvn_STNC_reg4.004.234.084.02
struvn_STRU_reg4.002.472.262.39
tempvn_TEMP_reg4.004.314.254.17
warmvn_WARM_reg4.002.302.392.34
agevvn_AGEV_reg3.002.412.532.61
arshvn_ARSH_reg3.003.654.263.87
bkgnvn_BKGN_reg3.002.221.932.03
chnkvn_CHNK_reg3.003.763.983.82
darcvn_DARC_reg3.002.842.852.83
fullvn_FULL_reg3.001.932.161.97
r maskvn_R_MASK_reg3.002.732.632.75
r thrtvn_R_THRT_reg3.001.671.821.61
rcqlvn_RCQL_reg3.002.312.292.48
respvn_RESP_reg3.002.332.672.28
s authvn_S_AUTH_reg3.002.772.512.64
valsvn_VALS_reg3.004.244.214.25
coglvn_COGL_reg2.000.621.120.98
dfluvn_DFLU_reg2.003.002.982.93
metlvn_METL_reg2.002.522.512.54
r headvn_R_HEAD_reg2.003.002.912.89
r naslvn_R_NASL_reg2.004.053.913.77
rougvn_ROUG_reg2.002.662.512.59
s dramvn_S_DRAM_reg2.004.344.124.14
s narrvn_S_NARR_reg2.00-0.07-0.060.01
tensvn_TENS_reg2.001.361.451.27
vflxvn_VFLX_reg2.003.353.623.29
voltvn_VOLT_reg2.003.103.143.15
vulnvn_VULN_reg2.001.421.641.55
regsvn_REGS_reg1.001.011.201.14
s cartvn_S_CART_reg1.001.852.071.84
s formvn_S_FORM_reg1.000.220.290.29
s monovn_S_MONO_reg1.002.242.252.18
s newsvn_S_NEWS_reg1.00-0.06-0.00-0.09
s stryvn_S_STRY_reg1.003.033.073.03
explvn_EXPL_reg0.000.720.590.58
s asmrvn_S_ASMR_reg0.00-0.02-0.18-0.16
s rantvn_S_RANT_reg0.002.122.402.31
s whisvn_S_WHIS_reg0.000.870.560.52
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.852.97
eiv_extra:Arousal2.422.40
eiv_extra:Authenticity2.892.95
eiv_extra:Background_Noise0.860.84
eiv_extra:Confident_vs._Hesitant1.121.05
eiv_extra:Gender-0.35-0.39
eiv_extra:High-Pitched_vs._Low-Pitched1.791.86
eiv_extra:Monotone_vs._Expressive2.712.76
eiv_extra:Recording_Quality2.412.60
eiv_extra:Serious_vs._Humorous1.531.40
eiv_extra:Soft_vs._Harsh0.390.50
eiv_extra:Submissive_vs._Dominant0.620.68
eiv_extra:Valence2.592.46
eiv_extra:Vulnerable_vs._Emotionally_Detached1.421.41
eiv_extra:Warm_vs._Cold1.171.28
eiv_extra:score_background_quality2.862.93
eiv_extra:score_content_enjoyment4.864.93
eiv_extra:score_overall_quality2.512.47
eiv_extra:score_speech_quality1.751.75
audiobox:CE5.485.67
audiobox:CU5.806.33
audiobox:PC2.292.02
audiobox:PQ6.616.96
dnsmos:SIG_raw3.633.70
dnsmos:BAK_raw2.863.13
dnsmos:OVRL_raw2.802.93
dnsmos:SIG3.333.37
dnsmos:BAK3.043.27
dnsmos:OVRL2.622.72
dnsmos:P808_MOS3.583.68
voiceclap_attribute:Affection1.231.11
voiceclap_attribute:Age3.343.09
voiceclap_attribute:Amusement1.270.92
voiceclap_attribute:Anger0.980.74
voiceclap_attribute:Arousal2.852.68
voiceclap_attribute:Astonishment_Surprise0.770.85
voiceclap_attribute:Authenticity3.002.96
voiceclap_attribute:Awe0.430.43
voiceclap_attribute:Background_Noise0.810.66
voiceclap_attribute:Bitterness0.540.46
voiceclap_attribute:Concentration0.941.01
voiceclap_attribute:Confident_vs._Hesitant1.301.15
voiceclap_attribute:Confusion0.260.22
voiceclap_attribute:Contemplation0.390.52
voiceclap_attribute:Contempt0.790.66
voiceclap_attribute:Contentment1.091.14
voiceclap_attribute:Disappointment0.580.69
voiceclap_attribute:Disgust0.540.44
voiceclap_attribute:Distress0.390.68
voiceclap_attribute:Doubt0.340.44
voiceclap_attribute:Elation1.811.59
voiceclap_attribute:Embarrassment0.420.21
voiceclap_attribute:Emotional_Numbness0.010.13
voiceclap_attribute:Fatigue_Exhaustion0.060.03
voiceclap_attribute:Fear0.450.30
voiceclap_attribute:Gender-0.24-0.38
voiceclap_attribute:Helplessness0.020.10
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.911.83
voiceclap_attribute:Hope_Enthusiasm_Optimism2.302.42
voiceclap_attribute:Impatience_and_Irritability1.120.91
voiceclap_attribute:Infatuation0.210.18
voiceclap_attribute:Interest2.672.58
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.380.30
voiceclap_attribute:Jealousy_&_Envy0.670.56
voiceclap_attribute:Longing0.180.19
voiceclap_attribute:Malevolence_Malice0.890.68
voiceclap_attribute:Monotone_vs._Expressive3.202.83
voiceclap_attribute:Pain-0.080.08
voiceclap_attribute:Pleasure_Ecstasy1.030.95
voiceclap_attribute:Pride0.821.00
voiceclap_attribute:Recording_Quality2.602.70
voiceclap_attribute:Relief0.820.93
voiceclap_attribute:Sadness0.170.15
voiceclap_attribute:Serious_vs._Humorous1.841.27
voiceclap_attribute:Sexual_Lust0.340.31
voiceclap_attribute:Shame0.480.47
voiceclap_attribute:Soft_vs._Harsh0.220.17
voiceclap_attribute:Sourness0.820.76
voiceclap_attribute:Submissive_vs._Dominant0.800.85
voiceclap_attribute:Teasing1.131.04
voiceclap_attribute:Thankfulness_Gratitude1.541.44
voiceclap_attribute:Triumph1.000.96
voiceclap_attribute:Valence1.371.18
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.431.11
voiceclap_attribute:Warm_vs._Cold1.070.61
voiceclap_attribute:duration17.7520.05
voiceclap_attribute:score_background_quality3.033.36
voiceclap_attribute:score_content_enjoyment5.055.13
voiceclap_attribute:score_overall_quality2.602.77
voiceclap_attribute:score_speech_quality1.851.86
voiceclap_attribute:talking_speed14.1412.59
Reproducibility and API usage

Dataset UID: EN_L1ZXATDAthU_W000038
Audio SHA-256: 2e6d8bf979dbda6d7cf1b12ebab4610f56e8524778333f9452fa71597960bd05
Gemini call: 6.98 s; input tokens 25639; cached tokens 25085; output tokens 1596.

S10-12 · en / real

Teasing

11.7 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Teasing score (z=4.35); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

Now, you're talking toe issues. I noticed in your Twitter bio you have your 40 time, 4.21. That's amazing. What do you think, if you're completely healthy, what do you think you could run right now?

Audio caption

A single young adult masculine-coded speaker delivers an engaged, conversational query in General American English, characteristic of a professional sports podcast or broadcast interview. The vocal timbre is grounded with balanced chest and oral resonance, possessing solid warmth, clarity, and moderate brightness with minimal roughness. Phrasing proceeds at a brisk, energetic tempo with natural conversational chunking and clear, practiced articulation. The delivery is marked by genuine curiosity, enthusiasm, and a sense of impressed wonder when citing the athletic achievement, accompanied by subtle smile-voice coloring and playful engagement. Pitch range and emphasis actively contour the key figures and transitions without theatrics or tension. Background noise is virtually imperceptible within a clean, studio-standard recording space, contributing to an effortless, highly authentic conversational performance devoid of non-verbal vocal bursts.

Director caption

Deliver this as an engaging, upbeat sports podcast host conducting a live interview. Open casually but with forward momentum: "Now, you're talking toe issues." Pick up the tempo slightly and lean into conversational intimacy, stressing the discovery: "I noticed in your Twitter bio you have your 40 time," then pause deliberately before emphasizing the exact numbers with genuine awe and crisp diction: "4.21." Let an appreciative smile color your voice on "That's amazing." Transition directly into a bright, eager question, raising pitch and energy to draw in the guest: "What do you think, if you're completely healthy, what do you think you could run right now?" Keep the tone friendly, enthusiastic, and authoritative yet entirely relaxed.

Gemini bursts0
Base / Small count0.01 / 0.00
Genuineness (G / B / S)5 / 4.90 / 5.08
Burst blend (G / B / S)— / 6.67 / 6.50
CPS (Base / Small)18.14 / 17.82
0 s11.7 s
Event captions and top-3 Whisper classes
  • Base proposals: Start: 5.86 s · End: 6.02 s: Ahem 0.87, Breathy Giggle 0.05, Surprised Gasp 0.02
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.914.914.75
s convvn_S_CONV_reg5.004.744.724.77
arouvn_AROU_reg4.003.583.543.55
arshvn_ARSH_reg4.003.693.573.63
bkgnvn_BKGN_reg4.002.342.512.52
brgtvn_BRGT_reg4.002.622.512.67
clrtvn_CLRT_reg4.003.062.803.04
darcvn_DARC_reg4.001.972.031.99
emphvn_EMPH_reg4.003.653.673.63
esthvn_ESTH_reg4.002.212.342.28
focsvn_FOCS_reg4.003.263.333.19
fullvn_FULL_reg4.003.282.942.81
harmvn_HARM_reg4.002.902.842.64
r chstvn_R_CHST_reg4.002.472.592.65
r mixdvn_R_MIXD_reg4.002.642.472.33
r oralvn_R_ORAL_reg4.002.152.152.18
rangvn_RANG_reg4.003.043.083.04
rcqlvn_RCQL_reg4.003.083.143.10
s casuvn_S_CASU_reg4.004.814.834.87
smthvn_SMTH_reg4.003.052.942.95
stncvn_STNC_reg4.003.973.763.90
struvn_STRU_reg4.002.372.272.38
tempvn_TEMP_reg4.003.523.193.21
valnvn_VALN_reg4.003.233.013.10
valsvn_VALS_reg4.003.153.223.32
warmvn_WARM_reg4.002.482.392.42
agevvn_AGEV_reg3.002.892.962.86
atckvn_ATCK_reg3.003.002.933.05
chnkvn_CHNK_reg3.003.343.132.90
r maskvn_R_MASK_reg3.002.762.632.82
r thrtvn_R_THRT_reg3.001.631.631.50
s authvn_S_AUTH_reg3.001.841.951.80
s playvn_S_PLAY_reg3.003.893.753.70
vflxvn_VFLX_reg3.002.772.672.49
coglvn_COGL_reg2.002.101.882.10
dfluvn_DFLU_reg2.003.633.593.61
metlvn_METL_reg2.002.171.791.87
r headvn_R_HEAD_reg2.002.762.732.66
r naslvn_R_NASL_reg2.003.383.163.36
respvn_RESP_reg2.001.041.000.96
rougvn_ROUG_reg2.002.542.442.43
s dramvn_S_DRAM_reg2.003.403.503.62
s formvn_S_FORM_reg2.000.520.450.33
s narrvn_S_NARR_reg2.000.11-0.010.03
s newsvn_S_NEWS_reg2.000.040.050.02
s stryvn_S_STRY_reg2.003.213.073.16
tensvn_TENS_reg2.001.571.401.40
voltvn_VOLT_reg2.003.263.283.25
vulnvn_VULN_reg2.002.432.382.33
regsvn_REGS_reg1.000.880.961.12
s monovn_S_MONO_reg1.001.221.201.08
s techvn_S_TECH_reg1.000.320.550.41
explvn_EXPL_reg0.000.470.450.56
s asmrvn_S_ASMR_reg0.00-0.63-0.41-0.61
s cartvn_S_CART_reg0.000.630.620.34
s rantvn_S_RANT_reg0.003.593.043.25
s whisvn_S_WHIS_reg0.00-0.29-0.26-0.11
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.912.91
eiv_extra:Arousal2.272.47
eiv_extra:Authenticity2.882.96
eiv_extra:Background_Noise0.790.54
eiv_extra:Confident_vs._Hesitant1.251.08
eiv_extra:Gender-0.65-1.09
eiv_extra:High-Pitched_vs._Low-Pitched1.821.88
eiv_extra:Monotone_vs._Expressive2.842.73
eiv_extra:Recording_Quality2.272.47
eiv_extra:Serious_vs._Humorous2.041.99
eiv_extra:Soft_vs._Harsh0.370.30
eiv_extra:Submissive_vs._Dominant1.040.92
eiv_extra:Valence1.061.01
eiv_extra:Vulnerable_vs._Emotionally_Detached1.631.62
eiv_extra:Warm_vs._Cold0.550.51
eiv_extra:score_background_quality3.533.54
eiv_extra:score_content_enjoyment4.935.01
eiv_extra:score_overall_quality2.882.88
eiv_extra:score_speech_quality1.961.96
audiobox:CE5.555.93
audiobox:CU6.486.88
audiobox:PC1.571.83
audiobox:PQ7.407.64
dnsmos:SIG_raw3.903.88
dnsmos:BAK_raw3.923.82
dnsmos:OVRL_raw3.563.41
dnsmos:SIG3.503.48
dnsmos:BAK3.833.77
dnsmos:OVRL3.143.06
dnsmos:P808_MOS4.184.25
voiceclap_attribute:Affection0.810.73
voiceclap_attribute:Age3.062.97
voiceclap_attribute:Amusement1.721.56
voiceclap_attribute:Anger1.191.33
voiceclap_attribute:Arousal2.512.55
voiceclap_attribute:Astonishment_Surprise1.191.28
voiceclap_attribute:Authenticity3.063.01
voiceclap_attribute:Awe0.300.19
voiceclap_attribute:Background_Noise0.760.63
voiceclap_attribute:Bitterness0.590.58
voiceclap_attribute:Concentration0.360.60
voiceclap_attribute:Confident_vs._Hesitant1.961.74
voiceclap_attribute:Confusion0.991.03
voiceclap_attribute:Contemplation0.630.61
voiceclap_attribute:Contempt0.760.93
voiceclap_attribute:Contentment0.700.54
voiceclap_attribute:Disappointment0.840.84
voiceclap_attribute:Disgust0.780.76
voiceclap_attribute:Distress0.770.70
voiceclap_attribute:Doubt0.680.69
voiceclap_attribute:Elation1.320.99
voiceclap_attribute:Embarrassment1.110.80
voiceclap_attribute:Emotional_Numbness0.280.09
voiceclap_attribute:Fatigue_Exhaustion0.470.30
voiceclap_attribute:Fear0.490.34
voiceclap_attribute:Gender-0.55-0.47
voiceclap_attribute:Helplessness0.370.33
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.691.78
voiceclap_attribute:Hope_Enthusiasm_Optimism1.611.45
voiceclap_attribute:Impatience_and_Irritability1.511.80
voiceclap_attribute:Infatuation0.510.25
voiceclap_attribute:Interest2.092.03
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.740.51
voiceclap_attribute:Jealousy_&_Envy0.670.73
voiceclap_attribute:Longing0.370.29
voiceclap_attribute:Malevolence_Malice0.700.88
voiceclap_attribute:Monotone_vs._Expressive3.412.92
voiceclap_attribute:Pain0.200.11
voiceclap_attribute:Pleasure_Ecstasy0.860.76
voiceclap_attribute:Pride0.950.79
voiceclap_attribute:Recording_Quality2.202.25
voiceclap_attribute:Relief1.220.88
voiceclap_attribute:Sadness0.350.26
voiceclap_attribute:Serious_vs._Humorous2.451.96
voiceclap_attribute:Sexual_Lust0.640.70
voiceclap_attribute:Shame0.640.53
voiceclap_attribute:Soft_vs._Harsh0.06-0.09
voiceclap_attribute:Sourness0.720.89
voiceclap_attribute:Submissive_vs._Dominant1.151.13
voiceclap_attribute:Teasing1.041.28
voiceclap_attribute:Thankfulness_Gratitude1.671.44
voiceclap_attribute:Triumph0.830.66
voiceclap_attribute:Valence0.42-0.18
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.851.24
voiceclap_attribute:Warm_vs._Cold0.620.28
voiceclap_attribute:duration9.3110.63
voiceclap_attribute:score_background_quality3.453.40
voiceclap_attribute:score_content_enjoyment4.834.86
voiceclap_attribute:score_overall_quality2.922.84
voiceclap_attribute:score_speech_quality1.951.95
voiceclap_attribute:talking_speed19.3920.45
Reproducibility and API usage

Dataset UID: EN_B00039_S08500_W000017
Audio SHA-256: d6f2f82147fa5bdd6fbae672aa4386cfb617a0401ffda4f84d6a4436bf7380d3
Gemini call: 6.08 s; input tokens 25392; cached tokens 25085; output tokens 1385.

S10-13 · en / real

Astonishment Surprise

11.9 s · Complete

Source: emolia (CC-BY-4.0) · en/real · chosen for high existing Astonishment Surprise score (z=4.57); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · General American (uncertain)

Transcript

Oh my god. Oh my god. Oh! Oh my god. Oh my god. Oh my god! Oh! Oh god! Oh my god!

Audio caption

A single speaker delivers a series of escalating exclamations of shock, bewilderment, and distress repeating the phrase 'Oh my god' with varied inflections. The performance features a young adult voice with a predominantly feminine-leaning to androgynous acoustic quality, shifting rapidly across vocal registers from breathy head resonance to strained, pressed throat-heavy production. Tempo varies in short, repetitive chunks separated by sharp gasps and heavy breathing. Beginning with quiet, breathy disbelief, the arousal and intensity steadily climb into loud, strained, almost panicked outcries. Timbral qualities transition from bright and whisper-adjacent to gritty, metallic, and rough as throat constriction increases under high emotional charge. Clean studio or semi-treated recording environment with minimal background interference. The delivery appears theatrical and performed, functioning as a repetitive drill or dynamic voice-acting exercise.

Director caption

Deliver a sequence of repeated exclamations that steadily escalate in sheer disbelief, panic, and volume. Start with a breathy, quiet register, keeping the pitch slightly lifted in head resonance: "Oh my god." Take a brief pause, then repeat with slightly more air and tremor: "Oh my god." Abruptly hit a sharp, startled intake of breath—an audible gasp—and immediately follow with a heavy exhale. Lower your pitch into a chestier, strained register, pressing the phonation: "Oh my god." Keep ramping up the energy and throat tension on the next delivery: "Oh my god." Push into a full, loud, crackling theatrical belt with strong emphasis on the final word: "Oh my god!" Release into a ragged, breathy sigh of exasperation, transition directly into a strained, frustrated groan in the lower throat, and immediately recover to cap off the sequence with one final, bright, high-intensity shriek: "Oh my god!"

