{"id": "en-00159", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 4, "note": "Tagged as 'very having a crush' which is a misleading label for protective distress."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Uncertainty fits reasonably well, but tone is urgent whisper."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as detachment, but it sounds tense and fearful rather than numb."}, {"segment_id": "segment-004", "emotion_fit": 1, "delivery_fit": 3, "note": "Schadenfreude is completely incorrect here; the line is protective and desperate."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Extremely short chunk; detachment tag does not fit."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "Whispered and tense, not emotionally detached."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Tense whisper, not detached."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as burnout; speaker is panicking and planning an escape."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Despairing defeat rather than general burnout."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Terror/fear fits the desperate pleading."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Terror fits well."}, {"segment_id": "segment-012", "emotion_fit": 2, "delivery_fit": 3, "note": "Saudade does not fit the urgent pleading context."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 3, "note": "Desperate plea, not nostalgic longing (saudade)."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Soothing, gentle reassurance fits well."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Comforting whisper fits well."}, {"segment_id": "segment-016", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as infatuation; it is protective soothing."}, {"segment_id": "segment-017", "emotion_fit": 1, "delivery_fit": 3, "note": "Boredom is entirely incorrect; it is a heartfelt whispered promise."}], "audible_events": [{"start_s": 0.05, "end_s": 1.1, "type": "sigh"}, {"start_s": 5.4, "end_s": 6.0, "type": "gasp"}, {"start_s": 8.2, "end_s": 8.9, "type": "sigh"}, {"start_s": 10.7, "end_s": 11.2, "type": "gasp"}, {"start_s": 12.8, "end_s": 13.8, "type": "sigh"}, {"start_s": 14.8, "end_s": 15.6, "type": "sigh"}, {"start_s": 16.3, "end_s": 16.8, "type": "gasp"}, {"start_s": 18.2, "end_s": 18.8, "type": "sigh"}], "overall_note": "The global acoustic description accurately captures the close-mic ASMR-like whispered performance. However, segment-level emotion tags suffer from several bizarre choices (such as schadenfreude, burnout, saudade, and boredom) for what is clearly a frightened, urgent, protective monologue. Furthermore, several burst events have heavy overlapping timestamps with speech or each other."}, "usage": {"promptTokenCount": 7753, "candidatesTokenCount": 1252, "totalTokenCount": 9005, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 704}, {"modality": "TEXT", "tokenCount": 7049}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01050975, "model_version": "gemini-3.8-flash", "response_id": "nGrLav7EHtmpvdIPjbCkqQ0", "weighted_score": 3.1, "annotation_sha256": "69c7c2c0e149e3209d1a87e83d147865756adaf272337a88ca28c5794b0fda15", "audio_sha256": "afae5a11d9c13d5e2f1580844e550b76b527a5aaccf65468c5cdf6a288a9749b", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-01167", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 2, "event_coverage": 3, "transcript_fidelity": 3, "speech_timing_fit": 3, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone is moderately playful, split sentence is awkward."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Labels are moderately aligned with the conversational delivery."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Shock label slightly overstates mild engagement."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Isolated word marked with shock is excessive."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Suspicion and tempo descriptions are partially supported."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Awkwardness label moderately captures the narrative tone."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Sourness is slightly exaggerated for the emphatic finish."}], "audible_events": [{"start_s": 5.65, "end_s": 6.05, "type": "snicker"}, {"start_s": 7.7, "end_s": 8.1, "type": "snicker"}, {"start_s": 12.1, "end_s": 12.5, "type": "sigh"}], "overall_note": "Burst events are excessively duplicated with overlapping windows for single events."}, "usage": {"promptTokenCount": 4574, "candidatesTokenCount": 586, "totalTokenCount": 5160, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 394}, {"modality": "TEXT", "tokenCount": 4180}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.005628, "model_version": "gemini-3.8-flash", "response_id": "nGrLasGeJ4b1kdUP56CwuA0", "weighted_score": 2.85, "annotation_sha256": "f0700b9a16d21ef5f8db70eb7708b6dca17b40150306b8add8451d50ca00da02", "audio_sha256": "ee42cc761e029db86d5a2092eefe1643fdea3819eab04e1e40a88e2beee05a9d", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-01199", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 4, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Exhaled, muttered delivery is well captured, but 'solace' doesn't quite fit the weary sigh."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Slow, quiet, lethargic whisper style matches well."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathless question fits the lethargic tone."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 4, "note": "The tone is tired and detached; labeling it as sexual lust is inaccurate."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 4, "note": "Again, lust is an inaccurate emotion tag here; the delivery is exhausted and observational."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 4, "note": "Mattered has a resigned tone rather than lust."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Detached, flat, intimate tone matches well."