Gemini bursts4
Base / Small count0.81 / 1.16
Genuineness (G / B / S)3 / 2.69 / 2.30
Burst blend (G / B / S)7 / 1.93 / 2.08
CPS (Base / Small)5.87 / 6.05
0 s11.9 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 3.75 s · End: 4.15 s · Surprised Gasp gasp
    A sudden, sharp vocalized intake of air that interrupts the pause between repetitions; it possesses an abrupt onset and high pitch flare signaling sudden shock or startle before dropping into a heavier delivery.
  • Gemini · Start: 4.16 s · End: 4.70 s · Heavy Breathing breath_fast
    A quick, audible breathy exhale following the sharp intake, carrying tension and rapid air release before launching into the next vocalization.
  • Gemini · Start: 9.20 s · End: 9.60 s · Exasperated Sigh sigh_neg
    A breathy, stressed exhalation produced in a pause after a strained exclamation, conveying mounting exhaustion and distress with ragged air noise.
  • Gemini · Start: 9.80 s · End: 10.45 s · Frustrated Groan sigh_neg
    A low-to-mid pitched, heavily vocalized groan of exasperation and strain between phrases, blending naturally from vocal fry and ragged breath into the final shout.
  • Existing S10 marker · Start: 9.54 s · End: 9.92 s
  • Base proposals: Start: 9.50 s · End: 9.94 s: Surprised Gasp 0.92, Scream 0.01, Shriek 0.01; Start: 9.64 s · End: 9.90 s: Surprised Gasp 0.93, Childlike Giggle 0.01, Nervous Giggle 0.01; Start: 9.70 s · End: 9.92 s: Surprised Gasp 0.92, Ahem 0.01, Childlike Giggle 0.01
  • Small proposals: Start: 3.70 s · End: 3.92 s: Surprised Gasp 0.85, Childlike Giggle 0.01, Spitting 0.01; Start: 3.76 s · End: 3.94 s: Surprised Gasp 0.84, Childlike Giggle 0.02, Ahem 0.01; Start: 3.82 s · End: 3.98 s: Surprised Gasp 0.87, Ahem 0.02, Childlike Giggle 0.01; Start: 9.54 s · End: 9.84 s: Surprised Gasp 0.93, Scream 0.02, Shriek 0.01; Start: 9.66 s · End: 9.90 s: Surprised Gasp 0.77, Childlike Giggle 0.11, Shriek 0.02; Start: 9.72 s · End: 9.92 s: Surprised Gasp 0.63, Childlike Giggle 0.14, Ahem 0.07
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.004.964.724.92
arshvn_ARSH_reg5.002.171.802.16
darcvn_DARC_reg5.005.035.045.04
rangvn_RANG_reg5.005.094.814.96
s dramvn_S_DRAM_reg5.004.664.724.78
atckvn_ATCK_reg4.005.164.544.74
brgtvn_BRGT_reg4.002.112.572.35
emphvn_EMPH_reg4.004.363.954.39
focsvn_FOCS_reg4.002.172.372.40
r headvn_R_HEAD_reg4.002.222.922.60
r oralvn_R_ORAL_reg4.002.112.342.16
respvn_RESP_reg4.004.844.254.43
s casuvn_S_CASU_reg4.005.615.435.39
s monovn_S_MONO_reg4.000.100.330.41
tensvn_TENS_reg4.003.693.223.66
vflxvn_VFLX_reg4.003.062.963.07
voltvn_VOLT_reg4.005.354.795.07
vulnvn_VULN_reg4.003.554.074.00
agevvn_AGEV_reg3.000.390.220.59
bkgnvn_BKGN_reg3.001.201.491.53
clrtvn_CLRT_reg3.000.740.680.78
esthvn_ESTH_reg3.000.390.790.51
fullvn_FULL_reg3.000.870.890.69
harmvn_HARM_reg3.002.402.912.58
metlvn_METL_reg3.003.573.043.28
r maskvn_R_MASK_reg3.002.652.652.63
r mixdvn_R_MIXD_reg3.000.890.980.77
r thrtvn_R_THRT_reg3.001.471.361.53
rcqlvn_RCQL_reg3.001.401.151.26
regsvn_REGS_reg3.004.274.274.11
rougvn_ROUG_reg3.003.953.633.77
s cartvn_S_CART_reg3.004.464.234.59
s rantvn_S_RANT_reg3.002.922.892.95
stncvn_STNC_reg3.003.743.483.63
tempvn_TEMP_reg3.003.032.732.84
gendvn_GEND_reg2.001.501.531.62
r chstvn_R_CHST_reg2.000.730.600.67
r naslvn_R_NASL_reg2.003.923.633.72
s convvn_S_CONV_reg2.001.142.411.41
s playvn_S_PLAY_reg2.003.022.982.69
smthvn_SMTH_reg2.00-0.11-0.08-0.08
valnvn_VALN_reg2.001.451.981.44
valsvn_VALS_reg2.001.311.861.16
warmvn_WARM_reg2.001.000.870.94
chnkvn_CHNK_reg1.000.680.800.70
coglvn_COGL_reg1.001.732.071.93
dfluvn_DFLU_reg1.004.544.354.12
s authvn_S_AUTH_reg1.000.24-0.010.23
s stryvn_S_STRY_reg1.002.292.472.67
s whisvn_S_WHIS_reg1.000.901.061.18
struvn_STRU_reg1.000.660.610.69
explvn_EXPL_reg0.000.080.130.06
s asmrvn_S_ASMR_reg0.00-0.04-0.150.28
s formvn_S_FORM_reg0.00-0.38-0.27-0.18
s narrvn_S_NARR_reg0.00-0.130.050.08
s newsvn_S_NEWS_reg0.000.030.200.16
s techvn_S_TECH_reg0.00-0.65-0.02-0.37
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age0.841.18
eiv_extra:Arousal2.822.79
eiv_extra:Authenticity3.003.05
eiv_extra:Background_Noise1.000.93
eiv_extra:Confident_vs._Hesitant1.851.76
eiv_extra:Gender-0.030.25
eiv_extra:High-Pitched_vs._Low-Pitched1.661.64
eiv_extra:Monotone_vs._Expressive2.782.62
eiv_extra:Recording_Quality1.771.88
eiv_extra:Serious_vs._Humorous1.190.74
eiv_extra:Soft_vs._Harsh0.810.74
eiv_extra:Submissive_vs._Dominant0.030.09
eiv_extra:Valence-0.25-1.20
eiv_extra:Vulnerable_vs._Emotionally_Detached0.600.71
eiv_extra:Warm_vs._Cold0.310.03
eiv_extra:score_background_quality2.542.50
eiv_extra:score_content_enjoyment4.134.11
eiv_extra:score_overall_quality2.142.02
eiv_extra:score_speech_quality1.721.72
audiobox:CE3.973.70
audiobox:CU4.054.26
audiobox:PC2.662.87
audiobox:PQ4.995.09
dnsmos:SIG_raw1.741.58
dnsmos:BAK_raw1.721.32
dnsmos:OVRL_raw1.531.26
dnsmos:SIG1.831.70
dnsmos:BAK1.861.56
dnsmos:OVRL1.561.36
dnsmos:P808_MOS2.762.61
voiceclap_attribute:Affection0.941.10
voiceclap_attribute:Age0.971.04
voiceclap_attribute:Amusement1.621.41
voiceclap_attribute:Anger0.781.31
voiceclap_attribute:Arousal3.153.12
voiceclap_attribute:Astonishment_Surprise1.371.58
voiceclap_attribute:Authenticity3.233.20
voiceclap_attribute:Awe0.790.76
voiceclap_attribute:Background_Noise0.810.90
voiceclap_attribute:Bitterness0.440.64
voiceclap_attribute:Concentration0.390.38
voiceclap_attribute:Confident_vs._Hesitant2.231.93
voiceclap_attribute:Confusion0.810.96
voiceclap_attribute:Contemplation0.330.19
voiceclap_attribute:Contempt0.360.56
voiceclap_attribute:Contentment0.740.85
voiceclap_attribute:Disappointment1.201.27
voiceclap_attribute:Disgust0.510.55
voiceclap_attribute:Distress2.112.01
voiceclap_attribute:Doubt0.340.38
voiceclap_attribute:Elation1.821.78
voiceclap_attribute:Embarrassment0.990.64
voiceclap_attribute:Emotional_Numbness0.050.23
voiceclap_attribute:Fatigue_Exhaustion0.610.53
voiceclap_attribute:Fear1.171.17
voiceclap_attribute:Gender0.600.62
voiceclap_attribute:Helplessness1.441.34
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.591.69
voiceclap_attribute:Hope_Enthusiasm_Optimism1.952.02
voiceclap_attribute:Impatience_and_Irritability1.481.92
voiceclap_attribute:Infatuation0.620.57
voiceclap_attribute:Interest1.421.58
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.800.82
voiceclap_attribute:Jealousy_&_Envy0.540.63
voiceclap_attribute:Longing0.720.67
voiceclap_attribute:Malevolence_Malice0.590.80
voiceclap_attribute:Monotone_vs._Expressive3.163.15
voiceclap_attribute:Pain1.281.19
voiceclap_attribute:Pleasure_Ecstasy1.431.26
voiceclap_attribute:Pride0.750.76
voiceclap_attribute:Recording_Quality1.871.89
voiceclap_attribute:Relief1.111.02
voiceclap_attribute:Sadness1.481.40
voiceclap_attribute:Serious_vs._Humorous1.551.38
voiceclap_attribute:Sexual_Lust0.470.55
voiceclap_attribute:Shame0.770.58
voiceclap_attribute:Soft_vs._Harsh0.810.51
voiceclap_attribute:Sourness0.390.58
voiceclap_attribute:Submissive_vs._Dominant0.170.49
voiceclap_attribute:Teasing0.810.94
voiceclap_attribute:Thankfulness_Gratitude1.301.03
voiceclap_attribute:Triumph1.071.29
voiceclap_attribute:Valence0.02-0.60
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.410.62
voiceclap_attribute:Warm_vs._Cold0.860.49
voiceclap_attribute:duration10.0811.95
voiceclap_attribute:score_background_quality2.992.82
voiceclap_attribute:score_content_enjoyment4.534.58
voiceclap_attribute:score_overall_quality2.202.17
voiceclap_attribute:score_speech_quality1.911.85
voiceclap_attribute:talking_speed6.055.20
Reproducibility and API usage

Dataset UID: EN_fa-KVum8kzg_W000000
Audio SHA-256: 7d953be9b7a0e90b394586f8ff7f3a32a5056f91c14848894dc4f1cb1f3fb2ac
Gemini call: 8.02 s; input tokens 25396; cached tokens 25085; output tokens 1809.

S10-14 · en / real

Relief

3.4 s · Complete

Source: commonvoice (CC-0) · en/real · chosen for high existing Relief score (z=5.36); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

I was relieved.

Audio caption

A solo, adult masculine-coded voice speaks a brief reflective statement in General American English at a calm, relaxed tempo. The vocal quality is warm and predominantly chest-resonant with low tension, clear articulation, and a smooth, unhurried cadence. Pitch range is relatively restrained, centering in a comfortable baritone tessitura. The emotional tone conveys genuine relief, gentle contentment, and quiet contemplation, supported by an audible trailing exhalation after the phrase that blends naturally into silence against a clean, studio-like recording background.

Director caption

Deliver the phrase with a sense of calm, reflective release in a grounded, warm baritone register. Speak quietly and unhurriedly: "I was relieved." On the final syllable of "relieved", let the vocal tension soften and allow a gentle exhalation—a subtle relief sigh—to trail naturally off into silence without abrupt stopping.

Gemini bursts1
Base / Small count0.02 / 0.00
Genuineness (G / B / S)4 / 0.75 / 0.53
Burst blend (G / B / S)8 / 6.82 / 6.90
CPS (Base / Small)4.36 / 3.87
0 s3.4 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 1.48 s · End: 2.25 s · Relief Sigh sigh_pos
    A soft, relaxed exhalation occurs directly after the final syllable of 'relieved', acting as an organic relief sigh that gently drops in energy and breath support into the pause, exhibiting seamless acoustic continuity with the spoken delivery.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.644.954.86
bkgnvn_BKGN_reg4.003.653.603.52
clrtvn_CLRT_reg4.003.223.223.61
esthvn_ESTH_reg4.001.921.761.84
harmvn_HARM_reg4.003.122.803.14
r chstvn_R_CHST_reg4.002.733.012.91
rcqlvn_RCQL_reg4.003.953.713.81
s monovn_S_MONO_reg4.002.803.182.97
s narrvn_S_NARR_reg4.001.161.010.72
smthvn_SMTH_reg4.001.281.191.25
struvn_STRU_reg4.001.261.491.56
valnvn_VALN_reg4.002.092.112.13
valsvn_VALS_reg4.001.291.821.59
warmvn_WARM_reg4.002.893.122.98
agevvn_AGEV_reg3.003.383.453.82
brgtvn_BRGT_reg3.002.052.201.93
emphvn_EMPH_reg3.001.290.910.83
focsvn_FOCS_reg3.001.411.221.48
fullvn_FULL_reg3.001.841.721.78
r mixdvn_R_MIXD_reg3.001.661.811.63
r oralvn_R_ORAL_reg3.002.082.171.91
r thrtvn_R_THRT_reg3.001.221.701.48
s casuvn_S_CASU_reg3.002.452.302.06
s convvn_S_CONV_reg3.001.651.691.22
s stryvn_S_STRY_reg3.001.441.181.00
stncvn_STNC_reg3.002.532.722.49
vulnvn_VULN_reg3.002.152.402.23
arshvn_ARSH_reg2.002.542.522.46
atckvn_ATCK_reg2.002.502.182.25
chnkvn_CHNK_reg2.000.840.690.74
darcvn_DARC_reg2.002.031.781.65
r maskvn_R_MASK_reg2.001.181.321.35
rangvn_RANG_reg2.001.832.051.90
respvn_RESP_reg2.002.912.792.38
s asmrvn_S_ASMR_reg2.001.301.251.45
s authvn_S_AUTH_reg2.001.301.271.41
s dramvn_S_DRAM_reg2.001.111.330.98
s formvn_S_FORM_reg2.002.292.182.35
tempvn_TEMP_reg2.001.041.091.13
vflxvn_VFLX_reg2.002.512.382.33
arouvn_AROU_reg1.002.432.352.44
coglvn_COGL_reg1.001.321.201.53
metlvn_METL_reg1.001.431.501.33
r headvn_R_HEAD_reg1.001.211.401.11
r naslvn_R_NASL_reg1.002.112.402.39
regsvn_REGS_reg1.001.391.421.52
rougvn_ROUG_reg1.000.430.670.51
s newsvn_S_NEWS_reg1.000.440.580.54
s playvn_S_PLAY_reg1.002.071.801.70
s techvn_S_TECH_reg1.001.881.511.67
s whisvn_S_WHIS_reg1.003.042.802.97
tensvn_TENS_reg1.000.981.101.15
voltvn_VOLT_reg1.001.051.190.85
dfluvn_DFLU_reg0.000.650.560.55
explvn_EXPL_reg0.000.360.130.16
s cartvn_S_CART_reg0.00-0.020.200.05
s rantvn_S_RANT_reg0.000.150.120.04
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.283.23
eiv_extra:Arousal0.520.37
eiv_extra:Authenticity2.993.03
eiv_extra:Background_Noise-0.14-0.20
eiv_extra:Confident_vs._Hesitant0.690.66
eiv_extra:Gender0.040.28
eiv_extra:High-Pitched_vs._Low-Pitched1.000.84
eiv_extra:Monotone_vs._Expressive0.650.58
eiv_extra:Recording_Quality2.752.73
eiv_extra:Serious_vs._Humorous0.530.36
eiv_extra:Soft_vs._Harsh0.390.39
eiv_extra:Submissive_vs._Dominant0.090.04
eiv_extra:Valence0.070.07
eiv_extra:Vulnerable_vs._Emotionally_Detached1.030.88
eiv_extra:Warm_vs._Cold0.160.14
eiv_extra:score_background_quality3.473.49
eiv_extra:score_content_enjoyment4.564.58
eiv_extra:score_overall_quality2.442.52
eiv_extra:score_speech_quality1.991.93
audiobox:CE4.554.17
audiobox:CU6.626.23
audiobox:PC1.251.44
audiobox:PQ7.107.02
dnsmos:SIG_raw3.633.71
dnsmos:BAK_raw4.514.51
dnsmos:OVRL_raw3.543.53
dnsmos:SIG3.283.37
dnsmos:BAK4.214.23
dnsmos:OVRL3.113.14
dnsmos:P808_MOS3.523.42
voiceclap_attribute:Affection0.500.63
voiceclap_attribute:Age3.333.29
voiceclap_attribute:Amusement-0.10-0.09
voiceclap_attribute:Anger0.290.23
voiceclap_attribute:Arousal-0.070.02
voiceclap_attribute:Astonishment_Surprise0.290.32
voiceclap_attribute:Authenticity2.913.00
voiceclap_attribute:Awe0.400.39
voiceclap_attribute:Background_Noise-0.02-0.00
voiceclap_attribute:Bitterness0.300.27
voiceclap_attribute:Concentration0.160.07
voiceclap_attribute:Confident_vs._Hesitant0.570.52
voiceclap_attribute:Confusion0.090.24
voiceclap_attribute:Contemplation0.610.62
voiceclap_attribute:Contempt0.190.05
voiceclap_attribute:Contentment0.580.59
voiceclap_attribute:Disappointment0.580.53
voiceclap_attribute:Disgust0.300.24
voiceclap_attribute:Distress0.650.69
voiceclap_attribute:Doubt0.630.71
voiceclap_attribute:Elation0.170.27
voiceclap_attribute:Embarrassment0.240.28
voiceclap_attribute:Emotional_Numbness1.261.17
voiceclap_attribute:Fatigue_Exhaustion0.990.83
voiceclap_attribute:Fear0.550.60
voiceclap_attribute:Gender-0.050.15
voiceclap_attribute:Helplessness0.981.07
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.060.89
voiceclap_attribute:Hope_Enthusiasm_Optimism0.150.35
voiceclap_attribute:Impatience_and_Irritability0.410.23
voiceclap_attribute:Infatuation0.890.95
voiceclap_attribute:Interest0.160.29
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.340.38
voiceclap_attribute:Jealousy_&_Envy0.030.00
voiceclap_attribute:Longing0.720.78
voiceclap_attribute:Malevolence_Malice0.440.33
voiceclap_attribute:Monotone_vs._Expressive0.640.62
voiceclap_attribute:Pain0.460.58
voiceclap_attribute:Pleasure_Ecstasy0.250.32
voiceclap_attribute:Pride0.330.33
voiceclap_attribute:Recording_Quality2.732.85
voiceclap_attribute:Relief1.541.52
voiceclap_attribute:Sadness1.011.07
voiceclap_attribute:Serious_vs._Humorous0.400.38
voiceclap_attribute:Sexual_Lust0.490.42
voiceclap_attribute:Shame0.510.68
voiceclap_attribute:Soft_vs._Harsh0.300.37
voiceclap_attribute:Sourness0.220.15
voiceclap_attribute:Submissive_vs._Dominant0.110.08
voiceclap_attribute:Teasing0.220.10
voiceclap_attribute:Thankfulness_Gratitude0.710.82
voiceclap_attribute:Triumph0.160.13
voiceclap_attribute:Valence-0.060.24
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.151.15
voiceclap_attribute:Warm_vs._Cold0.030.11
voiceclap_attribute:duration3.174.51
voiceclap_attribute:score_background_quality3.523.45
voiceclap_attribute:score_content_enjoyment4.674.72
voiceclap_attribute:score_overall_quality2.552.57
voiceclap_attribute:score_speech_quality2.032.03
voiceclap_attribute:talking_speed4.884.50
Reproducibility and API usage

Dataset UID: d55abd1785954e0c8e7646d11aba40cf
Audio SHA-256: a2aacc29163680634fa38229a7f6846c109131ce85d9f543f0f83827974595db
Gemini call: 5.07 s; input tokens 25185; cached tokens 25085; output tokens 1307.

S10-15 · de / synth

Impatience and Irritability

6.1 s · Complete

Source: vc_sidon (CC-BY-4.0) · de/synth · chosen for high existing Impatience and Irritability score (z=3.69); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Verdammt, dieses Ding ist so ein Arschloch, Mann. Ich werde es ihm echt in die Schienbeine treten.

Audio caption

A single young adult, masculine-coded speaker delivers an irritated, angry venting outburst in colloquial Standard German. The performance begins with a prominent exasperated breath/sigh that sets an elevated state of physiological arousal and throat tension. The vocal delivery is brisk and driving, characterized by sharp consonant attacks, punchy emphasis on derogatory words, and a chest- and throat-grounded baritone resonance with moderate grain and biological roughness. The speaker projects strong irritation, impatience, and aggressive contempt directed at a problematic object or person, maintaining an informal, venting monologue style. The acoustic environment is clean and dry with minimal background distraction, preserving natural vocal transients and believable emotional commitment.

Director caption

Begin with an audible, heavy exhale of frustration: let out a sharp, exasperated breath to set up deep irritation. Immediately jump in with a hard, punched attack on the curse word: "Verdammt,". Maintain a driving, aggressive pace with tight throat tension, emphasizing the insults with sharp bite: "dieses Ding ist so ein Arschloch, Mann." Take only a minimal breath break before continuing in a spiteful, determined cadence, leaning heavily on the threat with focused anger: "Ich werde es ihm echt in die Schienbeine treten."

Gemini bursts1
Base / Small count0.97 / 0.97
Genuineness (G / B / S)4 / 2.01 / 2.02
Burst blend (G / B / S)8 / 8.54 / 8.41
CPS (Base / Small)16.47 / 16.76
0 s6.1 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.05 s · End: 1.25 s · Exasperated Sigh sigh_neg
    A heavy, dual-phase exasperated sigh and breath release occurs right before speech onset, starting with a deep inward pull followed by a forceful, audible, unvoiced exhale through parted lips; it seamlessly transitions into the tense, aggressive attack of the opening word 'Verdammt', showing realistic physiological preparation for an angry outburst.
  • Existing S10 marker · Start: 0.04 s · End: 0.38 s
  • Base proposals: Start: 0.00 s · End: 0.38 s: Contented Sigh 0.93, Nervous Giggle 0.00, Snicker 0.00
  • Small proposals: Start: 0.00 s · End: 0.40 s: Contented Sigh 0.94, Nervous Giggle 0.01, Spitting 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.001.261.911.80
emphvn_EMPH_reg5.003.062.773.11
gendvn_GEND_reg5.005.365.225.14
s casuvn_S_CASU_reg5.002.372.392.30
s rantvn_S_RANT_reg5.001.841.962.45
stncvn_STNC_reg5.003.293.243.45
arshvn_ARSH_reg4.001.821.802.05
atckvn_ATCK_reg4.000.570.600.68
bkgnvn_BKGN_reg4.002.032.022.01
clrtvn_CLRT_reg4.000.620.600.66
darcvn_DARC_reg4.000.260.420.36
esthvn_ESTH_reg4.001.801.631.61
focsvn_FOCS_reg4.002.582.592.85
fullvn_FULL_reg4.002.362.272.23
r chstvn_R_CHST_reg4.003.352.843.03
r mixdvn_R_MIXD_reg4.001.651.061.18
r thrtvn_R_THRT_reg4.002.372.262.63
rangvn_RANG_reg4.002.472.562.80
rcqlvn_RCQL_reg4.002.152.132.22
respvn_RESP_reg4.004.644.664.71
s convvn_S_CONV_reg4.002.351.872.26
s dramvn_S_DRAM_reg4.003.694.304.34
smthvn_SMTH_reg4.001.461.201.54
struvn_STRU_reg4.001.081.000.99
tempvn_TEMP_reg4.001.071.031.10
tensvn_TENS_reg4.003.363.053.21
agevvn_AGEV_reg3.003.733.813.88
brgtvn_BRGT_reg3.001.591.051.18
chnkvn_CHNK_reg3.001.220.930.91
harmvn_HARM_reg3.001.601.181.36
metlvn_METL_reg3.001.041.461.18
r maskvn_R_MASK_reg3.000.420.090.20
r oralvn_R_ORAL_reg3.001.390.820.96
rougvn_ROUG_reg3.003.043.373.60
s authvn_S_AUTH_reg3.001.751.401.80
s monovn_S_MONO_reg3.003.023.263.24
vflxvn_VFLX_reg3.00-0.030.350.17
warmvn_WARM_reg3.003.352.943.04
r naslvn_R_NASL_reg2.000.640.100.30
s cartvn_S_CART_reg2.002.832.642.76
s stryvn_S_STRY_reg2.002.463.003.03
valsvn_VALS_reg2.001.011.090.94
voltvn_VOLT_reg2.003.253.373.51
coglvn_COGL_reg1.002.262.662.58
explvn_EXPL_reg1.000.380.150.27
r headvn_R_HEAD_reg1.000.730.080.39
regsvn_REGS_reg1.000.17-0.25-0.15
s narrvn_S_NARR_reg1.002.262.292.28
s playvn_S_PLAY_reg1.000.400.620.34
valnvn_VALN_reg1.000.51-0.070.10
vulnvn_VULN_reg1.002.973.192.89
dfluvn_DFLU_reg0.002.472.882.73
s asmrvn_S_ASMR_reg0.001.232.131.75
s formvn_S_FORM_reg0.000.820.820.73
s newsvn_S_NEWS_reg0.00-0.40-0.20-0.37
s techvn_S_TECH_reg0.00-1.47-1.66-1.98
s whisvn_S_WHIS_reg0.002.533.242.90
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.363.35
eiv_extra:Arousal2.512.36
eiv_extra:Authenticity3.153.10
eiv_extra:Background_Noise0.260.15
eiv_extra:Confident_vs._Hesitant0.840.83
eiv_extra:Gender-0.44-0.33
eiv_extra:High-Pitched_vs._Low-Pitched1.341.29
eiv_extra:Monotone_vs._Expressive1.691.50
eiv_extra:Recording_Quality2.472.53
eiv_extra:Serious_vs._Humorous0.330.21
eiv_extra:Soft_vs._Harsh-0.21-0.33
eiv_extra:Submissive_vs._Dominant1.060.80
eiv_extra:Valence-1.03-0.82
eiv_extra:Vulnerable_vs._Emotionally_Detached1.071.10
eiv_extra:Warm_vs._Cold-0.35-0.36
eiv_extra:score_background_quality3.343.25
eiv_extra:score_content_enjoyment4.554.58
eiv_extra:score_overall_quality2.622.57
eiv_extra:score_speech_quality1.811.81
audiobox:CE5.785.75
audiobox:CU6.726.81
audiobox:PC2.041.85
audiobox:PQ7.577.72
dnsmos:SIG_raw2.592.86
dnsmos:BAK_raw3.283.56
dnsmos:OVRL_raw2.522.80
dnsmos:SIG2.572.76
dnsmos:BAK3.293.51
dnsmos:OVRL2.382.58
dnsmos:P808_MOS3.413.21
voiceclap_attribute:Affection0.860.71
voiceclap_attribute:Age3.273.44
voiceclap_attribute:Amusement0.430.39
voiceclap_attribute:Anger2.102.02
voiceclap_attribute:Arousal2.522.40
voiceclap_attribute:Astonishment_Surprise1.191.27
voiceclap_attribute:Authenticity3.083.05
voiceclap_attribute:Awe0.710.80
voiceclap_attribute:Background_Noise0.320.21
voiceclap_attribute:Bitterness0.880.94
voiceclap_attribute:Concentration0.470.52
voiceclap_attribute:Confident_vs._Hesitant1.040.83
voiceclap_attribute:Confusion0.740.67
voiceclap_attribute:Contemplation0.560.59
voiceclap_attribute:Contempt0.961.16
voiceclap_attribute:Contentment0.05-0.09
voiceclap_attribute:Disappointment1.431.51
voiceclap_attribute:Disgust1.281.30
voiceclap_attribute:Distress1.761.48
voiceclap_attribute:Doubt0.710.71
voiceclap_attribute:Elation0.450.27
voiceclap_attribute:Embarrassment0.360.47
voiceclap_attribute:Emotional_Numbness0.600.68
voiceclap_attribute:Fatigue_Exhaustion0.560.54
voiceclap_attribute:Fear1.231.17
voiceclap_attribute:Gender-0.22-0.16
voiceclap_attribute:Helplessness1.251.27
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.401.40
voiceclap_attribute:Hope_Enthusiasm_Optimism0.650.47
voiceclap_attribute:Impatience_and_Irritability2.061.89
voiceclap_attribute:Infatuation0.980.89
voiceclap_attribute:Interest0.910.83
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.900.96
voiceclap_attribute:Jealousy_&_Envy1.231.20
voiceclap_attribute:Longing0.740.78
voiceclap_attribute:Malevolence_Malice1.781.84
voiceclap_attribute:Monotone_vs._Expressive2.051.80
voiceclap_attribute:Pain0.980.76
voiceclap_attribute:Pleasure_Ecstasy0.500.50
voiceclap_attribute:Pride0.950.94
voiceclap_attribute:Recording_Quality2.202.31
voiceclap_attribute:Relief1.421.34
voiceclap_attribute:Sadness1.391.41
voiceclap_attribute:Serious_vs._Humorous0.380.29
voiceclap_attribute:Sexual_Lust1.031.04
voiceclap_attribute:Shame0.670.78
voiceclap_attribute:Soft_vs._Harsh-0.37-0.41
voiceclap_attribute:Sourness1.001.05
voiceclap_attribute:Submissive_vs._Dominant1.041.11
voiceclap_attribute:Teasing0.570.63
voiceclap_attribute:Thankfulness_Gratitude1.430.81
voiceclap_attribute:Triumph1.221.07
voiceclap_attribute:Valence-1.37-1.39
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.000.94
voiceclap_attribute:Warm_vs._Cold-0.68-0.78
voiceclap_attribute:duration8.227.03
voiceclap_attribute:score_background_quality3.233.26
voiceclap_attribute:score_content_enjoyment4.664.60
voiceclap_attribute:score_overall_quality2.442.56
voiceclap_attribute:score_speech_quality1.881.91
voiceclap_attribute:talking_speed10.3911.87
Reproducibility and API usage

Dataset UID: emolia_c0547__V__S_CASU__very_high__de.c013
Audio SHA-256: a283c72d8335b2d370d98f009e5fec7ba152259432efd3d637f5d74153d708ca
Gemini call: 6.31 s; input tokens 25251; cached tokens 25085; output tokens 1427.

S10-16 · de / synth

Pleasure Ecstasy

8.6 s · Complete

Source: vprof_original (CC-BY-4.0) · de/synth · chosen for high existing Pleasure Ecstasy score (z=5.78); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Huhu, huch! Oh, die Freude in diesem Moment, die Gnade, die mich überflutet, ich spüre es tief in meinem Herzen. Hey!

Audio caption

A high-pitched, feminine-coded young adult voice delivers an exuberant and highly expressive exclamation in German. The timbre is exceptionally bright and head-resonance dominant, with clear oral projection and minimal vocal roughness or lower chest weight. The delivery begins with lively, play-acted exclamations ('Huhu, huch!'), interrupted by a quick surprised gasp, before continuing with brisk tempo, broad melodic pitch excursions, and intense elation. The emotional space is saturated with euphoria, gratitude, and awe, rendered in a deliberately dramatic, slightly theatrical style that balances between heartfelt enthusiasm and animated character voice. Background noise is virtually non-existent, captured in a clean, dry recording environment with crisp acoustic transients.

Director caption

Perform with radiant, theatrical ecstasy in a bright, elevated head voice: start with a buoyant, playful call, "Huhu, huch!", immediately followed by a quick, breathy gasp of sudden delight. Without dropping momentum, launch into "Oh, die Freude in diesem Moment, die Gnade, die mich überflutet, ich spüre es tief in meinem Herzen," maintaining sweeping melodic range, sharp enunciation, and openhearted gratitude as if overwhelmed by sheer joy. Conclude on a sudden, bright, upward-inflected exclamation: "Hey!"

Gemini bursts1
Base / Small count0.01 / 0.00
Genuineness (G / B / S)3 / 1.49 / 1.53
Burst blend (G / B / S)5 / 5.75 / 6.13
CPS (Base / Small)12.67 / 13.40
0 s8.6 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.98 s · End: 1.25 s · Surprised Gasp gasp
    A quick, breathy intake of air occurring immediately between the opening exclamations and the phrase 'Oh, die Freude', sounding like a light startled gasp mixed with delight; it sits cleanly within the energetic cadence of the speaker's breathless delivery, functioning as a sudden expressive hitch.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.004.364.214.25
brgtvn_BRGT_reg5.003.713.153.08
r headvn_R_HEAD_reg5.004.334.144.00
rangvn_RANG_reg5.004.785.034.81
s dramvn_S_DRAM_reg5.004.994.834.91
valnvn_VALN_reg5.004.003.723.71
atckvn_ATCK_reg4.002.852.632.97
bkgnvn_BKGN_reg4.002.081.821.93
clrtvn_CLRT_reg4.001.721.061.55
darcvn_DARC_reg4.004.764.114.12
emphvn_EMPH_reg4.004.103.933.99
esthvn_ESTH_reg4.001.281.341.30
focsvn_FOCS_reg4.002.382.092.22
harmvn_HARM_reg4.003.713.803.76
r maskvn_R_MASK_reg4.004.243.353.67
r mixdvn_R_MIXD_reg4.001.801.461.38
r oralvn_R_ORAL_reg4.003.723.243.44
rcqlvn_RCQL_reg4.002.742.312.45
regsvn_REGS_reg4.003.523.343.27
s playvn_S_PLAY_reg4.003.362.822.80
smthvn_SMTH_reg4.001.040.630.86
stncvn_STNC_reg4.002.091.842.24
struvn_STRU_reg4.001.961.551.77
tempvn_TEMP_reg4.002.191.801.81
vulnvn_VULN_reg4.003.374.023.72
agevvn_AGEV_reg3.001.662.262.40
arshvn_ARSH_reg3.003.523.253.36
chnkvn_CHNK_reg3.001.651.591.91
fullvn_FULL_reg3.000.580.440.45
s cartvn_S_CART_reg3.004.374.114.40
s casuvn_S_CASU_reg3.002.112.541.94
s convvn_S_CONV_reg3.002.341.671.26
s stryvn_S_STRY_reg3.003.273.273.23
valsvn_VALS_reg3.002.851.851.97
vflxvn_VFLX_reg3.002.872.292.36
warmvn_WARM_reg3.001.311.271.39
metlvn_METL_reg2.003.212.662.81
r chstvn_R_CHST_reg2.000.870.820.85
r naslvn_R_NASL_reg2.003.123.843.26
r thrtvn_R_THRT_reg2.002.301.952.12
respvn_RESP_reg2.002.512.852.63
s monovn_S_MONO_reg2.001.842.232.41
s narrvn_S_NARR_reg2.001.842.032.20
tensvn_TENS_reg2.002.462.452.63
voltvn_VOLT_reg2.003.503.633.57
coglvn_COGL_reg1.001.331.741.74
dfluvn_DFLU_reg1.001.801.791.62
gendvn_GEND_reg1.002.421.651.91
rougvn_ROUG_reg1.002.572.552.57
s authvn_S_AUTH_reg1.000.430.310.42
s formvn_S_FORM_reg1.000.510.590.84
explvn_EXPL_reg0.00-0.06-0.09-0.12
s asmrvn_S_ASMR_reg0.000.390.200.43
s newsvn_S_NEWS_reg0.000.180.420.30
s rantvn_S_RANT_reg0.003.452.693.23
s techvn_S_TECH_reg0.001.590.650.72
s whisvn_S_WHIS_reg0.00-0.510.06-0.11
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.213.12
eiv_extra:Arousal2.222.23
eiv_extra:Authenticity3.293.26
eiv_extra:Background_Noise0.220.28
eiv_extra:Confident_vs._Hesitant0.790.91
eiv_extra:Gender1.461.39
eiv_extra:High-Pitched_vs._Low-Pitched1.101.14
eiv_extra:Monotone_vs._Expressive1.832.05
eiv_extra:Recording_Quality2.822.73
eiv_extra:Serious_vs._Humorous0.981.00
eiv_extra:Soft_vs._Harsh0.540.63
eiv_extra:Submissive_vs._Dominant0.230.33
eiv_extra:Valence1.982.10
eiv_extra:Vulnerable_vs._Emotionally_Detached0.770.75
eiv_extra:Warm_vs._Cold0.820.80
eiv_extra:score_background_quality3.463.52
eiv_extra:score_content_enjoyment4.724.70
eiv_extra:score_overall_quality2.772.86
eiv_extra:score_speech_quality1.951.94
audiobox:CE6.145.53
audiobox:CU6.966.94
audiobox:PC1.101.55
audiobox:PQ7.867.77
dnsmos:SIG_raw3.633.76
dnsmos:BAK_raw3.963.90
dnsmos:OVRL_raw3.373.36
dnsmos:SIG3.333.41
dnsmos:BAK3.933.82
dnsmos:OVRL3.033.02
dnsmos:P808_MOS3.313.43
voiceclap_attribute:Affection1.541.60
voiceclap_attribute:Age3.543.58
voiceclap_attribute:Amusement0.690.55
voiceclap_attribute:Anger1.121.13
voiceclap_attribute:Arousal2.832.26
voiceclap_attribute:Astonishment_Surprise0.921.18
voiceclap_attribute:Authenticity3.283.34
voiceclap_attribute:Awe1.021.10
voiceclap_attribute:Background_Noise0.170.23
voiceclap_attribute:Bitterness0.730.74
voiceclap_attribute:Concentration0.540.39
voiceclap_attribute:Confident_vs._Hesitant0.910.92
voiceclap_attribute:Confusion0.830.82
voiceclap_attribute:Contemplation0.730.90
voiceclap_attribute:Contempt0.560.63
voiceclap_attribute:Contentment0.880.77
voiceclap_attribute:Disappointment1.291.36
voiceclap_attribute:Disgust0.810.72
voiceclap_attribute:Distress1.591.66
voiceclap_attribute:Doubt0.550.58
voiceclap_attribute:Elation1.461.68
voiceclap_attribute:Embarrassment0.540.32
voiceclap_attribute:Emotional_Numbness0.260.51
voiceclap_attribute:Fatigue_Exhaustion0.620.52
voiceclap_attribute:Fear0.850.86
voiceclap_attribute:Gender0.871.33
voiceclap_attribute:Helplessness1.231.42
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.211.17
voiceclap_attribute:Hope_Enthusiasm_Optimism1.361.90
voiceclap_attribute:Impatience_and_Irritability1.301.12
voiceclap_attribute:Infatuation1.161.21
voiceclap_attribute:Interest1.171.31
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness1.030.68
voiceclap_attribute:Jealousy_&_Envy0.991.13
voiceclap_attribute:Longing0.911.05
voiceclap_attribute:Malevolence_Malice0.710.79
voiceclap_attribute:Monotone_vs._Expressive2.242.03
voiceclap_attribute:Pain0.921.05
voiceclap_attribute:Pleasure_Ecstasy1.191.26
voiceclap_attribute:Pride0.791.10
voiceclap_attribute:Recording_Quality2.572.75
voiceclap_attribute:Relief1.911.63
voiceclap_attribute:Sadness1.671.62
voiceclap_attribute:Serious_vs._Humorous0.750.77
voiceclap_attribute:Sexual_Lust0.770.62
voiceclap_attribute:Shame0.840.92
voiceclap_attribute:Soft_vs._Harsh0.470.72
voiceclap_attribute:Sourness0.840.73
voiceclap_attribute:Submissive_vs._Dominant0.500.45
voiceclap_attribute:Teasing0.800.99
voiceclap_attribute:Thankfulness_Gratitude2.082.05
voiceclap_attribute:Triumph1.181.42
voiceclap_attribute:Valence0.630.40
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.570.71
voiceclap_attribute:Warm_vs._Cold0.731.00
voiceclap_attribute:duration4.869.06
voiceclap_attribute:score_background_quality3.443.46
voiceclap_attribute:score_content_enjoyment4.604.86
voiceclap_attribute:score_overall_quality2.662.70
voiceclap_attribute:score_speech_quality1.981.95
voiceclap_attribute:talking_speed11.0911.42
Reproducibility and API usage

Dataset UID: k17_age3_bg1__V__BRGT__very_high__de.c023
Audio SHA-256: 3a0c6ff43c0e63be0f353cf545b7c7cd9a18113451be66f50021413c98caa186
Gemini call: 5.87 s; input tokens 25313; cached tokens 25085; output tokens 1434.

S10-17 · de / synth

Shame

10.7 s · Complete

Source: vprof_repair (CC-BY-4.0) · de/synth · chosen for high existing Shame score (z=5.64); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Ich schäme mich, dass ich mich so vitaminmangelhaft werden ließ, mit trockenen Augen und so sehr trockener Haut. Hinzu kommt die Gewichtszunahme und der hohe Cholesterinspiegel. Es ist peinlich.