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Apathy and thin intimate voice suit the delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 4, "note": "Contains multiple overlapping nonverbal events and a quiet chuckle/sigh before speaking; 'sympathy' is slightly off."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet, breathy, tired delivery accurately marked."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, exhausted tone fits."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, tired delivery fits the weariness description."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Weary, hushed phrasing matches well."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Exhausted half-whisper matches well."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Flat, numb, quiet concluding phrase matches indifference/asmr."}], "audible_events": [{"start_s": 0.04, "end_s": 0.85, "type": "inhalation"}, {"start_s": 1.25, "end_s": 2.12, "type": "sigh"}, {"start_s": 6.55, "end_s": 7.05, "type": "gasp"}, {"start_s": 12.4, "end_s": 13.5, "type": "snicker"}, {"start_s": 17.7, "end_s": 19.5, "type": "sigh"}, {"start_s": 21.45, "end_s": 22.15, "type": "sigh"}, {"start_s": 28.7, "end_s": 29.25, "type": "sigh"}], "overall_note": "The global description is strong, but several segments are inappropriately tagged with 'lust'. Additionally, the burst events feature heavily redundant overlapping duplicates (e.g. at 12-13.5s and 17.6-20.2s)."}, "usage": {"promptTokenCount": 7815, "candidatesTokenCount": 1151, "totalTokenCount": 8966, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 832}, {"modality": "TEXT", "tokenCount": 6983}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0101775, "model_version": "gemini-3.8-flash", "response_id": "nGrLap6DJ8nBvdIPrZyNqAo", "weighted_score": 3.45, "annotation_sha256": "6d444624b5d320929983e8114560ec942a2b565325c8bca73179699f0e969793", "audio_sha256": "11c1c1ac02f63497735cc579d544a670bd583f89e7d23b1fff8508f69317fab5", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-01608", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 4, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 4, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Accurately identifies the whispered, vulnerable opening."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Good fit for the shaky whispered delivery."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Well described breathy tone and longing."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Appropriate description of breathy infatuation."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Delivery matches the trailing off whisper."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Captures the emotional vulnerability accurately."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Fits the breathy pause and continuation."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Well characterized breathy delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Tagged as mumbled/scattered, but it is clear whispered speech with sorrowful tone."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Tension and bitter disappointment are audible."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Short final word maintains the tense emotion."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Wistful, hurt, and vulnerable tone is accurately identified."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet fading question matches the wistful tone."}], "audible_events": [{"start_s": 1.95, "end_s": 2.85, "type": "sigh"}, {"start_s": 3.75, "end_s": 4.25, "type": "gasp"}, {"start_s": 7.3, "end_s": 8.7, "type": "sigh"}, {"start_s": 10.5, "end_s": 11.1, "type": "gasp"}, {"start_s": 12.0, "end_s": 12.45, "type": "inhalation"}, {"start_s": 13.9, "end_s": 14.8, "type": "sigh"}, {"start_s": 21.3, "end_s": 22.45, "type": "sigh"}], "overall_note": "Strong overall description of vocal quality and emotional arc. However, some nonverbal burst event boundaries overlap significantly (e.g. EVENT_0003 and EVENT_0004 cover the same exhalation after 'me'), and EVENT_0000 placed an intake right over the spoken word 'God'."}, "usage": {"promptTokenCount": 6705, "candidatesTokenCount": 1021, "totalTokenCount": 7726, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 667}, {"modality": "TEXT", "tokenCount": 6038}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0088575, "model_version": "gemini-3.8-flash", "response_id": "nGrLarHSHuK3nsEP2MnlyAw", "weighted_score": 3.75, "annotation_sha256": "ecf7e7fc801e6854121f9b6cb39e0243033e5f23868393cbd974ec6be68f7050", "audio_sha256": "58303d3794cc0ec1a99fc9dbdb760f43d0a3eb6e6056c1ca1950b092a5ba0f65", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-01865", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 3, "speech_timing_fit": 3, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Whispered command; 'detachment' does not fit the intimate tone."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Intimate whisper rather than emotional detachment."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 3, "note": "Low sensual whispered delivery, fits lust/intimacy reasonably well."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 3, "note": "Soft whispered direction, intimate."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "'Very liberation' overinterprets a simple quiet affirmation."}, {"segment_id": "segment-006", "emotion_fit": 1, "delivery_fit": 2, "note": "The phrase ends around 10.0s, but the segment timeline is stretched to 11.46s encompassing pauses and breaths. 'Insensitivity' contradicts the affectionate whispered intimacy."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 2, "note": "Intimate praise, not 'numbness' or 'dissociated'."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 4, "note": "Warm whispered praise; 'butterflies in the stomach' is slightly exaggerated."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Attention shift rather than 'shyness'."