Audio caption

A single speaker with a young-adult, masculine-coded vocal presentation speaks in Standard German. The performance is characterized by a subdued, reflective, and somber tone, conveying deep shame, self-directed disappointment, and mild embarrassment. The pitch register sits comfortably in a lower-mid baritone range with restrained melodic movement and controlled dynamic projection that slightly softens toward the end. Articulation is clear, neat, and fluent without audible fillers, false starts, or noticeable hesitations, showing minimal cognitive strain and a linear discourse structure. The vocal timbre is balanced, moderately warm, and periodic, marked by low biological roughness and a gentle, slightly soft attack. Phonation is slightly hushed and inward-looking, leaning toward an intimate monologic or confessional style rather than an interactive conversation. No audible non-speech vocal bursts are detected throughout the utterance. The recording is technically clean and studio-like, featuring an acoustically dry background free of perceptible environmental noise or artifacts.

Director caption

Deliver this as an intimate, vulnerable self-confession steeped in quiet shame and dejection. Begin in a subdued, slightly downcast tone with soft, controlled volume: "Ich schäme mich, dass ich mich so vitaminmangelhaft werden ließ, mit trockenen Augen und so sehr trockener Haut." Keep the pacing steady and the melodic excursions narrow, maintaining modest breath support and a gentle inward focus. Take a very slight, natural pause, then continue listing the physical symptoms in a matter-of-fact yet regretful manner: "Hinzu kommt die Gewichtszunahme und der hohe Cholesterinspiegel." On the final sentence, let the dynamic level ease off slightly, allowing a quiet sense of defeat to color the diction without dramatic sobbing or vocal cracks: "Es ist peinlich."

Gemini bursts0
Base / Small count0.27 / 0.89
Genuineness (G / B / S)4 / 0.97 / 0.89
Burst blend (G / B / S)— / 9.32 / 8.89
CPS (Base / Small)19.03 / 19.18
0 s10.7 s
Event captions and top-3 Whisper classes
  • Existing S10 marker · Start: 0.26 s · End: 0.40 s
  • Base proposals: Start: 0.24 s · End: 0.42 s: Surprised Gasp 0.59, Breathy Giggle 0.33, Wistful Sigh 0.02
  • Small proposals: Start: 0.22 s · End: 0.42 s: Surprised Gasp 0.79, Breathy Giggle 0.14, Wistful Sigh 0.01; Start: 0.28 s · End: 0.44 s: Surprised Gasp 0.61, Ahem 0.20, Breathy Giggle 0.06
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
bkgnvn_BKGN_reg4.003.823.953.93
clrtvn_CLRT_reg4.002.132.262.25
gendvn_GEND_reg4.004.164.794.85
harmvn_HARM_reg4.002.292.582.55
rcqlvn_RCQL_reg4.002.943.273.15
s monovn_S_MONO_reg4.003.503.693.46
smthvn_SMTH_reg4.001.732.452.23
struvn_STRU_reg4.002.302.752.51
vulnvn_VULN_reg4.002.192.092.07
agevvn_AGEV_reg3.002.922.952.61
brgtvn_BRGT_reg3.002.402.422.48
chnkvn_CHNK_reg3.002.452.712.73
esthvn_ESTH_reg3.002.222.602.58
focsvn_FOCS_reg3.001.532.112.11
fullvn_FULL_reg3.001.551.881.67
r chstvn_R_CHST_reg3.002.372.432.35
r maskvn_R_MASK_reg3.001.501.611.60
r mixdvn_R_MIXD_reg3.002.462.632.66
r oralvn_R_ORAL_reg3.002.402.322.36
s convvn_S_CONV_reg3.001.942.252.31
tempvn_TEMP_reg3.001.822.232.17
vflxvn_VFLX_reg3.001.151.121.15
warmvn_WARM_reg3.003.383.493.32
arshvn_ARSH_reg2.002.362.902.72
atckvn_ATCK_reg2.002.052.132.28
darcvn_DARC_reg2.000.911.001.08
emphvn_EMPH_reg2.002.753.002.94
r headvn_R_HEAD_reg2.001.441.591.69
r naslvn_R_NASL_reg2.002.142.162.17
r thrtvn_R_THRT_reg2.002.371.761.86
rangvn_RANG_reg2.003.163.313.42
respvn_RESP_reg2.002.082.042.05
s casuvn_S_CASU_reg2.002.092.332.39
s dramvn_S_DRAM_reg2.001.842.232.22
s formvn_S_FORM_reg2.001.962.502.21
s narrvn_S_NARR_reg2.002.963.013.02
tensvn_TENS_reg2.001.301.531.55
valsvn_VALS_reg2.001.271.681.52
arouvn_AROU_reg1.002.172.212.27
coglvn_COGL_reg1.001.702.031.88
metlvn_METL_reg1.001.251.431.42
regsvn_REGS_reg1.001.411.301.42
rougvn_ROUG_reg1.001.511.461.53
s asmrvn_S_ASMR_reg1.002.232.091.96
s authvn_S_AUTH_reg1.001.351.471.43
s stryvn_S_STRY_reg1.002.502.392.46
s techvn_S_TECH_reg1.00-0.55-0.15-0.16
s whisvn_S_WHIS_reg1.000.120.710.30
stncvn_STNC_reg1.002.492.352.40
valnvn_VALN_reg1.001.451.951.84
voltvn_VOLT_reg1.001.822.182.18
dfluvn_DFLU_reg0.000.810.981.13
explvn_EXPL_reg0.000.240.220.25
s cartvn_S_CART_reg0.000.670.720.76
s newsvn_S_NEWS_reg0.001.211.281.26
s playvn_S_PLAY_reg0.001.190.971.35
s rantvn_S_RANT_reg0.002.392.612.64
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.303.26
eiv_extra:Arousal1.741.84
eiv_extra:Authenticity3.183.27
eiv_extra:Background_Noise0.130.15
eiv_extra:Confident_vs._Hesitant0.930.69
eiv_extra:Gender-0.380.23
eiv_extra:High-Pitched_vs._Low-Pitched1.401.26
eiv_extra:Monotone_vs._Expressive1.701.53
eiv_extra:Recording_Quality2.712.93
eiv_extra:Serious_vs._Humorous0.820.40
eiv_extra:Soft_vs._Harsh0.010.01
eiv_extra:Submissive_vs._Dominant0.630.57
eiv_extra:Valence-1.08-0.73
eiv_extra:Vulnerable_vs._Emotionally_Detached1.241.10
eiv_extra:Warm_vs._Cold-0.21-0.08
eiv_extra:score_background_quality3.883.96
eiv_extra:score_content_enjoyment4.944.95
eiv_extra:score_overall_quality3.283.34
eiv_extra:score_speech_quality1.941.95
audiobox:CE6.356.19
audiobox:CU6.916.98
audiobox:PC1.421.66
audiobox:PQ7.838.02
dnsmos:SIG_raw4.254.33
dnsmos:BAK_raw4.564.62
dnsmos:OVRL_raw4.094.14
dnsmos:SIG3.683.74
dnsmos:BAK4.214.29
dnsmos:OVRL3.493.53
dnsmos:P808_MOS3.924.14
voiceclap_attribute:Affection0.921.04
voiceclap_attribute:Age3.303.31
voiceclap_attribute:Amusement0.200.23
voiceclap_attribute:Anger0.941.24
voiceclap_attribute:Arousal1.461.46
voiceclap_attribute:Astonishment_Surprise0.500.49
voiceclap_attribute:Authenticity3.223.37
voiceclap_attribute:Awe0.490.69
voiceclap_attribute:Background_Noise0.06-0.06
voiceclap_attribute:Bitterness0.660.82
voiceclap_attribute:Concentration0.800.92
voiceclap_attribute:Confident_vs._Hesitant0.950.78
voiceclap_attribute:Confusion0.810.80
voiceclap_attribute:Contemplation1.100.89
voiceclap_attribute:Contempt0.760.91
voiceclap_attribute:Contentment0.660.83
voiceclap_attribute:Disappointment1.321.43
voiceclap_attribute:Disgust0.720.84
voiceclap_attribute:Distress1.161.23
voiceclap_attribute:Doubt0.780.83
voiceclap_attribute:Elation0.450.47
voiceclap_attribute:Embarrassment0.510.56
voiceclap_attribute:Emotional_Numbness0.890.98
voiceclap_attribute:Fatigue_Exhaustion0.760.82
voiceclap_attribute:Fear0.870.84
voiceclap_attribute:Gender0.540.54
voiceclap_attribute:Helplessness0.851.04
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.221.18
voiceclap_attribute:Hope_Enthusiasm_Optimism0.660.83
voiceclap_attribute:Impatience_and_Irritability1.011.30
voiceclap_attribute:Infatuation0.930.90
voiceclap_attribute:Interest1.301.15
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.440.63
voiceclap_attribute:Jealousy_&_Envy1.041.14
voiceclap_attribute:Longing0.920.98
voiceclap_attribute:Malevolence_Malice0.650.86
voiceclap_attribute:Monotone_vs._Expressive1.401.47
voiceclap_attribute:Pain0.690.68
voiceclap_attribute:Pleasure_Ecstasy0.540.65
voiceclap_attribute:Pride1.091.13
voiceclap_attribute:Recording_Quality2.752.89
voiceclap_attribute:Relief1.831.80
voiceclap_attribute:Sadness1.191.39
voiceclap_attribute:Serious_vs._Humorous0.530.51
voiceclap_attribute:Sexual_Lust0.290.44
voiceclap_attribute:Shame1.111.32
voiceclap_attribute:Soft_vs._Harsh0.170.13
voiceclap_attribute:Sourness0.851.06
voiceclap_attribute:Submissive_vs._Dominant0.550.75
voiceclap_attribute:Teasing0.750.73
voiceclap_attribute:Thankfulness_Gratitude2.232.22
voiceclap_attribute:Triumph0.960.97
voiceclap_attribute:Valence0.220.03
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.050.94
voiceclap_attribute:Warm_vs._Cold-0.010.10
voiceclap_attribute:duration10.5211.51
voiceclap_attribute:score_background_quality3.763.99
voiceclap_attribute:score_content_enjoyment4.864.93
voiceclap_attribute:score_overall_quality3.043.27
voiceclap_attribute:score_speech_quality1.941.95
voiceclap_attribute:talking_speed15.4017.87
Reproducibility and API usage

Dataset UID: mediathek_0283__E__Shame__B__de.c005
Audio SHA-256: 77e2110b7bbaf81f61d0ac45eedefec5fb7058198e51fa018c5919e36f5ad845
Gemini call: 6.31 s; input tokens 25367; cached tokens 25085; output tokens 1427.

S10-18 · de / synth

Fatigue Exhaustion

14.0 s · Complete

Source: vprof_repair (CC-BY-4.0) · de/synth · chosen for high existing Fatigue Exhaustion score (z=7.52); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Dieser ständige Drang, alles allein entscheiden zu müssen, ist so erschöpfend. Ich fühle mich einfach völlig ausgelaugt, weil ich die ganze Last alleine trage.

Audio caption

A mature adult masculine-coded voice speaks in German with a Standard German accent, delivering a slow, heavy, and deeply weary monologue. The vocal timbre is low, baritone-centered, characterized by substantial biological roughness, gravelly vocal fry, and prominent pharyngeal and chest resonance. The tempo is very slow and heavily chunked into brief, laboriously sustained phrases separated by tired breath pauses and weary exhalations. Articulation remains clear but weighted by fatigue, with breathy, soft attacks and limited pitch excursion. The emotional posture is defined by severe exhaustion, sadness, helplessness, and subtle bitter disappointment. The acoustic environment is clean with minimal background noise, and the performance possesses a high degree of genuineness, capturing the raw, lived-in texture of psychological overwhelm.

Director caption

Deliver this as an intimate, emotionally drained soliloquy in a low baritone register, weighted down by profound fatigue. Start slowly and deliberately with a gravelly, fry-laced tone: "Dieser ständige Drang, alles allein entscheiden zu müssen,". Right at the end of the phrase, let out a weary, descending vocal sigh and exhausted groan before continuing with a breathy, dragging cadence: "ist so erschöpfend." Pause and take a slow, clearly audible breath of surrender. Resume with soft, defenseless enunciation: "Ich fühle mich einfach völlig ausgelaugt,". Drag out the pacing slightly on the final clause, keeping the tone grounded in deep chest and throat resonance with minimal pitch movement: "weil ich die ganze Last alleine trage."

Gemini bursts2
Base / Small count0.00 / 0.00
Genuineness (G / B / S)5 / 1.09 / 1.02
Burst blend (G / B / S)8 / 8.71 / 8.45
CPS (Base / Small)11.74 / 11.62
0 s14.0 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 4.88 s · End: 5.48 s · Exhausted Groan sigh_neg
    A weary, low-pitched breathy sigh and vocalized groan occurs right before 'ist so erschöpfend', conveying deep mental and physical deflation; it blends smoothly from the previous clause and sets a heavily fatigued tone for the subsequent phrase.
  • Gemini · Start: 6.35 s · End: 6.85 s · Deep Breath breath_calm
    An audible, slow inhalation occurs during the pause between sentences, displaying laboured respiratory effort consistent with emotional exhaustion before transitioning into the vulnerable confession 'Ich fühle mich einfach'.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.895.065.04
agevvn_AGEV_reg4.004.814.414.16
bkgnvn_BKGN_reg4.002.802.802.77
clrtvn_CLRT_reg4.001.421.411.40
r chstvn_R_CHST_reg4.003.133.003.00
r thrtvn_R_THRT_reg4.002.141.872.02
rcqlvn_RCQL_reg4.003.183.313.32
respvn_RESP_reg4.002.712.762.62
rougvn_ROUG_reg4.002.131.851.88
s monovn_S_MONO_reg4.004.914.544.79
struvn_STRU_reg4.002.442.452.51
vulnvn_VULN_reg4.003.373.213.16
emphvn_EMPH_reg3.001.491.441.51
esthvn_ESTH_reg3.002.722.882.86
focsvn_FOCS_reg3.001.351.591.72
fullvn_FULL_reg3.003.173.033.21
r mixdvn_R_MIXD_reg3.000.840.830.94
r oralvn_R_ORAL_reg3.000.700.750.75
s casuvn_S_CASU_reg3.001.521.381.42
s convvn_S_CONV_reg3.00-0.05-0.10-0.06
s dramvn_S_DRAM_reg3.002.933.113.09
smthvn_SMTH_reg3.002.091.891.98
tensvn_TENS_reg3.000.671.000.68
valsvn_VALS_reg3.001.591.651.73
vflxvn_VFLX_reg3.000.230.140.07
warmvn_WARM_reg3.004.404.264.41
arshvn_ARSH_reg2.001.841.911.89
atckvn_ATCK_reg2.000.380.470.36
brgtvn_BRGT_reg2.001.581.581.57
chnkvn_CHNK_reg2.000.900.690.77
coglvn_COGL_reg2.003.023.443.08
darcvn_DARC_reg2.00-0.47-0.26-0.41
harmvn_HARM_reg2.001.981.811.78
rangvn_RANG_reg2.002.312.062.17
s asmrvn_S_ASMR_reg2.004.113.883.92
s narrvn_S_NARR_reg2.002.832.612.78
s whisvn_S_WHIS_reg2.004.354.264.46
voltvn_VOLT_reg2.001.672.001.89
arouvn_AROU_reg1.000.830.760.84
dfluvn_DFLU_reg1.001.171.231.14
metlvn_METL_reg1.000.520.630.54
r headvn_R_HEAD_reg1.000.410.500.58
r maskvn_R_MASK_reg1.000.480.640.46
r naslvn_R_NASL_reg1.000.980.800.89
regsvn_REGS_reg1.000.220.370.44
s authvn_S_AUTH_reg1.000.360.540.37
s formvn_S_FORM_reg1.002.382.522.61
s stryvn_S_STRY_reg1.003.243.103.13
stncvn_STNC_reg1.001.581.531.52
tempvn_TEMP_reg1.000.670.740.67
valnvn_VALN_reg1.002.251.982.21
explvn_EXPL_reg0.00-0.43-0.41-0.41
s cartvn_S_CART_reg0.002.452.642.44
s newsvn_S_NEWS_reg0.001.150.950.92
s playvn_S_PLAY_reg0.00-0.16-0.27-0.15
s rantvn_S_RANT_reg0.001.511.531.36
s techvn_S_TECH_reg0.00-2.06-1.79-1.65
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.543.41
eiv_extra:Arousal1.381.13
eiv_extra:Authenticity3.243.19
eiv_extra:Background_Noise0.11-0.11
eiv_extra:Confident_vs._Hesitant1.100.98
eiv_extra:Gender-0.62-0.21
eiv_extra:High-Pitched_vs._Low-Pitched1.811.51
eiv_extra:Monotone_vs._Expressive1.631.41
eiv_extra:Recording_Quality2.722.78
eiv_extra:Serious_vs._Humorous0.18-0.12
eiv_extra:Soft_vs._Harsh0.130.09
eiv_extra:Submissive_vs._Dominant0.550.31
eiv_extra:Valence-1.46-1.07
eiv_extra:Vulnerable_vs._Emotionally_Detached1.160.98
eiv_extra:Warm_vs._Cold-0.32-0.13
eiv_extra:score_background_quality3.453.53
eiv_extra:score_content_enjoyment4.774.85
eiv_extra:score_overall_quality2.922.96
eiv_extra:score_speech_quality1.801.90
audiobox:CE6.216.09
audiobox:CU6.576.78
audiobox:PC1.471.69
audiobox:PQ7.757.81
dnsmos:SIG_raw4.234.24
dnsmos:BAK_raw4.484.51
dnsmos:OVRL_raw4.014.05
dnsmos:SIG3.673.68
dnsmos:BAK4.194.21
dnsmos:OVRL3.443.46
dnsmos:P808_MOS4.013.96
voiceclap_attribute:Affection1.491.49
voiceclap_attribute:Age3.433.51
voiceclap_attribute:Amusement-0.06-0.04
voiceclap_attribute:Anger0.830.95
voiceclap_attribute:Arousal1.291.02
voiceclap_attribute:Astonishment_Surprise0.240.07
voiceclap_attribute:Authenticity3.213.24
voiceclap_attribute:Awe0.750.94
voiceclap_attribute:Background_Noise0.250.17
voiceclap_attribute:Bitterness0.830.88
voiceclap_attribute:Concentration1.181.24
voiceclap_attribute:Confident_vs._Hesitant1.161.07
voiceclap_attribute:Confusion0.810.66
voiceclap_attribute:Contemplation2.012.01
voiceclap_attribute:Contempt0.330.43
voiceclap_attribute:Contentment1.041.09
voiceclap_attribute:Disappointment1.441.41
voiceclap_attribute:Disgust0.450.42
voiceclap_attribute:Distress1.751.39
voiceclap_attribute:Doubt0.740.66
voiceclap_attribute:Elation0.470.41
voiceclap_attribute:Embarrassment0.310.35
voiceclap_attribute:Emotional_Numbness0.841.04
voiceclap_attribute:Fatigue_Exhaustion0.881.08
voiceclap_attribute:Fear0.970.83
voiceclap_attribute:Gender-0.08-0.09
voiceclap_attribute:Helplessness1.261.34
voiceclap_attribute:High-Pitched_vs._Low-Pitched2.002.08
voiceclap_attribute:Hope_Enthusiasm_Optimism1.090.91
voiceclap_attribute:Impatience_and_Irritability0.710.62
voiceclap_attribute:Infatuation1.161.34
voiceclap_attribute:Interest1.281.34
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.610.88
voiceclap_attribute:Jealousy_&_Envy0.740.80
voiceclap_attribute:Longing1.271.39
voiceclap_attribute:Malevolence_Malice0.980.93
voiceclap_attribute:Monotone_vs._Expressive1.921.88
voiceclap_attribute:Pain0.910.89
voiceclap_attribute:Pleasure_Ecstasy0.710.71
voiceclap_attribute:Pride0.850.94
voiceclap_attribute:Recording_Quality2.512.64
voiceclap_attribute:Relief1.391.54
voiceclap_attribute:Sadness1.611.67
voiceclap_attribute:Serious_vs._Humorous0.300.29
voiceclap_attribute:Sexual_Lust0.750.88
voiceclap_attribute:Shame1.171.03
voiceclap_attribute:Soft_vs._Harsh0.470.59
voiceclap_attribute:Sourness0.600.71
voiceclap_attribute:Submissive_vs._Dominant0.550.58
voiceclap_attribute:Teasing0.250.35
voiceclap_attribute:Thankfulness_Gratitude1.941.87
voiceclap_attribute:Triumph0.820.80
voiceclap_attribute:Valence-0.43-0.35
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.111.07
voiceclap_attribute:Warm_vs._Cold-0.060.17
voiceclap_attribute:duration13.5914.17
voiceclap_attribute:score_background_quality3.503.71
voiceclap_attribute:score_content_enjoyment4.744.79
voiceclap_attribute:score_overall_quality2.782.95
voiceclap_attribute:score_speech_quality1.861.90
voiceclap_attribute:talking_speed11.0911.20
Reproducibility and API usage

Dataset UID: k209_age4_bg1__E__Fatigue_Exhaustion__C__de__c043
Audio SHA-256: e1776d824c59cb99303a5a18a513eef0f82795d3576eb3052e19e7469ba06c05
Gemini call: 6.78 s; input tokens 25449; cached tokens 25085; output tokens 1585.