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Gentle call, not embarrassed or shy."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 2, "note": "Transcript error: speaker says 'look at me for a second', not 'looking at me for real a second'."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Attentive, checking in; fits gentle caring tone."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 2, "note": "Speech is just 'Yes?' around 25.3s to 25.7s; segment spans breath intervals. 'Existential void' is inappropriate."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 3, "note": "Quiet check-in rather than genuine 'distrust'."}, {"segment_id": "segment-015", "emotion_fit": 2, "delivery_fit": 3, "note": "Quiet consent/acknowledgment, not indifference."}, {"segment_id": "segment-016", "emotion_fit": 2, "delivery_fit": 3, "note": "Transcript error: speaker says 'chin up', not 'shin up'. 'Emotional blunting' does not match."}, {"segment_id": "segment-017", "emotion_fit": 2, "delivery_fit": 3, "note": "Tender guidance, not 'indifference'."}, {"segment_id": "segment-018", "emotion_fit": 4, "delivery_fit": 4, "note": "Affectionate/caring fits the intimate whisper well."}], "audible_events": [{"start_s": 10.45, "end_s": 11.45, "type": "breath"}, {"start_s": 12.02, "end_s": 12.72, "type": "breath"}, {"start_s": 17.2, "end_s": 17.75, "type": "breath"}, {"start_s": 24.5, "end_s": 25.3, "type": "breath"}], "overall_note": "A slow intimate whisper performance. Several transcript errors ('shin up' for 'chin up', 'looking at me for real a second' for 'look at me for a second'). Several segments have duplicative, heavily overlapping burst event intervals (e.g. around 10-11s and 24-25s), and local emotion tags repeatedly default to 'emotional numbness/detachment/indifference' which conflicts with the intimate, sensual context."}, "usage": {"promptTokenCount": 8106, "candidatesTokenCount": 1291, "totalTokenCount": 9397, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 917}, {"modality": "TEXT", "tokenCount": 7189}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01092075, "model_version": "gemini-3.8-flash", "response_id": "o2rLavDLFN60kdUP7JiRKQ", "weighted_score": 3.2, "annotation_sha256": "efa9e5125a72a4f03f764d269190b95aa5d89202da14e9c61452be817ba088b7", "audio_sha256": "f78fce3b82b8101a3ce892e988e2c03b594f1110489f7bd31b3a8a475b03a9ee", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-02220", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged with 'carnal desire' which is completely inaccurate for this somber, grief-stricken whisper."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone is subdued and whispered; 'explicit' tag is unwarranted."}, {"segment_id": "segment-003", "emotion_fit": 1, "delivery_fit": 4, "note": "Again incorrectly labeled with 'carnal desire'."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Disappointment and whispered style match the audible bitter delivery."}, {"segment_id": "segment-005", "emotion_fit": 1, "delivery_fit": 3, "note": "Erroneously tagged with 'carnal desire' and 'explicit'."}, {"segment_id": "segment-006", "emotion_fit": 1, "delivery_fit": 3, "note": "Continuation of previous phrase, similarly mislabeled with sexual lust/carnal desire."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 4, "note": "Vulnerable whispered delivery is accurate, though affection/compassion is questionable here."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Vulnerable and sorrowful whisper fits well."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Vulnerable and tender confession matches well."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Apologetic, regretful whisper fits well."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet relief matches the spoken words."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft relief and comfort fit this affirmation."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Intimate ASMR-like whispered tone conveying quiet relief and resolution."}], "audible_events": [{"start_s": 1.5, "end_s": 2.2, "type": "gasp / breath"}, {"start_s": 5.4, "end_s": 6.1, "type": "exhale / sigh"}, {"start_s": 9.4, "end_s": 10.4, "type": "sigh / breath"}, {"start_s": 10.7, "end_s": 11.2, "type": "inhalation"}, {"start_s": 20.7, "end_s": 22.0, "type": "sigh / tremulous exhale"}, {"start_s": 25.1, "end_s": 25.8, "type": "breath intake"}, {"start_s": 32.3, "end_s": 32.9, "type": "breath intake"}], "overall_note": "Several segments (001, 003, 005, 006) are inappropriately tagged with 'carnal desire' / sexual lust, which severely contradicts the solemn, emotionally vulnerable grief narrative. Burst events also suffer from overlapping duplicate intervals around 1.5-2.4s and 9.3-10.6s."}, "usage": {"promptTokenCount": 7241, "candidatesTokenCount": 1078, "totalTokenCount": 8319, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 914}, {"modality": "TEXT", "tokenCount": 6327}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00947325, "model_version": "gemini-3.8-flash", "response_id": "pGrLatOePKmQ3boP9cr-6AM", "weighted_score": 3.1500000000000004, "annotation_sha256": "3820ca136e48d024f4c19d5eb95f9c7d8bf5a1244208c093a0a1f006eee45ed5", "audio_sha256": "85681fc7a6135c84309c170d4e83fe7b4cae4754171da8653e8d95b983624215", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-02261", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 0, "delivery_fit": 3, "note": "Tagged with 'feeling horny' (sexual lust), which is entirely wrong and absurd for this tense, confrontational delivery."}, {"segment_id": "segment-002", "emotion_fit": 0, "delivery_fit": 3, "note": "Inherited the completely hallucinated 'feeling horny' tag for 'that.'"}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "No emotion tag, which is acceptable for a brief interjection, though voice is sharp rather than tonal/bright."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Omits specific anger/frustration emotion tags, but acoustic descriptors are acceptable."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Dismay tag fits the exasperated, firm delivery decently."}, {"segment_id": "segment-006", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged with 'fervor / hope/optimism', which contradicts the resigned, bitter tone."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Irritability tag captures the sharp confrontational delivery well."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Irritability tag is suitable for the sharp questioning 'okay?'."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Dissociated/numbness captures the deflated, soft second 'okay'."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Acrimony/bitterness matches the strained confession."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Acrimony and tense delivery tags fit well."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Negative/acrimony matches the final vulnerable and hurt statement."}], "audible_events": [{"start_s": 0.0, "end_s": 0.44, "type": "gasp"}, {"start_s": 6.85, "end_s": 7.38, "type": "gasp"}, {"start_s": 9.9, "end_s": 10.55, "type": "sigh"}, {"start_s": 15.65, "end_s": 16.5, "type": "sigh"}, {"start_s": 16.7, "end_s": 17.4, "type": "snort"}], "overall_note": "Segments 1 and 2 suffer from a bizarrely hallucinated 'feeling horny' (sexual lust) emotion tag in an otherwise tense confrontation. Several breath/burst events overlap speech or are duplicated in the same pause gap (e.g., HVA_EVENT_0002 and HVA_EVENT_0003)."}, "usage": {"promptTokenCount": 6392, "candidatesTokenCount": 1005, "totalTokenCount": 7397, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 578}, {"modality": "TEXT", "tokenCount": 5814}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00856275, "model_version": "gemini-3.8-flash", "response_id": "pGrLarioL4PR28oP2Y-r8Qw", "weighted_score": 3.1500000000000004, "annotation_sha256": "8fccd35d28f5786b4aefc734e5c19b56ece58e3adbb5281f4a399490db851dfb", "audio_sha256": "ee91a4c2dbe2e556762a8c8ff686585d6bb8d4b4576f767b2b76f01c8ccc03ef", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-02600", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 1, "delivery_fit": 2, "note": "Tagged with 'relief' and 'brightening', but the speaker is speaking in a tense, anxious, calming whisper."}, {"segment_id": "segment-002", "emotion_fit": 1, "delivery_fit": 2, "note": "Reassuring whisper, not 'relief'."}, {"segment_id": "segment-003", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged as 'awestruck', which is inaccurate; the tone is supportive reassurance under intense stress."}, {"segment_id": "segment-004", "emotion_fit": 0, "delivery_fit": 2, "note": "Tagged as 'romantic desire', which completely misinterprets the tense emergency situation."}, {"segment_id": "segment-005", "emotion_fit": 0, "delivery_fit": 2, "note": "Tagged as 'mocking playfully', but this is an urgent instruction."}, {"segment_id": "segment-006", "emotion_fit": 1, "delivery_fit": 2, "note": "A tense, focused breathy 'Okay', not 'indifference' or 'scattered'."}, {"segment_id": "segment-007", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged with 'apathy', completely contrary to the focused emergency context."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as 'burnout'; speaker is bracing with physical exertion."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "A strained grunt/push ('Come on'), sharp-onset tag is reasonable."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Short exertion syllable ('up')."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "High physical tension and distress/desperation; 'irascibility'/'very tense' captures the strain reasonably well."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "A groaning exertion sound transcribed as 'Oh'."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Very strained, desperate pleading under heavy physical effort."}], "audible_events": [{"start_s": 12.1, "end_s": 12.8, "type": "grunt/groan of physical effort"}, {"start_s": 14.1, "end_s": 14.6, "type": "gasp/grunt"}, {"start_s": 17.2, "end_s": 17.8, "type": "groan/grunt"}, {"start_s": 17.8, "end_s": 18.2, "type": "sharp breath intake"}], "overall_note": "The global description is fairly accurate regarding the vocal progression from whisper to strained shouting/groaning. However, the local sentence emotion tags heavily hallucinate romantic desire, teasing/mocking, relief, and apathy during an obvious emergency rescue scenario. Furthermore, burst events heavily overlap each other repeatedly around 12s and 17s."}, "usage": {"promptTokenCount": 6348, "candidatesTokenCount": 1024, "totalTokenCount": 7372, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5835}, {"modality": "AUDIO", "tokenCount": 513}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.008601, "model_version": "gemini-3.8-flash", "response_id": "pGrLaurUN9G0kdUPjdKXqA8", "weighted_score": 3.1500000000000004, "annotation_sha256": "e4491cc60d057fc22e93b9cc63cde4c8fd923d72bcce4b710a9fd4597dbd6e36", "audio_sha256": "0cbcadf23719235f132af90d13df5c8067a5b648504d277cde685557be7fda3c", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-02690", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 4, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Casual tone; tags like solace are inaccurate."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Short tag phrase; solace fits poorly."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone is conspiratorial rather than pensiveness."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Mischievous and relaxed rather than reflective."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Rhetorical whisper rather than genuine astonishment."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "Stoicism poorly captures the playful delivery."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Compassion is a poor fit for the suggestive tone."