S10-19 · de / synth

Pride

6.6 s · Complete

Source: vc_sidon (CC-BY-4.0) · de/synth · chosen for high existing Pride score (z=6.52); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

German · Standard German

Transcript

Ich bin einfach so enttäuscht. Ich habe diese Schleifen immer perfekt hinbekommen, nie einmal so versagt.

Audio caption

A single feminine-coded voice, sounding like a young adult, speaks Standard German with clear, heightened theatrical emotion characterized by deep disappointment, bitter disbelief, and frustrated pride. The timbral profile is bright and slightly forward, driven primarily by oral and mask resonance with relatively thin chest support and noticeable throat tension. Syllable delivery is crisp and clear with an emphatic, slightly clipped rhythm. The performance begins with a sharp, distressed intake of breath before articulating profound letdown, followed by an exasperated sigh that introduces an indignant defense of past perfection. The recording is pristine and studio-clean with an acoustically dry background, free of distracting ambient noise or technical distortion. While the dramatic delivery leans somewhat into animated or voice-acting style, the vocal bursts and breath management integrate convincingly into the spoken phrases.

Director caption

Begin with an audible, sudden intake of breath expressing disbelief, then enter with high vulnerability and throat tension on "Ich bin einfach so enttäuscht." Drop the pitch slightly on the final syllables to register deep deflation. Immediately release an irritated, breathy huff of exasperation, then quickly pick up the pace with defensive indignation: "Ich habe diese Schleifen immer perfekt hinbekommen,", sharply punching the word 'immer' and leaning on 'perfekt'. Conclude without pausing, letting a bitter, slightly higher-pitched edge carry the final phrase, "nie einmal so versagt.", cutting the final consonant cleanly with unresolved distress.

Gemini bursts2
Base / Small count0.96 / 1.00
Genuineness (G / B / S)4 / 1.43 / 1.56
Burst blend (G / B / S)7 / 5.14 / 5.55
CPS (Base / Small)17.09 / 17.83
0 s6.6 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.00 s · End: 0.17 s · Sharp Inhale gasp
    A sharp, quick inhalation occurs right before the first word 'Ich', marked by a sudden intake of air through slightly parted lips, setting a tense, distressed emotional baseline for the line and connecting smoothly into the onset of speech.
  • Gemini · Start: 2.22 s · End: 2.45 s · Exasperated Sigh sigh_neg
    A short, exasperated huff/sigh is expelled between 'enttäuscht' and 'Ich habe', carrying audible friction and vocal fold tension that underscores acute frustration, cleanly bridging the two spoken clauses.
  • Existing S10 marker · Start: 0.02 s · End: 0.30 s
  • Base proposals: Start: 0.00 s · End: 0.32 s: Surprised Gasp 0.92, Breathy Giggle 0.03, Snicker 0.00
  • Small proposals: Start: 0.02 s · End: 0.36 s: Surprised Gasp 0.97, Breathy Giggle 0.00, Nervous Giggle 0.00; Start: 0.10 s · End: 0.30 s: Surprised Gasp 0.96, Breathy Giggle 0.00, Snicker 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
atckvn_ATCK_reg4.004.013.383.62
bkgnvn_BKGN_reg4.002.963.153.10
brgtvn_BRGT_reg4.003.713.953.79
clrtvn_CLRT_reg4.003.403.053.07
emphvn_EMPH_reg4.004.174.134.22
focsvn_FOCS_reg4.003.182.972.99
r maskvn_R_MASK_reg4.003.543.713.57
r oralvn_R_ORAL_reg4.003.973.893.71
rangvn_RANG_reg4.004.544.734.95
rcqlvn_RCQL_reg4.003.013.273.31
regsvn_REGS_reg4.003.523.573.72
s dramvn_S_DRAM_reg4.003.984.064.32
struvn_STRU_reg4.002.512.452.30
tensvn_TENS_reg4.003.053.023.01
vulnvn_VULN_reg4.001.732.312.40
agevvn_AGEV_reg3.002.672.482.50
arouvn_AROU_reg3.003.433.303.27
arshvn_ARSH_reg3.004.193.733.70
chnkvn_CHNK_reg3.003.113.142.93
darcvn_DARC_reg3.003.333.363.42
esthvn_ESTH_reg3.002.432.552.46
fullvn_FULL_reg3.001.411.691.51
harmvn_HARM_reg3.003.623.013.00
r headvn_R_HEAD_reg3.002.803.303.02
r mixdvn_R_MIXD_reg3.001.541.481.34
respvn_RESP_reg3.002.162.572.63
s casuvn_S_CASU_reg3.001.622.141.91
s convvn_S_CONV_reg3.001.952.522.30
s monovn_S_MONO_reg3.002.062.512.45
s rantvn_S_RANT_reg3.004.214.093.97
smthvn_SMTH_reg3.001.951.931.74
stncvn_STNC_reg3.003.813.363.50
tempvn_TEMP_reg3.004.053.953.90
valsvn_VALS_reg3.002.892.882.38
vflxvn_VFLX_reg3.002.352.682.33
metlvn_METL_reg2.002.352.312.19
r naslvn_R_NASL_reg2.004.504.434.48
r thrtvn_R_THRT_reg2.002.212.232.09
s authvn_S_AUTH_reg2.001.851.271.27
s cartvn_S_CART_reg2.004.234.484.29
voltvn_VOLT_reg2.002.813.173.35
warmvn_WARM_reg2.002.442.562.55
coglvn_COGL_reg1.001.381.641.67
dfluvn_DFLU_reg1.001.311.521.59
gendvn_GEND_reg1.001.431.361.32
r chstvn_R_CHST_reg1.001.101.251.07
rougvn_ROUG_reg1.002.472.522.44
s formvn_S_FORM_reg1.001.401.431.29
s narrvn_S_NARR_reg1.002.452.462.28
s stryvn_S_STRY_reg1.002.763.403.04
valnvn_VALN_reg1.002.002.111.89
explvn_EXPL_reg0.000.280.060.13
s asmrvn_S_ASMR_reg0.000.980.721.05
s newsvn_S_NEWS_reg0.000.240.230.10
s playvn_S_PLAY_reg0.003.503.783.63
s techvn_S_TECH_reg0.001.871.781.61
s whisvn_S_WHIS_reg0.00-0.250.260.31
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.373.31
eiv_extra:Arousal1.911.96
eiv_extra:Authenticity3.223.13
eiv_extra:Background_Noise-0.06-0.16
eiv_extra:Confident_vs._Hesitant0.710.71
eiv_extra:Gender1.431.36
eiv_extra:High-Pitched_vs._Low-Pitched1.030.97
eiv_extra:Monotone_vs._Expressive1.721.65
eiv_extra:Recording_Quality2.842.81
eiv_extra:Serious_vs._Humorous0.981.11
eiv_extra:Soft_vs._Harsh0.320.20
eiv_extra:Submissive_vs._Dominant0.520.68
eiv_extra:Valence-0.310.07
eiv_extra:Vulnerable_vs._Emotionally_Detached0.940.84
eiv_extra:Warm_vs._Cold0.110.17
eiv_extra:score_background_quality3.783.68
eiv_extra:score_content_enjoyment4.814.88
eiv_extra:score_overall_quality3.073.09
eiv_extra:score_speech_quality1.952.01
audiobox:CE6.446.08
audiobox:CU7.097.08
audiobox:PC1.691.91
audiobox:PQ7.957.86
dnsmos:SIG_raw4.084.15
dnsmos:BAK_raw4.394.33
dnsmos:OVRL_raw3.903.90
dnsmos:SIG3.603.64
dnsmos:BAK4.144.08
dnsmos:OVRL3.363.37
dnsmos:P808_MOS3.573.62
voiceclap_attribute:Affection0.710.76
voiceclap_attribute:Age3.603.46
voiceclap_attribute:Amusement1.050.83
voiceclap_attribute:Anger1.381.36
voiceclap_attribute:Arousal2.092.02
voiceclap_attribute:Astonishment_Surprise1.201.20
voiceclap_attribute:Authenticity3.203.27
voiceclap_attribute:Awe0.620.58
voiceclap_attribute:Background_Noise0.02-0.03
voiceclap_attribute:Bitterness0.710.74
voiceclap_attribute:Concentration0.380.61
voiceclap_attribute:Confident_vs._Hesitant0.660.87
voiceclap_attribute:Confusion0.800.91
voiceclap_attribute:Contemplation0.460.58
voiceclap_attribute:Contempt0.911.01
voiceclap_attribute:Contentment0.430.39
voiceclap_attribute:Disappointment1.311.41
voiceclap_attribute:Disgust1.171.12
voiceclap_attribute:Distress1.131.13
voiceclap_attribute:Doubt0.640.70
voiceclap_attribute:Elation0.850.88
voiceclap_attribute:Embarrassment0.600.63
voiceclap_attribute:Emotional_Numbness0.360.64
voiceclap_attribute:Fatigue_Exhaustion0.420.52
voiceclap_attribute:Fear0.580.66
voiceclap_attribute:Gender1.511.85
voiceclap_attribute:Helplessness0.760.99
voiceclap_attribute:High-Pitched_vs._Low-Pitched0.910.99
voiceclap_attribute:Hope_Enthusiasm_Optimism1.031.12
voiceclap_attribute:Impatience_and_Irritability1.761.45
voiceclap_attribute:Infatuation0.650.76
voiceclap_attribute:Interest1.341.12
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.630.79
voiceclap_attribute:Jealousy_&_Envy1.181.31
voiceclap_attribute:Longing0.540.69
voiceclap_attribute:Malevolence_Malice0.930.97
voiceclap_attribute:Monotone_vs._Expressive1.811.83
voiceclap_attribute:Pain0.540.56
voiceclap_attribute:Pleasure_Ecstasy0.640.73
voiceclap_attribute:Pride1.031.23
voiceclap_attribute:Recording_Quality2.792.90
voiceclap_attribute:Relief1.701.70
voiceclap_attribute:Sadness0.921.07
voiceclap_attribute:Serious_vs._Humorous1.050.89
voiceclap_attribute:Sexual_Lust0.470.33
voiceclap_attribute:Shame0.670.86
voiceclap_attribute:Soft_vs._Harsh0.120.26
voiceclap_attribute:Sourness1.141.12
voiceclap_attribute:Submissive_vs._Dominant0.740.69
voiceclap_attribute:Teasing1.171.00
voiceclap_attribute:Thankfulness_Gratitude1.731.87
voiceclap_attribute:Triumph1.131.29
voiceclap_attribute:Valence0.260.22
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.880.75
voiceclap_attribute:Warm_vs._Cold0.000.16
voiceclap_attribute:duration6.078.05
voiceclap_attribute:score_background_quality3.673.67
voiceclap_attribute:score_content_enjoyment4.814.89
voiceclap_attribute:score_overall_quality2.912.93
voiceclap_attribute:score_speech_quality2.012.00
voiceclap_attribute:talking_speed14.5816.93
Reproducibility and API usage

Dataset UID: anime_035__E__Jealousy_and_Envy__A__de.c024.k3
Audio SHA-256: bd81ab2c953ee622cb532f6e02ecb95fffdc2a7bd6acb5710af56552e07568ab
Gemini call: 8.07 s; input tokens 25265; cached tokens 25085; output tokens 1552.

S10-20 · en / synth

Bitterness

6.2 s · Complete

Source: vc_sidon (CC-BY-4.0) · en/synth · chosen for high existing Bitterness score (z=5.20); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

tuck away my mistake like it was a dirty secret. Bury it deep beneath all my shame.

Audio caption

A single young-adult-sounding masculine-coded speaker delivers an intense, dramatic soliloquy in General American English with a deep, grounded baritone register. Timbrally, the voice is moderately warm, resonant, and textured with audible pharyngeal tension and subtle vocal fry that conveys biting bitterness and self-directed disgust. Articulation is crisp and deliberate, utilizing controlled plosives and punchy emphasis on key thematic words such as 'mistake', 'dirty secret', and 'shame'. The pacing begins with moderate, rhythmic forward momentum before pulling back into a slower, hushed, half-whispered intensity across the second clause. The emotional profile is heavily weighted toward bitter distress, contempt, and intense remorse/shame, framed in a stark, inward monologue style. Muscular neck and throat constriction remain elevated throughout, lending an incisive, hard-edged bite to the phonation. Acoustically, the recording is exceptionally clean with virtually dead background ambience and minimal room coloration, capturing clear proximity and high fidelity.

Director caption

Deliver this as an intense, self-scathing internal monologue, keeping the vocal register low and grounded in chest and throat resonance. Start with a firm, cutting attack and a brisk, bitter cadence: "tuck away my mistake like it was a dirty secret." Lean heavily into the plosives and inject a contemptuous, biting edge into "dirty secret." Take a tense, deliberate micro-pause before shifting into a lower, darker, half-whispered intensity; let throat constriction tighten the vocal cords as you deliver: "Bury it deep beneath all my shame." Finish by letting the final word "shame" linger slightly with a breathy, hollow dissipation, capturing deep inward remorse and cold disgust.

Gemini bursts0
Base / Small count0.61 / 0.12
Genuineness (G / B / S)4 / 0.97 / 0.92
Burst blend (G / B / S)— / 7.60 / 7.40
CPS (Base / Small)14.64 / 14.52
0 s6.2 s
Event captions and top-3 Whisper classes
  • Base proposals: Start: 0.30 s · End: 0.56 s: Contented Sigh 0.53, Sharp Inhale 0.27, Wistful Sigh 0.05
  • Small proposals: Start: 0.30 s · End: 0.54 s: Contented Sigh 0.86, Ahem 0.03, Whispered Mumble 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.005.115.035.15
s monovn_S_MONO_reg5.004.544.164.50
atckvn_ATCK_reg4.000.140.350.61
bkgnvn_BKGN_reg4.003.563.493.51
clrtvn_CLRT_reg4.001.431.431.31
emphvn_EMPH_reg4.002.452.742.65
esthvn_ESTH_reg4.002.832.792.88
focsvn_FOCS_reg4.003.943.924.08
fullvn_FULL_reg4.002.642.522.55
r chstvn_R_CHST_reg4.003.112.923.06
r mixdvn_R_MIXD_reg4.001.801.621.62
r thrtvn_R_THRT_reg4.001.991.712.11
rcqlvn_RCQL_reg4.003.213.133.29
s dramvn_S_DRAM_reg4.004.214.054.50
smthvn_SMTH_reg4.002.041.972.06
stncvn_STNC_reg4.002.822.683.14
struvn_STRU_reg4.001.811.721.76
tensvn_TENS_reg4.001.411.701.74
vulnvn_VULN_reg4.002.442.172.26
agevvn_AGEV_reg3.003.583.473.32
arouvn_AROU_reg3.001.992.062.30
brgtvn_BRGT_reg3.001.321.511.31
chnkvn_CHNK_reg3.001.331.521.44
harmvn_HARM_reg3.001.121.111.24
metlvn_METL_reg3.001.491.772.03
r maskvn_R_MASK_reg3.00-0.36-0.24-0.37
r oralvn_R_ORAL_reg3.001.331.151.08
rougvn_ROUG_reg3.004.294.434.48
s authvn_S_AUTH_reg3.001.561.581.79
s formvn_S_FORM_reg3.001.481.391.55
s narrvn_S_NARR_reg3.002.812.722.88
s rantvn_S_RANT_reg3.001.892.131.95
s stryvn_S_STRY_reg3.003.233.333.55
tempvn_TEMP_reg3.001.101.311.37
warmvn_WARM_reg3.003.703.443.46
arshvn_ARSH_reg2.002.412.672.87
darcvn_DARC_reg2.001.081.431.52
rangvn_RANG_reg2.002.242.332.40
respvn_RESP_reg2.003.774.233.93
s convvn_S_CONV_reg2.001.621.951.48
s whisvn_S_WHIS_reg2.003.923.974.26
valsvn_VALS_reg2.001.351.491.37
vflxvn_VFLX_reg2.001.441.412.23
voltvn_VOLT_reg2.003.393.653.66
coglvn_COGL_reg1.001.591.281.46
r headvn_R_HEAD_reg1.000.670.570.59
r naslvn_R_NASL_reg1.000.540.510.35
regsvn_REGS_reg1.000.170.130.15
s asmrvn_S_ASMR_reg1.002.362.032.23
s casuvn_S_CASU_reg1.001.331.481.20
valnvn_VALN_reg1.000.02-0.070.01
dfluvn_DFLU_reg0.001.291.301.14
explvn_EXPL_reg0.000.380.600.41
s cartvn_S_CART_reg0.001.971.981.92
s newsvn_S_NEWS_reg0.000.650.410.56
s playvn_S_PLAY_reg0.00-0.540.03-0.37
s techvn_S_TECH_reg0.00-0.81-0.80-0.86
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.383.34
eiv_extra:Arousal1.781.61
eiv_extra:Authenticity3.193.15
eiv_extra:Background_Noise-0.11-0.24
eiv_extra:Confident_vs._Hesitant0.720.73
eiv_extra:Gender-0.07-0.29
eiv_extra:High-Pitched_vs._Low-Pitched1.281.40
eiv_extra:Monotone_vs._Expressive1.251.45
eiv_extra:Recording_Quality2.812.90
eiv_extra:Serious_vs._Humorous0.220.01
eiv_extra:Soft_vs._Harsh-0.03-0.08
eiv_extra:Submissive_vs._Dominant0.790.58
eiv_extra:Valence-0.57-0.73
eiv_extra:Vulnerable_vs._Emotionally_Detached1.161.24
eiv_extra:Warm_vs._Cold-0.18-0.15
eiv_extra:score_background_quality3.623.46
eiv_extra:score_content_enjoyment4.674.72
eiv_extra:score_overall_quality2.862.80
eiv_extra:score_speech_quality1.821.83
audiobox:CE6.406.32
audiobox:CU7.267.47
audiobox:PC1.621.66
audiobox:PQ7.938.07
dnsmos:SIG_raw4.054.13
dnsmos:BAK_raw4.334.40
dnsmos:OVRL_raw3.823.88
dnsmos:SIG3.573.63
dnsmos:BAK4.084.18
dnsmos:OVRL3.313.37
dnsmos:P808_MOS3.963.96
voiceclap_attribute:Affection1.231.45
voiceclap_attribute:Age3.333.34
voiceclap_attribute:Amusement0.590.31
voiceclap_attribute:Anger2.311.94
voiceclap_attribute:Arousal2.602.38
voiceclap_attribute:Astonishment_Surprise1.041.04
voiceclap_attribute:Authenticity3.223.24
voiceclap_attribute:Awe0.921.08
voiceclap_attribute:Background_Noise0.130.14
voiceclap_attribute:Bitterness1.031.08
voiceclap_attribute:Concentration0.320.58
voiceclap_attribute:Confident_vs._Hesitant0.530.66
voiceclap_attribute:Confusion0.490.56
voiceclap_attribute:Contemplation0.660.71
voiceclap_attribute:Contempt1.211.21
voiceclap_attribute:Contentment0.410.50
voiceclap_attribute:Disappointment1.581.66
voiceclap_attribute:Disgust1.331.19
voiceclap_attribute:Distress1.651.80
voiceclap_attribute:Doubt0.590.57
voiceclap_attribute:Elation0.770.71
voiceclap_attribute:Embarrassment0.680.71
voiceclap_attribute:Emotional_Numbness0.720.92
voiceclap_attribute:Fatigue_Exhaustion0.510.57
voiceclap_attribute:Fear1.191.25
voiceclap_attribute:Gender-0.14-0.02
voiceclap_attribute:Helplessness1.161.41
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.151.37
voiceclap_attribute:Hope_Enthusiasm_Optimism0.881.15
voiceclap_attribute:Impatience_and_Irritability2.161.67
voiceclap_attribute:Infatuation1.541.54
voiceclap_attribute:Interest1.071.01
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.900.86
voiceclap_attribute:Jealousy_&_Envy1.311.20
voiceclap_attribute:Longing0.821.04
voiceclap_attribute:Malevolence_Malice2.131.97
voiceclap_attribute:Monotone_vs._Expressive1.981.99
voiceclap_attribute:Pain0.911.05
voiceclap_attribute:Pleasure_Ecstasy0.780.81
voiceclap_attribute:Pride1.121.08
voiceclap_attribute:Recording_Quality2.742.76
voiceclap_attribute:Relief1.381.27
voiceclap_attribute:Sadness1.471.72
voiceclap_attribute:Serious_vs._Humorous0.440.14
voiceclap_attribute:Sexual_Lust1.361.43
voiceclap_attribute:Shame1.181.35
voiceclap_attribute:Soft_vs._Harsh-0.51-0.10
voiceclap_attribute:Sourness1.151.15
voiceclap_attribute:Submissive_vs._Dominant1.350.97
voiceclap_attribute:Teasing0.690.48
voiceclap_attribute:Thankfulness_Gratitude2.071.78
voiceclap_attribute:Triumph1.301.15
voiceclap_attribute:Valence-1.12-1.12
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.990.83
voiceclap_attribute:Warm_vs._Cold-0.57-0.31
voiceclap_attribute:duration7.087.40
voiceclap_attribute:score_background_quality3.433.43
voiceclap_attribute:score_content_enjoyment4.744.72
voiceclap_attribute:score_overall_quality2.612.69
voiceclap_attribute:score_speech_quality1.881.90
voiceclap_attribute:talking_speed12.6914.79
Reproducibility and API usage

Dataset UID: k165_age3_bg1__V__S_WHIS__moderately_high__en.c024.k3
Audio SHA-256: f2d13b12fb4ddc815ea4e2b06c428d9c302f4825f06d30a4b8519927cf53789a
Gemini call: 6.03 s; input tokens 25255; cached tokens 25085; output tokens 1388.