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Pacing tag does not match this brief single word."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone is teasing and dominant, not compassionate."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Clear assertive edge is mislabeled as compassion."}], "audible_events": [{"start_s": 2.74, "end_s": 3.25, "type": "laughter"}], "overall_note": "Acoustic and style descriptions are solid, but emotion tags diverge heavily from the playful conspiratorial intent."}, "usage": {"promptTokenCount": 4847, "candidatesTokenCount": 665, "totalTokenCount": 5512, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 526}, {"modality": "TEXT", "tokenCount": 4321}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.006129, "model_version": "gemini-3.8-flash", "response_id": "rGrLatKCA-HjkdUPxrn0IQ", "weighted_score": 3.5, "annotation_sha256": "07dfed91375179f307360125c6e9988c862b2d7911a117057aeba3d94c1ec643", "audio_sha256": "9e065a91f1023cf0e79813fdcc6c91dd192f55ce6a650bf4862ce614cb627c4c", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-02741", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Whispery, quiet tone matches well; 'fatigue' is debatable but plausible as languid weary menace."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Accurate whispery soft delivery."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 2, "note": "'Very meek' and 'pining' mischaracterize the sinister, controlled delivery."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 2, "note": "Over-fragmented segment; meek/pining does not match tone."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 2, "note": "Extremely brief fragment; tags carry over inaccurate meek/pining descriptors."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 4, "note": "Whispered, slow delivery fits well; 'wistfulness' is somewhat subjective."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 4, "note": "Whispered quiet delivery accurately described."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "'Warmth' does not capture the sinister undertone."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Creepy, whispered affect rather than genuine warmth."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Low, quiet breathy affirmation."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Slow, aggressive, malicious delivery fits well."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Sinister whispered emphasis matches."}, {"segment_id": "segment-013", "emotion_fit": 3, "delivery_fit": 4, "note": "'Saudade' is an unusual tag here, but slow steady whisper matches audio."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Controlled menacing threat aligns well with malice/sadism descriptor."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet whisper fits delivery."}, {"segment_id": "segment-016", "emotion_fit": 4, "delivery_fit": 4, "note": "Vindictive, whispering threat accurately captured."}, {"segment_id": "segment-017", "emotion_fit": 2, "delivery_fit": 3, "note": "Transcript treats nonverbal scoff 'Pff' as spoken text while also annotating it as an event."}, {"segment_id": "segment-018", "emotion_fit": 3, "delivery_fit": 4, "note": "Breathy challenge delivery matches."}, {"segment_id": "segment-019", "emotion_fit": 3, "delivery_fit": 4, "note": "Low quiet ending matches."}], "audible_events": [{"start_s": 0.0, "end_s": 0.55, "type": "breath"}, {"start_s": 13.25, "end_s": 14.35, "type": "sigh"}, {"start_s": 27.2, "end_s": 27.65, "type": "snort"}], "overall_note": "The global description is strong, accurately capturing the menacing half-whisper delivery. However, segment-017 duplicates the scoff sound ('Pff') as both spoken text and an event, and an earlier event (HVA_EVENT_0002) hallucinates a scoff between 'Gonna' and 'gonna pound it black' where none occurred. Some emotional labels (meek, warmth) conflict with the overarching menacing tone."}, "usage": {"promptTokenCount": 8247, "candidatesTokenCount": 1230, "totalTokenCount": 9477, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 762}, {"modality": "TEXT", "tokenCount": 7485}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01079775, "model_version": "gemini-3.8-flash", "response_id": "rGrLapv7E63nnsEPudSBCQ", "weighted_score": 3.4000000000000004, "annotation_sha256": "7293924b5f0670460fd0213ab3d214ac14002b7ac540326b3b13cbb3b728aed7", "audio_sha256": "8c237c3866e1ba308f99c940f0f17f92a74d56792aa2033c3ef8a812b26004e3", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-04819", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Stern, quiet confrontational tone is mislabeled with homesickness."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Infatuation label conflicts with the stern, authoritative instruction."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Direct, hushed demand fits darkening mood moderately well."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Infatuation tag does not match the firm confrontation."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Apathy is somewhat off for firm finality, but delivery is controlled."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Short rhetorical check; doubt is only partially appropriate."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Tersely spoken; cold tag fits better than boredom."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Shift to comfort tagged inappropriately as lust."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Gentle maternal comfort mischaracterized as lust."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Carnal desire label conflicts with soothing parental speech."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 3, "note": "Reassuring offer tagged as lust inappropriately."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Affection and devotion fit the soothing promise well."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 3, "note": "Reassuring closure mislabeled with crush/infatuation."