S10-21 · en / synth

Contempt

23.7 s · Complete

Source: vprof_original (CC-BY-4.0) · en/synth · chosen for high existing Contempt score (z=7.07); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

unclear · unclear

Transcript

[unclear]

Audio caption

A mature adult masculine-coded voice delivers an intensely theatrical, grotesque creature-like vocal performance dominated by extreme vocal roughness, heavy throat resonance, and exaggerated cartoonish villainy. Articulation is almost entirely non-lexical or unintelligibly distorted, characterized by aggressive attacks, high muscular tension, and low harmonicity full of rasp, fry, and aperiodic grit. The performance fluctuates wildly between deep guttural growling and piercing, strained screams, punctuated by manic cackles and breathless panting. Pacing is stop-and-go with fragmented phrase units, driven by furious anger, malice, and chaotic pain-like arousal. Background noise is low and studio-isolated, capturing the distorted, pressed timbral extremities cleanly.

Director caption

Channel an unhinged, monstrous goblin or creature archetype with heavy theatrical exaggeration. Start with an aggressive, clipped guttural snap, immediately breaking into a dry, abrasive "[unclear]" that trails into a sharp, spiteful cackle. Drop down into the chest and throat for a prolonged, gravelly subharmonic growl, letting the pitch drag and scrape against vocal fry. Suddenly erupt into a frantic, high-pitched screeching scream, pushing extreme muscular constriction in the throat across several gasping waves of rage. Without pausing, maintain the shrieking energy, letting the sound crack and fray into desperate panting. Settle briefly into a wet, low-pitched menacing growl before finishing with one last piercing, manic cackle-screech that violently exhausts your breath.

Gemini bursts8
Base / Small count0.66 / 0.90
Genuineness (G / B / S)3 / 1.71 / 1.75
Burst blend (G / B / S)7 / 3.76 / 3.95
CPS (Base / Small)7.14 / 7.44
0 s23.7 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.32 s · End: 0.88 s · Cackle laugh_loud
    A sharp, scratchy cackle bursts out in a high raspy register, displaying heavy throat friction and a strained, malicious quality directly following a heavily distorted syllabic utterance.
  • Gemini · Start: 1.75 s · End: 3.74 s · Growl growl
    A sustained, deep guttural growl vibrating with extreme biological roughness and subharmonic rasp, transitioning from a low groan into strained, creaky vocal fry.
  • Gemini · Start: 6.30 s · End: 9.45 s · Scream scream
    A piercing, unhinged creature-like scream that surges across multiple strained pitch spikes and breath catches, blending extreme aggressive anger with physical exertion.
  • Gemini · Start: 9.50 s · End: 12.35 s · Scream scream
    A prolonged, wailing screech filled with harsh vocal-fold tearing and high-arousal strain, pulsating with erratic throat constriction before dissolving into an exhausted wheeze.
  • Gemini · Start: 12.38 s · End: 13.90 s · Panting breath_fast
    Rapid, rough panting with heavy diaphragmatic force and dry pharyngeal turbulence, signaling sudden exhaustion and breathlessness immediately after intense screaming.
  • Gemini · Start: 15.00 s · End: 17.50 s · Growl growl
    A low-pitched, rattling growl that shifts into a strained groaning whine, characterized by wet pharyngeal resonance, extreme vocal fry, and a sinister, malevolent tone.
  • Gemini · Start: 18.05 s · End: 19.35 s · Cackle laugh_loud
    A high, wheezing cackle that breaks sharply through pressed throat constriction, sounding manic and deranged before cutting off abruptly.
  • Gemini · Start: 19.40 s · End: 21.40 s · Scream scream
    A final high-pitched screeching outburst that decays into strained breath and harsh vocal fry, marking the end of the manic vocal sequence.
  • Existing S10 marker · Start: 0.08 s · End: 0.20 s
  • Base proposals: Start: 0.04 s · End: 0.26 s: Surprised Gasp 0.79, Childlike Giggle 0.11, Ahem 0.04; Start: 0.10 s · End: 0.24 s: Ahem 0.72, Surprised Gasp 0.19, Spitting 0.01
  • Small proposals: Start: 0.04 s · End: 0.26 s: Surprised Gasp 0.89, Ahem 0.02, Childlike Giggle 0.02; Start: 0.10 s · End: 0.26 s: Surprised Gasp 0.45, Ahem 0.45, Whispered Mumble 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.005.545.395.43
atckvn_ATCK_reg5.005.034.934.80
emphvn_EMPH_reg5.005.335.615.34
gendvn_GEND_reg5.004.884.684.47
r thrtvn_R_THRT_reg5.003.573.413.35
rangvn_RANG_reg5.005.735.675.70
rougvn_ROUG_reg5.005.385.165.24
s cartvn_S_CART_reg5.005.565.555.38
s dramvn_S_DRAM_reg5.005.715.875.76
stncvn_STNC_reg5.006.146.115.88
tensvn_TENS_reg5.004.574.704.57
agevvn_AGEV_reg4.001.711.751.75
arshvn_ARSH_reg4.003.523.973.61
brgtvn_BRGT_reg4.002.492.342.22
darcvn_DARC_reg4.005.074.914.93
focsvn_FOCS_reg4.004.124.173.99
r chstvn_R_CHST_reg4.002.812.732.64
respvn_RESP_reg4.004.044.024.11
s monovn_S_MONO_reg4.000.100.240.04
s rantvn_S_RANT_reg4.005.925.905.82
voltvn_VOLT_reg4.005.515.485.29
bkgnvn_BKGN_reg3.001.111.171.11
dfluvn_DFLU_reg3.001.711.731.58
fullvn_FULL_reg3.001.371.361.12
metlvn_METL_reg3.004.364.394.23
r maskvn_R_MASK_reg3.002.722.712.61
r oralvn_R_ORAL_reg3.003.073.183.11
rcqlvn_RCQL_reg3.001.331.221.23
s authvn_S_AUTH_reg3.003.273.392.96
tempvn_TEMP_reg3.003.993.993.88
vflxvn_VFLX_reg3.003.663.853.71
chnkvn_CHNK_reg2.003.523.673.53
coglvn_COGL_reg2.000.360.320.36
r mixdvn_R_MIXD_reg2.001.381.611.40
r naslvn_R_NASL_reg2.003.063.013.12
s playvn_S_PLAY_reg2.002.681.932.09
valsvn_VALS_reg2.002.922.532.62
vulnvn_VULN_reg2.00-0.290.140.02
warmvn_WARM_reg2.001.431.351.37
clrtvn_CLRT_reg1.001.531.531.52
esthvn_ESTH_reg1.001.151.000.98
explvn_EXPL_reg1.000.090.050.02
harmvn_HARM_reg1.002.512.462.38
r headvn_R_HEAD_reg1.003.172.842.90
regsvn_REGS_reg1.003.133.173.15
s casuvn_S_CASU_reg1.005.134.784.87
s convvn_S_CONV_reg1.00-0.02-0.44-0.36
s stryvn_S_STRY_reg1.003.423.443.43
smthvn_SMTH_reg1.000.881.060.94
struvn_STRU_reg1.001.331.311.41
valnvn_VALN_reg1.004.004.114.02
s asmrvn_S_ASMR_reg0.000.370.680.55
s formvn_S_FORM_reg0.000.160.200.15
s narrvn_S_NARR_reg0.00-0.05-0.07-0.11
s newsvn_S_NEWS_reg0.00-0.06-0.14-0.07
s techvn_S_TECH_reg0.00-0.64-1.13-0.97
s whisvn_S_WHIS_reg0.001.351.671.74
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.033.09
eiv_extra:Arousal3.433.30
eiv_extra:Authenticity2.832.70
eiv_extra:Background_Noise1.121.22
eiv_extra:Confident_vs._Hesitant1.251.49
eiv_extra:Gender-0.90-0.52
eiv_extra:High-Pitched_vs._Low-Pitched2.221.91
eiv_extra:Monotone_vs._Expressive3.093.05
eiv_extra:Recording_Quality1.851.81
eiv_extra:Serious_vs._Humorous0.990.98
eiv_extra:Soft_vs._Harsh-0.16-0.28
eiv_extra:Submissive_vs._Dominant0.820.68
eiv_extra:Valence-0.93-1.43
eiv_extra:Vulnerable_vs._Emotionally_Detached1.060.99
eiv_extra:Warm_vs._Cold-1.04-0.71
eiv_extra:score_background_quality1.852.05
eiv_extra:score_content_enjoyment4.124.33
eiv_extra:score_overall_quality1.831.60
eiv_extra:score_speech_quality1.501.61
audiobox:CE3.704.31
audiobox:CU5.205.56
audiobox:PC2.442.60
audiobox:PQ6.476.92
dnsmos:SIG_raw2.662.87
dnsmos:BAK_raw1.341.59
dnsmos:OVRL_raw1.541.73
dnsmos:SIG2.602.71
dnsmos:BAK1.621.89
dnsmos:OVRL1.621.80
dnsmos:P808_MOS2.622.50
voiceclap_attribute:Affection0.751.23
voiceclap_attribute:Age3.002.65
voiceclap_attribute:Amusement1.982.04
voiceclap_attribute:Anger1.501.46
voiceclap_attribute:Arousal3.783.88
voiceclap_attribute:Astonishment_Surprise0.700.77
voiceclap_attribute:Authenticity2.782.77
voiceclap_attribute:Awe0.840.99
voiceclap_attribute:Background_Noise0.870.99
voiceclap_attribute:Bitterness0.890.93
voiceclap_attribute:Concentration0.400.19
voiceclap_attribute:Confident_vs._Hesitant1.081.05
voiceclap_attribute:Confusion0.410.47
voiceclap_attribute:Contemplation0.550.46
voiceclap_attribute:Contempt1.031.03
voiceclap_attribute:Contentment0.570.79
voiceclap_attribute:Disappointment1.461.35
voiceclap_attribute:Disgust0.680.61
voiceclap_attribute:Distress2.071.46
voiceclap_attribute:Doubt-0.21-0.05
voiceclap_attribute:Elation2.162.39
voiceclap_attribute:Embarrassment0.450.38
voiceclap_attribute:Emotional_Numbness-0.020.10
voiceclap_attribute:Fatigue_Exhaustion0.400.30
voiceclap_attribute:Fear0.920.91
voiceclap_attribute:Gender-0.87-0.61
voiceclap_attribute:Helplessness0.750.85
voiceclap_attribute:High-Pitched_vs._Low-Pitched2.072.16
voiceclap_attribute:Hope_Enthusiasm_Optimism2.632.59
voiceclap_attribute:Impatience_and_Irritability1.971.77
voiceclap_attribute:Infatuation0.590.50
voiceclap_attribute:Interest1.952.11
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness1.161.02
voiceclap_attribute:Jealousy_&_Envy0.480.70
voiceclap_attribute:Longing0.280.67
voiceclap_attribute:Malevolence_Malice1.681.49
voiceclap_attribute:Monotone_vs._Expressive3.273.74
voiceclap_attribute:Pain0.910.86
voiceclap_attribute:Pleasure_Ecstasy1.641.76
voiceclap_attribute:Pride1.621.54
voiceclap_attribute:Recording_Quality2.021.84
voiceclap_attribute:Relief0.450.61
voiceclap_attribute:Sadness0.930.92
voiceclap_attribute:Serious_vs._Humorous0.921.51
voiceclap_attribute:Sexual_Lust0.801.00
voiceclap_attribute:Shame0.620.35
voiceclap_attribute:Soft_vs._Harsh0.120.35
voiceclap_attribute:Sourness0.640.95
voiceclap_attribute:Submissive_vs._Dominant0.970.95
voiceclap_attribute:Teasing1.111.84
voiceclap_attribute:Thankfulness_Gratitude1.941.65
voiceclap_attribute:Triumph2.251.96
voiceclap_attribute:Valence0.070.58
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.920.71
voiceclap_attribute:Warm_vs._Cold-0.430.45
voiceclap_attribute:duration16.2619.31
voiceclap_attribute:score_background_quality2.512.54
voiceclap_attribute:score_content_enjoyment4.714.91
voiceclap_attribute:score_overall_quality1.861.99
voiceclap_attribute:score_speech_quality1.901.85
voiceclap_attribute:talking_speed7.214.35
Reproducibility and API usage

Dataset UID: k47_age5_bg1__E__Triumph__C__en.c015
Audio SHA-256: 0a6ab457f008eb9a8f59740dca5aaa2713b0e12f87735e63a6986c278c60fc02
Gemini call: 8.21 s; input tokens 25691; cached tokens 25085; output tokens 2082.

S10-22 · en / synth

Disappointment

11.3 s · Complete

Source: vprof_original (CC-BY-4.0) · en/synth · chosen for high existing Disappointment score (z=4.62); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General British

Transcript

I feel so awful, but please know that everything they did this year matters, truly. It just doesn't define how much I love them or whether I'm going to get them a gift.

Audio caption

A feminine-coded, young-adult speaker delivers a sincere, emotionally vulnerable message in a clean, studio-like recording environment with virtually no audible background noise. The vocal quality is warm, resonant, and balanced with mild breathiness that heightens intimacy and emotional permeability. Speaking with a standard General British accent, her delivery is measured and deliberate, characterized by a relaxed tempo, natural pauses, and gentle, caring emphasis on words like 'awful,' 'everything,' and 'truly.' The performance conveys genuine remorse, tenderness, and reassurance, blending slight distress and guilt with deep underlying affection. A prominent sharp inhalation between phrases marks a subtle emotional reset, transitioning smoothly into an earnest, comforting tone that feels entirely organic and deeply lived-in.

Director caption

Deliver the lines with deep, heartfelt vulnerability and an intimate, confessional tone. Begin with a hushed, sorrowful cadence, drawing out the vowel slightly: "I feel so awful,". Pause and take an audible, sharp breath of preparation and emotional containment—a sharp inhale—before leaning in with earnest reassurance: "but please know that everything they did this year matters,". Place a soft, grounded emphasis on "truly." Then, soften the delivery further into an affectionate, conversational tone, keeping pitch excursions modest and phrasing smooth: "It just doesn't define how much I love them or whether I'm going to get them a gift."