}], "audible_events": [{"start_s": 13.0, "end_s": 14.5, "type": "sigh"}], "overall_note": "Acoustic and stylistic descriptions are broadly adequate, but segment emotion tags repeatedly assign romantic or sexual labels to protective and reassuring speech."}, "usage": {"promptTokenCount": 5803, "candidatesTokenCount": 823, "totalTokenCount": 6626, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 619}, {"modality": "TEXT", "tokenCount": 5184}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0074385, "model_version": "gemini-3.8-flash", "response_id": "rGrLaqaqIf2D3boPrIKd8Q8", "weighted_score": 2.8000000000000003, "annotation_sha256": "9f67eaef85d6e6ac19205bd1c7f5fc16cad25733fcbd7cf51d7dcb2cc33709b8", "audio_sha256": "05b0d8f34deb7850f684216005284ee0554490fdced5506993c689d955618fc8", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-04841", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 4, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "The tone is tense and confrontational rather than strongly characterized as craving."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Bitterness fits the narrative setup well."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Consistent quiet bitter delivery."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Accusatory and bitter delivery matches."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Delivers the punchline of the anecdote with bitter restraint."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Disdain and contempt fit well."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered disgust/abhorrence is accurately captured."}, {"segment_id": "segment-008", "emotion_fit": 1, "delivery_fit": 3, "note": "Labeling this as sexual lust is completely inaccurate for this dramatic, hurt monologue."}, {"segment_id": "segment-009", "emotion_fit": 1, "delivery_fit": 3, "note": "Sexual lust is inappropriate for this quiet pause/word."}, {"segment_id": "segment-010", "emotion_fit": 1, "delivery_fit": 3, "note": "Severe mismatch with 'sexual lust'; the speaker expresses vulnerable hurt and resentment."}, {"segment_id": "segment-011", "emotion_fit": 1, "delivery_fit": 3, "note": "Severe mismatch with sexual lust."}, {"segment_id": "segment-012", "emotion_fit": 1, "delivery_fit": 3, "note": "'Having a crush' / infatuation is completely dissonant with the confrontational demand."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 3, "note": "'Pride' does not match the bitter, demanding resolution."}], "audible_events": [{"start_s": 11.5, "end_s": 12.3, "type": "scoff / breath"}, {"start_s": 17.1, "end_s": 18.2, "type": "sigh / exhalation"}], "overall_note": "The global description captures the monologue's tone, pacing, and sigh well. However, duplicate overlapping events were proposed for the chuckle/snort around 11-12s, and segments 8 through 12 have completely hallucinated romantic/sexual emotion tags ('sexual lust', 'having a crush') that conflict sharply with the bitter confrontational performance."}, "usage": {"promptTokenCount": 6442, "candidatesTokenCount": 906, "totalTokenCount": 7348, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5595}, {"modality": "AUDIO", "tokenCount": 847}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.008229, "model_version": "gemini-3.8-flash", "response_id": "rGrLas2nHJaLxN8PjuukqQo", "weighted_score": 3.35, "annotation_sha256": "dfa1e1e3d7fd0f9675bbc19d5b6d922e2e2b3d34681307cdb74d5be9bc432153", "audio_sha256": "1c1151c961def205996f6886686dae582bb1ad0c7d823a95f7deeb60d32c0e4e", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-05245", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Startlement tag is exaggerated for this quiet reflection."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Amazement is slightly overstated; tone is mild."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 3, "note": "Playful tags fit well, though repeated chuckles clutter the timeline."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Mournfulness is mismatched to the intimate tone."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Continues an exaggerated sadness characterization."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Transcript mishears 'pried' as 'pry'; delivery tags are acceptable."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Isolated segment carries mild doubt; reasonable fit."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Doubt is fitting, but overlaps with duplicate sigh events."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Suspicion tag does not match the flirtatious hesitation."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Extremely brief conjunction inheriting unverified suspicion tags."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Flirtatious delivery mismatches the negative suspicion cue."}], "audible_events": [{"start_s": 0.0, "end_s": 0.46, "type": "sigh"}, {"start_s": 4.5, "end_s": 5.0, "type": "laughter"}, {"start_s": 7.02, "end_s": 7.6, "type": "laughter"}, {"start_s": 15.35, "end_s": 15.85, "type": "gasp"}, {"start_s": 19.3, "end_s": 20.3, "type": "sigh"}], "overall_note": "Acoustic style descriptions are solid, but several burst events are duplicated across overlapping intervals. Emotional labeling skews overly dramatic with mournfulness and suspicion."}, "usage": {"promptTokenCount": 5865, "candidatesTokenCount": 1037, "totalTokenCount": 6902, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 646}, {"modality": "TEXT", "tokenCount": 5219}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0082875, "model_version": "gemini-3.8-flash", "response_id": "tGrLaoucBdudvdIP1MmVgQo", "weighted_score": 3.3000000000000003, "annotation_sha256": "883f500a0d577d819fec9435e5717c5a83d742e9bcf0c287437cd7e4e1b68f9c", "audio_sha256": "0613567032b9ad3f03f65f24072c940636c14b0af7c9c058a5ba287deb3e893c", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-06071", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 4, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 4, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 5, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, breathless athletic setup."