Gemini bursts1
Base / Small count0.00 / 0.00
Genuineness (G / B / S)5 / 1.99 / 2.11
Burst blend (G / B / S)8 / 7.12 / 7.62
CPS (Base / Small)15.14 / 15.06
0 s11.3 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 2.25 s · End: 2.85 s · Sharp Inhale gasp
    A sharp, audible intake of breath occurs during the pause between 'awful' and 'but please know', marked by an unvoiced glottal gasp that physically preps the following clause while signaling emotional tension and vulnerability; it seamlessly integrates into the ongoing respiratory rhythm and emotional carriage without sounding spliced.
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
bkgnvn_BKGN_reg4.002.462.472.40
clrtvn_CLRT_reg4.001.221.341.21
emphvn_EMPH_reg4.001.411.851.68
esthvn_ESTH_reg4.002.302.412.31
focsvn_FOCS_reg4.001.151.301.18
harmvn_HARM_reg4.002.151.911.84
r mixdvn_R_MIXD_reg4.001.661.581.61
rcqlvn_RCQL_reg4.002.632.522.58
regsvn_REGS_reg4.002.122.152.07
s convvn_S_CONV_reg4.001.581.351.08
smthvn_SMTH_reg4.001.361.281.19
struvn_STRU_reg4.001.701.681.48
vulnvn_VULN_reg4.004.254.374.40
warmvn_WARM_reg4.002.132.052.09
agevvn_AGEV_reg3.002.812.932.87
arshvn_ARSH_reg3.001.181.161.18
brgtvn_BRGT_reg3.001.831.801.74
darcvn_DARC_reg3.00-0.50-0.23-0.40
fullvn_FULL_reg3.001.391.391.23
r chstvn_R_CHST_reg3.001.041.011.01
r headvn_R_HEAD_reg3.001.902.021.70
r maskvn_R_MASK_reg3.001.361.381.26
r oralvn_R_ORAL_reg3.001.681.541.49
rangvn_RANG_reg3.002.902.992.75
respvn_RESP_reg3.003.593.803.73
s casuvn_S_CASU_reg3.002.992.682.59
s dramvn_S_DRAM_reg3.002.332.852.70
s monovn_S_MONO_reg3.003.583.723.87
stncvn_STNC_reg3.000.170.230.15
tensvn_TENS_reg3.001.411.301.22
valsvn_VALS_reg3.000.751.060.66
vflxvn_VFLX_reg3.000.540.780.73
arouvn_AROU_reg2.001.081.261.27
atckvn_ATCK_reg2.000.090.210.07
chnkvn_CHNK_reg2.001.341.361.15
coglvn_COGL_reg2.003.893.924.01
r thrtvn_R_THRT_reg2.000.690.590.47
s authvn_S_AUTH_reg2.00-0.07-0.17-0.17
s formvn_S_FORM_reg2.000.821.121.16
s narrvn_S_NARR_reg2.001.121.351.26
s stryvn_S_STRY_reg2.001.671.841.68
tempvn_TEMP_reg2.001.121.601.27
valnvn_VALN_reg2.001.091.100.83
voltvn_VOLT_reg2.003.343.383.42
dfluvn_DFLU_reg1.002.882.482.48
gendvn_GEND_reg1.001.261.091.02
metlvn_METL_reg1.000.360.340.26
r naslvn_R_NASL_reg1.001.661.501.07
rougvn_ROUG_reg1.000.891.130.89
s asmrvn_S_ASMR_reg1.001.961.921.66
s whisvn_S_WHIS_reg1.001.701.751.60
explvn_EXPL_reg0.00-0.29-0.35-0.31
s cartvn_S_CART_reg0.001.971.941.98
s newsvn_S_NEWS_reg0.000.450.430.46
s playvn_S_PLAY_reg0.000.840.570.24
s rantvn_S_RANT_reg0.000.540.920.81
s techvn_S_TECH_reg0.00-0.93-0.57-0.88
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.343.23
eiv_extra:Arousal1.571.78
eiv_extra:Authenticity3.313.43
eiv_extra:Background_Noise0.040.01
eiv_extra:Confident_vs._Hesitant1.401.08
eiv_extra:Gender1.481.66
eiv_extra:High-Pitched_vs._Low-Pitched1.251.12
eiv_extra:Monotone_vs._Expressive1.931.75
eiv_extra:Recording_Quality2.893.04
eiv_extra:Serious_vs._Humorous0.600.36
eiv_extra:Soft_vs._Harsh0.800.58
eiv_extra:Submissive_vs._Dominant0.120.25
eiv_extra:Valence-0.67-0.53
eiv_extra:Vulnerable_vs._Emotionally_Detached0.790.65
eiv_extra:Warm_vs._Cold0.240.28
eiv_extra:score_background_quality3.603.67
eiv_extra:score_content_enjoyment4.694.81
eiv_extra:score_overall_quality3.003.06
eiv_extra:score_speech_quality1.861.93
audiobox:CE6.136.00
audiobox:CU7.187.13
audiobox:PC1.441.69
audiobox:PQ7.657.78
dnsmos:SIG_raw4.254.31
dnsmos:BAK_raw4.474.58
dnsmos:OVRL_raw4.014.12
dnsmos:SIG3.693.71
dnsmos:BAK4.174.26
dnsmos:OVRL3.443.51
dnsmos:P808_MOS3.853.80
voiceclap_attribute:Affection1.672.01
voiceclap_attribute:Age3.293.52
voiceclap_attribute:Amusement0.390.13
voiceclap_attribute:Anger0.850.74
voiceclap_attribute:Arousal1.901.74
voiceclap_attribute:Astonishment_Surprise0.580.65
voiceclap_attribute:Authenticity3.443.46
voiceclap_attribute:Awe0.620.82
voiceclap_attribute:Background_Noise0.240.23
voiceclap_attribute:Bitterness0.750.84
voiceclap_attribute:Concentration0.780.62
voiceclap_attribute:Confident_vs._Hesitant1.611.62
voiceclap_attribute:Confusion1.041.08
voiceclap_attribute:Contemplation1.151.41
voiceclap_attribute:Contempt0.470.56
voiceclap_attribute:Contentment0.911.07
voiceclap_attribute:Disappointment1.521.70
voiceclap_attribute:Disgust0.740.53
voiceclap_attribute:Distress1.981.91
voiceclap_attribute:Doubt0.790.80
voiceclap_attribute:Elation0.780.88
voiceclap_attribute:Embarrassment1.051.14
voiceclap_attribute:Emotional_Numbness0.850.91
voiceclap_attribute:Fatigue_Exhaustion0.680.89
voiceclap_attribute:Fear1.050.98
voiceclap_attribute:Gender1.151.51
voiceclap_attribute:Helplessness1.281.48
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.381.36
voiceclap_attribute:Hope_Enthusiasm_Optimism1.261.44
voiceclap_attribute:Impatience_and_Irritability1.231.05
voiceclap_attribute:Infatuation1.341.52
voiceclap_attribute:Interest1.301.21
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.700.75
voiceclap_attribute:Jealousy_&_Envy0.951.00
voiceclap_attribute:Longing1.241.35
voiceclap_attribute:Malevolence_Malice0.780.63
voiceclap_attribute:Monotone_vs._Expressive2.242.20
voiceclap_attribute:Pain0.891.07
voiceclap_attribute:Pleasure_Ecstasy0.820.89
voiceclap_attribute:Pride0.380.58
voiceclap_attribute:Recording_Quality2.672.73
voiceclap_attribute:Relief1.401.75
voiceclap_attribute:Sadness1.681.97
voiceclap_attribute:Serious_vs._Humorous0.690.35
voiceclap_attribute:Sexual_Lust0.710.81
voiceclap_attribute:Shame1.341.53
voiceclap_attribute:Soft_vs._Harsh0.520.71
voiceclap_attribute:Sourness0.780.84
voiceclap_attribute:Submissive_vs._Dominant0.290.33
voiceclap_attribute:Teasing0.480.51
voiceclap_attribute:Thankfulness_Gratitude2.372.09
voiceclap_attribute:Triumph0.560.67
voiceclap_attribute:Valence-0.57-0.87
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.530.52
voiceclap_attribute:Warm_vs._Cold0.310.30
voiceclap_attribute:duration10.0111.64
voiceclap_attribute:score_background_quality3.623.68
voiceclap_attribute:score_content_enjoyment4.664.68
voiceclap_attribute:score_overall_quality2.892.97
voiceclap_attribute:score_speech_quality1.891.90
voiceclap_attribute:talking_speed13.2312.84
Reproducibility and API usage

Dataset UID: mediathek_0073__E__Embarrassment__C__en.c024
Audio SHA-256: afc5f248e72cebf78ddec306561fcb1327d7e6adf773824d9365787ff7774c50
Gemini call: 6.65 s; input tokens 25381; cached tokens 25085; output tokens 1469.

S10-23 · en / synth

Longing

13.8 s · Complete

Source: vprof_original (CC-BY-4.0) · en/synth · chosen for high existing Longing score (z=5.31); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

I still feel that chill sometimes, remembering how my mother hurt herself gathering firewood. The shock of seeing her like that still sends a shiver down my spine.

Audio caption

A solo masculine-coded speaker in the young adult to mature adult age range speaks in General American English with a quiet, breathy, half-whispered delivery. The acoustic profile is characterized by dark to warm low-mid frequencies, noticeable biological vocal fry and roughness, and prominent chest resonance coupled with intimate oral placement. Phonation is restrained and soft, operating with low overall arousal and negative-leaning valence marked by somber distress, fear, and reflective sadness. Phrasing is segmented into deliberate, short breath groups separated by heavy, audible respiratory events, including sharp preparatory inhales and a lingering, distressed exhalation. The performance maintains a reflective, dramatic monologue style reminiscent of an intimate storytelling voiceover, with clean studio acoustics and minimal background interference.

Director caption

Deliver this as an intimate, haunted personal memory, speaking in a breathy, half-voiced baritone register. Start with a quick, audible gasp of breath: "I still feel that chill sometimes," keeping the tempo slow and the tone somber. Take a subtle, tight catch of breath, then continue with soft vocal fry: "remembering how my mother hurt herself gathering firewood." Pause and release a heavy, tired sigh of lingering dread. Gather yourself and deliver the final thought quietly with delicate, vulnerable focus: "The shock of seeing her like that still sends a shiver down my spine."

Gemini bursts3
Base / Small count0.93 / 0.98
Genuineness (G / B / S)4 / 1.42 / 1.44
Burst blend (G / B / S)7 / 5.70 / 5.84
CPS (Base / Small)11.62 / 11.77
0 s13.8 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.05 s · End: 0.45 s · Sharp Inhale gasp
    A sharp, audible intake of breath through the mouth and throat initiates the clip just before the word 'I', establishing a tense, cold, and startled tone.
  • Gemini · Start: 3.42 s · End: 3.75 s · Sharp Inhale gasp
    A quiet, sharp breath intake occurs in the brief pause before 'remembering', marked by slight tension in the pharynx that naturally carries over into the breathy delivery.
  • Gemini · Start: 8.08 s · End: 8.78 s · Exasperated Sigh sigh_neg
    An extended, heavy exhalation of breath with audible friction sits alone in the pause between 'firewood' and 'The shock', conveying lingering distress and weary dread.
  • Existing S10 marker · Start: 8.36 s · End: 8.48 s
  • Base proposals: Start: 8.36 s · End: 8.50 s: Contented Sigh 0.92, Spitting 0.01, Nervous Giggle 0.01
  • Small proposals: Start: 8.36 s · End: 8.52 s: Contented Sigh 0.93, Snicker 0.01, Nervous Giggle 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.384.424.57
s monovn_S_MONO_reg5.003.703.443.51
bkgnvn_BKGN_reg4.002.091.942.11
clrtvn_CLRT_reg4.001.291.251.27
focsvn_FOCS_reg4.001.492.061.99
r chstvn_R_CHST_reg4.002.001.801.86
rcqlvn_RCQL_reg4.002.822.442.63
respvn_RESP_reg4.003.203.523.41
s dramvn_S_DRAM_reg4.003.173.133.21
s narrvn_S_NARR_reg4.001.741.671.79
s stryvn_S_STRY_reg4.002.512.292.44
struvn_STRU_reg4.001.391.301.47
vulnvn_VULN_reg4.004.334.374.37
agevvn_AGEV_reg3.003.063.293.01
arshvn_ARSH_reg3.000.590.930.75
darcvn_DARC_reg3.00-0.43-0.41-0.35
emphvn_EMPH_reg3.001.061.391.48
esthvn_ESTH_reg3.002.442.432.44
fullvn_FULL_reg3.001.691.291.54
r mixdvn_R_MIXD_reg3.000.971.121.17
r oralvn_R_ORAL_reg3.000.720.740.70
r thrtvn_R_THRT_reg3.000.430.160.30
rougvn_ROUG_reg3.001.911.801.98
s asmrvn_S_ASMR_reg3.002.222.202.45
s convvn_S_CONV_reg3.000.260.430.53
smthvn_SMTH_reg3.001.110.921.12
tensvn_TENS_reg3.001.171.231.21
valsvn_VALS_reg3.000.680.540.75
vflxvn_VFLX_reg3.000.180.31-0.04
warmvn_WARM_reg3.003.022.772.90
arouvn_AROU_reg2.001.101.101.07
atckvn_ATCK_reg2.00-0.010.10-0.03
brgtvn_BRGT_reg2.001.531.431.48
chnkvn_CHNK_reg2.001.561.191.39
coglvn_COGL_reg2.002.962.802.94
harmvn_HARM_reg2.001.451.311.33
r headvn_R_HEAD_reg2.000.830.630.70
r maskvn_R_MASK_reg2.000.380.360.33
rangvn_RANG_reg2.001.661.671.70
s casuvn_S_CASU_reg2.002.472.422.41
s whisvn_S_WHIS_reg2.002.913.223.07
stncvn_STNC_reg2.000.940.830.88
tempvn_TEMP_reg2.000.550.500.50
valnvn_VALN_reg2.000.871.030.95
voltvn_VOLT_reg2.003.323.553.59
dfluvn_DFLU_reg1.001.411.691.60
metlvn_METL_reg1.000.740.720.60
r naslvn_R_NASL_reg1.000.18-0.18-0.05
regsvn_REGS_reg1.000.630.630.58
s authvn_S_AUTH_reg1.000.440.400.42
s formvn_S_FORM_reg1.002.001.791.80
explvn_EXPL_reg0.00-0.26-0.23-0.14
s cartvn_S_CART_reg0.002.572.642.26
s newsvn_S_NEWS_reg0.000.420.360.41
s playvn_S_PLAY_reg0.000.08-0.110.15
s rantvn_S_RANT_reg0.000.660.570.51
s techvn_S_TECH_reg0.00-0.97-0.89-0.68
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.663.41
eiv_extra:Arousal1.321.19
eiv_extra:Authenticity3.323.38
eiv_extra:Background_Noise0.320.03
eiv_extra:Confident_vs._Hesitant1.000.96
eiv_extra:Gender0.230.34
eiv_extra:High-Pitched_vs._Low-Pitched1.811.39
eiv_extra:Monotone_vs._Expressive1.971.65
eiv_extra:Recording_Quality2.752.96
eiv_extra:Serious_vs._Humorous0.440.16
eiv_extra:Soft_vs._Harsh0.870.61
eiv_extra:Submissive_vs._Dominant0.130.12
eiv_extra:Valence-0.68-0.37
eiv_extra:Vulnerable_vs._Emotionally_Detached0.820.70
eiv_extra:Warm_vs._Cold0.180.17
eiv_extra:score_background_quality3.653.81
eiv_extra:score_content_enjoyment4.824.93
eiv_extra:score_overall_quality3.013.15
eiv_extra:score_speech_quality1.791.87
audiobox:CE6.486.40
audiobox:CU7.477.28
audiobox:PC1.711.67
audiobox:PQ8.108.00
dnsmos:SIG_raw4.154.32
dnsmos:BAK_raw4.104.47
dnsmos:OVRL_raw3.764.06
dnsmos:SIG3.643.73
dnsmos:BAK3.944.18
dnsmos:OVRL3.273.48
dnsmos:P808_MOS4.094.09
voiceclap_attribute:Affection1.511.68
voiceclap_attribute:Age3.223.51
voiceclap_attribute:Amusement0.350.20
voiceclap_attribute:Anger0.980.81
voiceclap_attribute:Arousal1.981.90
voiceclap_attribute:Astonishment_Surprise0.790.74
voiceclap_attribute:Authenticity3.413.42
voiceclap_attribute:Awe0.791.03
voiceclap_attribute:Background_Noise0.290.34
voiceclap_attribute:Bitterness0.930.92
voiceclap_attribute:Concentration0.760.64
voiceclap_attribute:Confident_vs._Hesitant1.191.14
voiceclap_attribute:Confusion0.900.66
voiceclap_attribute:Contemplation1.341.40
voiceclap_attribute:Contempt0.390.50
voiceclap_attribute:Contentment0.951.07
voiceclap_attribute:Disappointment1.681.59
voiceclap_attribute:Disgust0.570.52
voiceclap_attribute:Distress2.362.13
voiceclap_attribute:Doubt0.620.50
voiceclap_attribute:Elation0.850.81
voiceclap_attribute:Embarrassment0.580.69
voiceclap_attribute:Emotional_Numbness0.780.80
voiceclap_attribute:Fatigue_Exhaustion0.670.79
voiceclap_attribute:Fear1.251.19
voiceclap_attribute:Gender0.520.45
voiceclap_attribute:Helplessness1.481.55
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.751.86
voiceclap_attribute:Hope_Enthusiasm_Optimism1.151.11
voiceclap_attribute:Impatience_and_Irritability1.180.97
voiceclap_attribute:Infatuation1.371.47
voiceclap_attribute:Interest1.361.39
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.550.65
voiceclap_attribute:Jealousy_&_Envy0.840.72
voiceclap_attribute:Longing1.231.22
voiceclap_attribute:Malevolence_Malice1.051.10
voiceclap_attribute:Monotone_vs._Expressive2.262.22
voiceclap_attribute:Pain1.141.22
voiceclap_attribute:Pleasure_Ecstasy0.880.90
voiceclap_attribute:Pride0.610.71
voiceclap_attribute:Recording_Quality2.622.76
voiceclap_attribute:Relief1.371.57
voiceclap_attribute:Sadness1.991.95
voiceclap_attribute:Serious_vs._Humorous0.480.26
voiceclap_attribute:Sexual_Lust0.900.89
voiceclap_attribute:Shame1.191.37
voiceclap_attribute:Soft_vs._Harsh0.450.74
voiceclap_attribute:Sourness0.660.73
voiceclap_attribute:Submissive_vs._Dominant0.480.54
voiceclap_attribute:Teasing0.490.50
voiceclap_attribute:Thankfulness_Gratitude2.032.01
voiceclap_attribute:Triumph0.800.84
voiceclap_attribute:Valence-0.78-0.86
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.880.83
voiceclap_attribute:Warm_vs._Cold0.080.30
voiceclap_attribute:duration12.3413.43
voiceclap_attribute:score_background_quality3.513.57
voiceclap_attribute:score_content_enjoyment4.794.77
voiceclap_attribute:score_overall_quality2.712.87
voiceclap_attribute:score_speech_quality1.861.88
voiceclap_attribute:talking_speed11.1811.81
Reproducibility and API usage

Dataset UID: k562_age4_bg1__X__cold_shiver__en.c042
Audio SHA-256: c18faf2d8649294c226c006846750d2f567d2083aa62c61ba348696cec94c0cc
Gemini call: 6.41 s; input tokens 25445; cached tokens 25085; output tokens 1617.

S10-24 · en / synth

Interest

18.5 s · Complete

Source: dramabox_reint (CC-BY-4.0) · en/synth · chosen for high existing Interest score (z=2.51); existing burst marker absent. This was selection metadata, never sent to Gemini.

Language / accent

English · General American

Transcript

Oh God. What is that? It's it's moving. I I can feel it. The tree, it's humming. It's beautiful. So ancient. I've never seen anything like it. A presence so vast. It's a gift. A sacred glimpse.

Audio caption

A solo masculine-coded, young-adult speaker delivers an intensely intimate, dramatic soliloquy in General American English, shifting from breathless apprehension to reverent awe. Articulation is dominated by a close-mic stage whisper with high unvoiced airflow, exceptionally low harmonicity, and prominent oral and pharyngeal resonance that enhances proximity. The delivery is chopped into short, delicate phrases separated by frequent audible inhalations, hesitations, and a soft, wondering sigh. Starting with a tremulous gasp of astonishment on realizing something supernatural is unfolding, the speaker's vocal tension relaxes as apprehension resolves into profound veneration, describing an ancient humming tree. The recording is pristine, dry, and free of background noise, highlighting the rich dynamic detail of breath and quiet awe.

Director caption

Deliver this entirely in a close-mic, hushed whisper, treating the discovery like a fragile, sacred revelation. Begin by pulling in a sudden, trembling breath of shock: enter right on top of it with hushed intensity, "Oh God. What is that?" Pause briefly as if frozen, then utter with slight stammering disbelief: "It's it's moving." Inhale quickly through parted lips, leaning forward into wonder: "I I can feel it. The tree, it's humming." Let the pitch rise slightly in amazed delight on "It's beautiful." Release a soft, wistful sigh of awe, letting the shoulders drop, then continue with slow, reverent gravity: "So ancient. I've never seen anything like it. A presence so vast." Finish with lingering, breathless quietude, stressing the final words with tender conviction: "It's a gift. A sacred glimpse."