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet, steady whisper."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Breath-led pacing, accurate ASMR whisper tone."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft and whispered delivery."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 3, "note": "Isolated single word framed by heavy breaths; timing overlaps with burst boundaries."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, intimate delivery with sensual inflection."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet breathless questioning."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Brief whisper."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 2, "note": "Duration assigned (0.03s) is unrealistically narrow and poorly segmented relative to speech."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft whisper followed immediately by breath/sigh."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Sensual whisper."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 3, "note": "Overlaps with breath tags around 'Please'."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Faint breathy whisper ending the phrase."}], "audible_events": [{"start_s": 0.0, "end_s": 0.65, "type": "gasp / breath"}, {"start_s": 1.45, "end_s": 2.2, "type": "pant / breath"}, {"start_s": 10.7, "end_s": 11.5, "type": "breath"}, {"start_s": 12.8, "end_s": 13.5, "type": "sharp breath"}, {"start_s": 15.0, "end_s": 15.6, "type": "breath"}, {"start_s": 20.7, "end_s": 22.0, "type": "panting"}, {"start_s": 22.3, "end_s": 23.0, "type": "breath"}, {"start_s": 25.8, "end_s": 27.5, "type": "groan / breathy sigh"}, {"start_s": 28.4, "end_s": 29.2, "type": "breath"}, {"start_s": 31.3, "end_s": 32.1, "type": "breath"}], "overall_note": "The speaker delivers a breathy, intimate, ASMR-style whispered performance with heavy panting throughout. Several annotated burst events heavily overlap each other (e.g. HVA_EVENT_0001 through 0005, and 0011 with 0012) creating redundant detections over single breath instances, while segment-009 has an artificially compressed duration budget."}, "usage": {"promptTokenCount": 7465, "candidatesTokenCount": 1128, "totalTokenCount": 8593, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 848}, {"modality": "TEXT", "tokenCount": 6617}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00982875, "model_version": "gemini-3.8-flash", "response_id": "tGrLas2PLK2ExN8P89zcgQg", "weighted_score": 3.6, "annotation_sha256": "5e5e4ce4984b88947d4ffeadf24748b04900bd8542e3ab0cd1e691307d4f276e", "audio_sha256": "2dbf49f7f12b15a49daa9c49432efc940afcd8ed612fec2dc3e3a644ed69010d", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-06195", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Prompt startlement emotion does not capture the mildly exasperated pleading."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Carries forward startlement instead of urgent, persuasive reasoning."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Optimism tag aligns reasonably well with the hopeful projection."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Playful and bantering tags reflect the conversational pivot."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Short remnant carries acceptable playfully casual cues."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "Single word conjunction; contentment/ease does not fit the cynical pivot."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Ease is inappropriate for the pessimistic counter-argument."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Awestruck label misses the critical and skeptical tone."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Shock emotion loosely maps to the alarmed, urgent warning."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Honor/pride contradicts the weary, resigned conclusion."}], "audible_events": [{"start_s": 0.0, "end_s": 0.35, "type": "inhalation"}, {"start_s": 6.3, "end_s": 6.75, "type": "chuckle"}, {"start_s": 18.25, "end_s": 18.9, "type": "sigh"}], "overall_note": "Acoustic and style descriptions are largely grounded, but burst events include duplicated/overlapping intervals and local emotion tags mismatch speaker cynicism."}, "usage": {"promptTokenCount": 5498, "candidatesTokenCount": 899, "totalTokenCount": 6397, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 516}, {"modality": "TEXT", "tokenCount": 4982}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00749475, "model_version": "gemini-3.8-flash", "response_id": "tWrLauP4CJSwnsEP5eLSmAM", "weighted_score": 2.7, "annotation_sha256": "10b4d0b09d17096a07c9ea132d1c033ddc4414f342dd47e9c44bf3c9b1958b01", "audio_sha256": "b1fe021f798ab681dfb354474d758b51553ab026baf30f3739742c68fa0f2504", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-06251", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 4, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Low energy greeting, somewhat detached."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Fatigued agreement; 'cold' is overly clinical."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 4, "note": "Tired, slow delivery rather than pure boredom."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 4, "note": "Continuation of the previous segment, monotone and weary."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Good identification of fatigue, though the inline burst timing is slightly off."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Mild surprise/interruption rather than acute discomfiture."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Playful disbelief rather than discomfiture."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 3, "note": "Ribbing/amusement is accurate; 'very explicit' descriptor is inaccurate."