Gemini bursts2
Base / Small count0.94 / 1.00
Genuineness (G / B / S)5 / 1.63 / 1.63
Burst blend (G / B / S)9 / 9.77 / 9.62
CPS (Base / Small)10.89 / 10.86
0 s18.5 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 0.00 s · End: 0.65 s · Surprised Gasp gasp
    A deep, trembling breathy intake preceding the whispered exclamation 'Oh God', marked by wide pharyngeal openness, audible rushing air, and sudden astonished arrest that seamlessly feeds into the initial unvoiced glottal onset of the lexical utterance.
  • Gemini · Start: 9.42 s · End: 10.25 s · Wistful Sigh sigh_pos
    A soft, prolonged, breath-filled exhalation occurring between the phrases 'It's beautiful' and 'So ancient', carrying a warm, awe-struck release of tension with audible turbulent airflow that naturally resets the speaker's breath support for the subsequent reverent reflection.
  • Base proposals: Start: 9.96 s · End: 10.46 s: Contented Sigh 0.91, Spitting 0.01, Nervous Giggle 0.01
  • Small proposals: Start: 9.96 s · End: 10.48 s: Contented Sigh 0.93, Spitting 0.01, Nervous Giggle 0.00
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
gendvn_GEND_reg5.004.745.194.94
rcqlvn_RCQL_reg5.001.811.501.73
respvn_RESP_reg5.003.473.963.54
s dramvn_S_DRAM_reg5.002.792.732.73
s monovn_S_MONO_reg5.003.102.702.93
s whisvn_S_WHIS_reg5.003.442.793.12
valsvn_VALS_reg5.001.221.411.39
vulnvn_VULN_reg5.003.993.893.66
bkgnvn_BKGN_reg4.001.281.661.44
brgtvn_BRGT_reg4.001.471.711.50
clrtvn_CLRT_reg4.001.081.181.14
emphvn_EMPH_reg4.001.911.881.72
esthvn_ESTH_reg4.001.531.871.77
focsvn_FOCS_reg4.002.031.971.97
r mixdvn_R_MIXD_reg4.001.531.851.65
r oralvn_R_ORAL_reg4.000.991.071.01
rangvn_RANG_reg4.001.911.741.78
s asmrvn_S_ASMR_reg4.002.372.242.37
s stryvn_S_STRY_reg4.001.501.071.24
valnvn_VALN_reg4.000.920.650.84
warmvn_WARM_reg4.002.101.801.69
agevvn_AGEV_reg3.002.041.581.81
arouvn_AROU_reg3.001.891.491.57
coglvn_COGL_reg3.004.124.214.10
darcvn_DARC_reg3.000.260.980.58
fullvn_FULL_reg3.001.291.751.49
r chstvn_R_CHST_reg3.001.281.311.07
r headvn_R_HEAD_reg3.000.360.560.56
r maskvn_R_MASK_reg3.000.630.430.41
r thrtvn_R_THRT_reg3.000.040.140.07
s casuvn_S_CASU_reg3.003.473.533.54
struvn_STRU_reg3.001.191.021.07
vflxvn_VFLX_reg3.00-0.84-0.91-0.99
voltvn_VOLT_reg3.002.772.962.78
arshvn_ARSH_reg2.001.391.401.46
dfluvn_DFLU_reg2.003.694.153.97
regsvn_REGS_reg2.000.970.860.90
s convvn_S_CONV_reg2.001.642.121.71
s narrvn_S_NARR_reg2.001.130.570.81
smthvn_SMTH_reg2.000.810.740.67
tempvn_TEMP_reg2.001.131.271.11
tensvn_TENS_reg2.002.122.221.95
atckvn_ATCK_reg1.000.430.160.28
chnkvn_CHNK_reg1.000.711.021.06
harmvn_HARM_reg1.001.431.691.68
metlvn_METL_reg1.001.011.080.95
r naslvn_R_NASL_reg1.00-0.79-0.38-0.38
rougvn_ROUG_reg1.000.940.700.58
stncvn_STNC_reg1.001.551.561.58
explvn_EXPL_reg0.00-0.070.08-0.05
s authvn_S_AUTH_reg0.000.810.730.68
s cartvn_S_CART_reg0.001.851.971.76
s formvn_S_FORM_reg0.001.360.901.09
s newsvn_S_NEWS_reg0.000.06-0.000.08
s playvn_S_PLAY_reg0.00-0.710.30-0.14
s rantvn_S_RANT_reg0.000.260.22-0.06
s techvn_S_TECH_reg0.00-0.130.260.12
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age3.313.16
eiv_extra:Arousal2.161.93
eiv_extra:Authenticity3.333.45
eiv_extra:Background_Noise0.300.20
eiv_extra:Confident_vs._Hesitant0.950.85
eiv_extra:Gender-0.16-0.30
eiv_extra:High-Pitched_vs._Low-Pitched1.511.30
eiv_extra:Monotone_vs._Expressive1.991.86
eiv_extra:Recording_Quality2.923.07
eiv_extra:Serious_vs._Humorous0.750.40
eiv_extra:Soft_vs._Harsh0.640.49
eiv_extra:Submissive_vs._Dominant0.370.26
eiv_extra:Valence1.511.10
eiv_extra:Vulnerable_vs._Emotionally_Detached1.090.97
eiv_extra:Warm_vs._Cold0.650.39
eiv_extra:score_background_quality3.473.65
eiv_extra:score_content_enjoyment4.814.82
eiv_extra:score_overall_quality2.832.88
eiv_extra:score_speech_quality1.711.84
audiobox:CE6.496.21
audiobox:CU7.427.21
audiobox:PC1.951.64
audiobox:PQ7.937.94
dnsmos:SIG_raw3.813.90
dnsmos:BAK_raw4.104.37
dnsmos:OVRL_raw3.573.75
dnsmos:SIG3.423.47
dnsmos:BAK3.974.13
dnsmos:OVRL3.163.26
dnsmos:P808_MOS3.763.66
voiceclap_attribute:Affection0.690.63
voiceclap_attribute:Age2.903.36
voiceclap_attribute:Amusement0.310.04
voiceclap_attribute:Anger1.411.24
voiceclap_attribute:Arousal2.232.28
voiceclap_attribute:Astonishment_Surprise1.131.43
voiceclap_attribute:Authenticity3.193.19
voiceclap_attribute:Awe0.281.12
voiceclap_attribute:Background_Noise0.380.29
voiceclap_attribute:Bitterness0.870.80
voiceclap_attribute:Concentration0.981.05
voiceclap_attribute:Confident_vs._Hesitant1.411.22
voiceclap_attribute:Confusion0.951.00
voiceclap_attribute:Contemplation0.981.21
voiceclap_attribute:Contempt0.440.67
voiceclap_attribute:Contentment0.270.31
voiceclap_attribute:Disappointment1.381.48
voiceclap_attribute:Disgust0.880.72
voiceclap_attribute:Distress2.121.69
voiceclap_attribute:Doubt0.980.94
voiceclap_attribute:Elation0.540.80
voiceclap_attribute:Embarrassment0.360.46
voiceclap_attribute:Emotional_Numbness0.690.72
voiceclap_attribute:Fatigue_Exhaustion0.370.67
voiceclap_attribute:Fear1.421.27
voiceclap_attribute:Gender-0.090.17
voiceclap_attribute:Helplessness1.151.46
voiceclap_attribute:High-Pitched_vs._Low-Pitched1.701.66
voiceclap_attribute:Hope_Enthusiasm_Optimism0.991.20
voiceclap_attribute:Impatience_and_Irritability1.711.65
voiceclap_attribute:Infatuation0.690.72
voiceclap_attribute:Interest1.461.59
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.400.47
voiceclap_attribute:Jealousy_&_Envy0.800.63
voiceclap_attribute:Longing0.670.73
voiceclap_attribute:Malevolence_Malice1.020.88
voiceclap_attribute:Monotone_vs._Expressive2.121.97
voiceclap_attribute:Pain0.900.93
voiceclap_attribute:Pleasure_Ecstasy0.520.56
voiceclap_attribute:Pride0.470.68
voiceclap_attribute:Recording_Quality2.382.63
voiceclap_attribute:Relief1.201.30
voiceclap_attribute:Sadness1.341.44
voiceclap_attribute:Serious_vs._Humorous0.700.22
voiceclap_attribute:Sexual_Lust0.520.39
voiceclap_attribute:Shame0.880.86
voiceclap_attribute:Soft_vs._Harsh0.150.35
voiceclap_attribute:Sourness0.650.74
voiceclap_attribute:Submissive_vs._Dominant0.360.40
voiceclap_attribute:Teasing0.540.36
voiceclap_attribute:Thankfulness_Gratitude1.470.99
voiceclap_attribute:Triumph0.831.04
voiceclap_attribute:Valence-0.85-1.10
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached1.281.06
voiceclap_attribute:Warm_vs._Cold0.110.21
voiceclap_attribute:duration15.0219.85
voiceclap_attribute:score_background_quality3.483.33
voiceclap_attribute:score_content_enjoyment4.784.75
voiceclap_attribute:score_overall_quality2.632.51
voiceclap_attribute:score_speech_quality1.851.86
voiceclap_attribute:talking_speed12.0311.37
Reproducibility and API usage

Dataset UID: 000_00000858_5181ba31-5f5a-403a-9b31-b73cdac7b0f3.s0.top2
Audio SHA-256: d36fb135a0c00019086b3e41709a71992627d7733cd25c0727b6bcf9fdd4731f
Gemini call: 7.12 s; input tokens 25561; cached tokens 25085; output tokens 1657.

S10-25 · en / synth

Triumph

13.4 s · Complete

Source: vprof_original (CC-BY-4.0) · en/synth · chosen for high existing Triumph score (z=7.42); existing burst marker present. This was selection metadata, never sent to Gemini.

Language / accent

English · General American (stylized)

Transcript

S1: We finally cracked the security protocols! That is worth celebrating, because we rewrite the code! S2: Look, take the elevator, the penthouse is a whole new level.

Audio caption

A dynamic exchange between two heavily stylized character voices in General American English, set against a quiet background. The dominant first speaker exhibits a high-energy, youthful, masculine-leaning cartoon presentation with elevated brightness, pronounced oral and mask resonance, and significant theatrical tension. This speaker begins with intense triumph, delivering lines at a brisk, punchy tempo before culminating in an extended, high-pitched celebratory scream on 'code.' Immediately following, a second speaker enters with a radically altered vocal profile: a much lower, heavily gravelly, raspy, throat-centered register with low arousal and exhausted, casual delivery advising to take the elevator. While the recording itself is clean with virtually no ambient interference, the performative cartoon style and abrupt transition between the over-the-top celebratory scream and the deadpan secondary voice result in a lower genuineness score and moderately spliced burst blend.

Director caption

Deliver the first section as an eccentric, manic cartoon character riding a high wave of triumph: punch the phrase "We finally cracked the security protocols!" with sharp, elevated pitch and high mask resonance. Keep the energy climbing through "That is worth celebrating, because we rewrite the..." before exploding on "code!" into a prolonged, ecstatic "Scream" that trails off into an extended, raspy high-register cry. Immediately cut that manic celebration dead and transition to a secondary, weary character voice: drop into a low, gravelly, throat-fried rumble, speaking with relaxed, deadpan cadence: "Look, take the elevator, the penthouse is a whole new level."

Gemini bursts1
Base / Small count0.99 / 1.21
Genuineness (G / B / S)2 / 1.80 / 1.81
Burst blend (G / B / S)4 / 4.49 / 4.44
CPS (Base / Small)9.92 / 11.01
0 s13.4 s
Event captions and top-3 Whisper classes
  • Gemini · Start: 6.36 s · End: 8.08 s · Scream scream
    A prolonged, high-pitched, triumphant vocalic shout and sustained cheer extends directly off the word 'code,' peaking in intensity with bright head-mask resonance and slight rough rasp; it functions as a performative celebratory shriek rather than acute terror, blending directly out of lexical speech before cutting off abruptly as the second speaker enters.
  • Existing S10 marker · Start: 8.88 s · End: 9.22 s
  • Base proposals: Start: 8.88 s · End: 9.28 s: Ahem 0.78, Surprised Gasp 0.04, Exhausted Groan 0.02
  • Small proposals: Start: 8.86 s · End: 9.32 s: Ahem 0.90, Chuckle 0.01, Cackle 0.01
All 40 EmoNet emotions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
affectionvn_AFFECTION_reg————
amusementvn_AMUSEMENT_reg————
angervn_ANGER_reg————
astonishment surprisevn_ASTONISHMENT_SURPRISE_reg————
awevn_AWE_reg————
bitternessvn_BITTERNESS_reg————
concentrationvn_CONCENTRATION_reg————
confusionvn_CONFUSION_reg————
contemplationvn_CONTEMPLATION_reg————
contemptvn_CONTEMPT_reg————
contentmentvn_CONTENTMENT_reg————
disappointmentvn_DISAPPOINTMENT_reg————
disgustvn_DISGUST_reg————
distressvn_DISTRESS_reg————
doubtvn_DOUBT_reg————
elationvn_ELATION_reg————
embarrassmentvn_EMBARRASSMENT_reg————
emotional numbnessvn_EMOTIONAL_NUMBNESS_reg————
fatigue exhaustionvn_FATIGUE_EXHAUSTION_reg————
fearvn_FEAR_reg————
gratitudevn_GRATITUDE_reg————
helplessnessvn_HELPLESSNESS_reg————
hope optimismvn_HOPE_OPTIMISM_reg————
impatience irritabilityvn_IMPATIENCE_IRRITABILITY_reg————
infatuationvn_INFATUATION_reg————
interestvn_INTEREST_reg————
intoxication altered statesvn_INTOXICATION_ALTERED_STATES_reg————
jealousy envyvn_JEALOUSY_ENVY_reg————
longingvn_LONGING_reg————
malevolence malicevn_MALEVOLENCE_MALICE_reg————
painvn_PAIN_reg————
pleasure ecstasyvn_PLEASURE_ECSTASY_reg————
pridevn_PRIDE_reg————
reliefvn_RELIEF_reg————
sadnessvn_SADNESS_reg————
sexual lustvn_SEXUAL_LUST_reg————
shamevn_SHAME_reg————
sournessvn_SOURNESS_reg————
teasingvn_TEASING_reg————
triumphvn_TRIUMPH_reg————
All 57 VoiceNet dimensions: raw scores
DimensionGeminiExisting S10 teacherWhisper Base S10Whisper Small S10
arouvn_AROU_reg5.004.965.295.18
atckvn_ATCK_reg5.004.163.883.99
emphvn_EMPH_reg5.005.015.105.15
rangvn_RANG_reg5.005.575.675.42
s cartvn_S_CART_reg5.004.925.044.65
s dramvn_S_DRAM_reg5.006.186.085.99
stncvn_STNC_reg5.005.195.315.31
bkgnvn_BKGN_reg4.001.601.501.52
brgtvn_BRGT_reg4.002.142.242.37
clrtvn_CLRT_reg4.001.111.361.52
focsvn_FOCS_reg4.003.834.584.46
gendvn_GEND_reg4.005.174.834.63
r maskvn_R_MASK_reg4.003.133.423.10
r oralvn_R_ORAL_reg4.003.343.573.36
r thrtvn_R_THRT_reg4.003.203.172.92
rcqlvn_RCQL_reg4.001.661.581.75
rougvn_ROUG_reg4.004.724.724.70
s playvn_S_PLAY_reg4.003.342.662.58
tempvn_TEMP_reg4.003.713.663.66
tensvn_TENS_reg4.004.103.943.87
valnvn_VALN_reg4.004.795.595.35
voltvn_VOLT_reg4.005.004.534.37
agevvn_AGEV_reg3.001.922.242.30
chnkvn_CHNK_reg3.003.633.573.36
esthvn_ESTH_reg3.001.771.952.24
fullvn_FULL_reg3.000.991.051.21
harmvn_HARM_reg3.002.902.833.08
metlvn_METL_reg3.004.144.154.06
r chstvn_R_CHST_reg3.002.823.003.09
r headvn_R_HEAD_reg3.003.413.713.53
r mixdvn_R_MIXD_reg3.002.222.322.61
r naslvn_R_NASL_reg3.003.293.503.43
regsvn_REGS_reg3.002.862.592.78
s authvn_S_AUTH_reg3.002.322.622.59
s casuvn_S_CASU_reg3.004.724.224.16
s convvn_S_CONV_reg3.00-0.63-0.93-0.69
s rantvn_S_RANT_reg3.004.684.964.48
smthvn_SMTH_reg3.001.411.751.88
struvn_STRU_reg3.001.501.661.87
respvn_RESP_reg2.003.543.303.04
s stryvn_S_STRY_reg2.004.434.624.42
valsvn_VALS_reg2.003.053.183.09
warmvn_WARM_reg2.001.431.421.57
arshvn_ARSH_reg1.004.174.614.45
coglvn_COGL_reg1.000.320.420.44
darcvn_DARC_reg1.005.275.255.08
dfluvn_DFLU_reg1.001.090.730.63
s formvn_S_FORM_reg1.00-0.110.120.24
s monovn_S_MONO_reg1.000.560.960.85
s narrvn_S_NARR_reg1.00-0.110.080.11
s techvn_S_TECH_reg1.000.08-0.40-0.38
vflxvn_VFLX_reg1.003.823.863.88
vulnvn_VULN_reg1.001.581.161.36
explvn_EXPL_reg0.000.190.030.10
s asmrvn_S_ASMR_reg0.000.310.500.36
s newsvn_S_NEWS_reg0.000.18-0.010.28
s whisvn_S_WHIS_reg0.002.222.242.55
Other trained outputs: AudioBox, DNSMOS, quality, VoiceCLAP attributes
ScoreBase S10Small S10
eiv_extra:Age2.952.81
eiv_extra:Arousal3.193.48
eiv_extra:Authenticity2.752.81
eiv_extra:Background_Noise1.031.07
eiv_extra:Confident_vs._Hesitant1.191.26
eiv_extra:Gender-0.87-0.55
eiv_extra:High-Pitched_vs._Low-Pitched2.001.93
eiv_extra:Monotone_vs._Expressive3.263.46
eiv_extra:Recording_Quality2.062.26
eiv_extra:Serious_vs._Humorous1.331.07
eiv_extra:Soft_vs._Harsh0.29-0.04
eiv_extra:Submissive_vs._Dominant1.331.18
eiv_extra:Valence1.581.35
eiv_extra:Vulnerable_vs._Emotionally_Detached1.191.13
eiv_extra:Warm_vs._Cold0.430.29
eiv_extra:score_background_quality2.081.89
eiv_extra:score_content_enjoyment4.534.76
eiv_extra:score_overall_quality1.851.65
eiv_extra:score_speech_quality1.641.58
audiobox:CE4.775.09
audiobox:CU5.095.62
audiobox:PC3.944.13
audiobox:PQ6.116.03
dnsmos:SIG_raw3.443.62
dnsmos:BAK_raw1.841.72
dnsmos:OVRL_raw2.092.10
dnsmos:SIG3.183.29
dnsmos:BAK2.101.99
dnsmos:OVRL2.072.09
dnsmos:P808_MOS2.712.52
voiceclap_attribute:Affection1.201.32
voiceclap_attribute:Age2.952.94
voiceclap_attribute:Amusement1.011.03
voiceclap_attribute:Anger0.951.25
voiceclap_attribute:Arousal3.283.06
voiceclap_attribute:Astonishment_Surprise0.510.53
voiceclap_attribute:Authenticity2.872.91
voiceclap_attribute:Awe0.820.97
voiceclap_attribute:Background_Noise0.901.01
voiceclap_attribute:Bitterness0.650.66
voiceclap_attribute:Concentration0.740.68
voiceclap_attribute:Confident_vs._Hesitant1.061.13
voiceclap_attribute:Confusion0.380.43
voiceclap_attribute:Contemplation0.720.73
voiceclap_attribute:Contempt0.600.64
voiceclap_attribute:Contentment0.981.22
voiceclap_attribute:Disappointment1.201.01
voiceclap_attribute:Disgust0.420.47
voiceclap_attribute:Distress1.461.21
voiceclap_attribute:Doubt0.060.04
voiceclap_attribute:Elation2.162.26
voiceclap_attribute:Embarrassment0.140.27
voiceclap_attribute:Emotional_Numbness0.380.51
voiceclap_attribute:Fatigue_Exhaustion0.330.31
voiceclap_attribute:Fear0.820.68
voiceclap_attribute:Gender-0.67-0.49
voiceclap_attribute:Helplessness0.770.75
voiceclap_attribute:High-Pitched_vs._Low-Pitched2.042.12
voiceclap_attribute:Hope_Enthusiasm_Optimism2.943.04
voiceclap_attribute:Impatience_and_Irritability1.001.33
voiceclap_attribute:Infatuation0.991.04
voiceclap_attribute:Interest2.352.38
voiceclap_attribute:Intoxication_Altered_States_of_Consciousness0.900.87
voiceclap_attribute:Jealousy_&_Envy0.540.52
voiceclap_attribute:Longing0.720.86
voiceclap_attribute:Malevolence_Malice1.091.30
voiceclap_attribute:Monotone_vs._Expressive3.543.52
voiceclap_attribute:Pain0.650.69
voiceclap_attribute:Pleasure_Ecstasy1.441.59
voiceclap_attribute:Pride1.681.42
voiceclap_attribute:Recording_Quality2.322.29
voiceclap_attribute:Relief0.740.59
voiceclap_attribute:Sadness0.980.91
voiceclap_attribute:Serious_vs._Humorous0.841.06
voiceclap_attribute:Sexual_Lust0.961.28
voiceclap_attribute:Shame0.650.53
voiceclap_attribute:Soft_vs._Harsh0.320.37
voiceclap_attribute:Sourness0.410.50
voiceclap_attribute:Submissive_vs._Dominant1.171.11
voiceclap_attribute:Teasing0.781.06
voiceclap_attribute:Thankfulness_Gratitude2.071.99
voiceclap_attribute:Triumph2.041.79
voiceclap_attribute:Valence1.561.32
voiceclap_attribute:Vulnerable_vs._Emotionally_Detached0.920.91
voiceclap_attribute:Warm_vs._Cold0.540.70
voiceclap_attribute:duration13.4713.06
voiceclap_attribute:score_background_quality2.492.59
voiceclap_attribute:score_content_enjoyment4.824.83
voiceclap_attribute:score_overall_quality2.052.12
voiceclap_attribute:score_speech_quality1.851.85
voiceclap_attribute:talking_speed5.826.18
Reproducibility and API usage

Dataset UID: mediathek_0184__E__Triumph__A__en.c029
Audio SHA-256: fe3661f0670d1dbd98ef0f7e3f281fecda54d2f8f6806073e1c4da09a89af87e
Gemini call: 6.49 s; input tokens 25433; cached tokens 25085; output tokens 1506.