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 3, "note": "Overlaps with an amused sigh/chuckle."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 3, "note": "Exasperated amusement fits nicely."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 3, "note": "'Very revulsion' is overly dramatic; it is affectionate/playful teasing."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Tired pivot back to conversation."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Exhausted conversational pacing."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Smooth continuation with mild fatigue."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Teasing comment about illness."}, {"segment_id": "segment-016", "emotion_fit": 3, "delivery_fit": 3, "note": "Short pause word ('hang')."}, {"segment_id": "segment-017", "emotion_fit": 3, "delivery_fit": 3, "note": "Continuation ('on')."}, {"segment_id": "segment-018", "emotion_fit": 2, "delivery_fit": 3, "note": "Apologetic, but 'very mortification' is exaggerated."}, {"segment_id": "segment-019", "emotion_fit": 3, "delivery_fit": 3, "note": "Skepticism tag is mismatched; she coughs/clears throat before resuming."}, {"segment_id": "segment-020", "emotion_fit": 3, "delivery_fit": 4, "note": "Questioning tone, straightforward scheduling prompt."}], "audible_events": [{"start_s": 5.4, "end_s": 5.9, "type": "groan"}, {"start_s": 8.9, "end_s": 9.8, "type": "sigh"}, {"start_s": 13.2, "end_s": 13.8, "type": "laughter"}, {"start_s": 14.0, "end_s": 14.5, "type": "laughter"}, {"start_s": 17.1, "end_s": 18.0, "type": "laughter"}, {"start_s": 18.7, "end_s": 19.2, "type": "inhalation"}, {"start_s": 27.2, "end_s": 28.3, "type": "cough"}], "overall_note": "The speaker is audibly sick and tired, and the global monologue description captures this context nicely. However, several local emotion labels dramatically overstate negative affect (e.g., revulsion, mortification) when the tone is playfully conversational. In the latter section (around 27-28s), the speaker clearly coughs, but the annotation mischaracterizes it as a chuckle followed by a gasp."}, "usage": {"promptTokenCount": 9042, "candidatesTokenCount": 1356, "totalTokenCount": 10398, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 8274}, {"modality": "AUDIO", "tokenCount": 768}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0118665, "model_version": "gemini-3.8-flash", "response_id": "tWrLapLUJuSN28oPru7bgAg", "weighted_score": 3.5500000000000003, "annotation_sha256": "603518cb4fe476179d58e52a7f58805a86ae29a96af2cc7c56717cb4410b1426", "audio_sha256": "10344f307276a5a45889096988867e0335d05f2a1d88e7f7f065c6516f4d6ef1", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-06532", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone is friendly reassurance rather than irritation."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Fairly casual and reassuring rather than strongly provoking."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 3, "note": "Fits the relaxed, relieved conversational tone well."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Fervor is overly dramatic for a casual thought."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Simple continuation, low intensity."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Light and warm, tags are somewhat exaggerated."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Moderate fit; calm forward-looking statement."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Affirming reassurance rather than shock."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Apathy does not quite match the gentle, friendly conclusion."}], "audible_events": [{"start_s": 0.05, "end_s": 0.55, "type": "chuckle"}, {"start_s": 3.15, "end_s": 3.65, "type": "laughter"}, {"start_s": 13.2, "end_s": 13.85, "type": "chuckle"}, {"start_s": 17.4, "end_s": 18.0, "type": "sigh"}], "overall_note": "Annotation captures overall acoustic qualities well, but includes several duplicate burst events and over-interprets mild conversational turns as extreme emotional states."}, "usage": {"promptTokenCount": 5280, "candidatesTokenCount": 718, "totalTokenCount": 5998, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 479}, {"modality": "TEXT", "tokenCount": 4801}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0066525, "model_version": "gemini-3.8-flash", "response_id": "vGrLao3GKNG0kdUPjdKXqA8", "weighted_score": 3.4000000000000004, "annotation_sha256": "35354940e31d2ff8ba5d9ffe2552fd16c72062cf8b68bff27a1b97f569fa7d7c", "audio_sha256": "d0361dc4c0c9825ed7f031ab4a41858360760444b8ef5c498ad3c0d8d12c2982", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-06597", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged sympathy conflicts with the confrontational tone."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Continues hurt and confrontation rather than sympathy."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Fatigue label is plausible though tone is mostly firm."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Reasonable delivery fit for a brief adverbial phrase."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Captures the deflated delivery adequately."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Firm interruption rather than purely stoic."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Very short segment matching the preceding delivery."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Neutral emotion omission is acceptable here."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Firm and assertive demand."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 3, "note": "Letdown fits the exasperated delivery well."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Physical pain tag is somewhat overstated for emotional pain."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Firm boundary-setting delivery fits moderately well."}], "audible_events": [{"start_s": 7.5, "end_s": 8.5, "type": "sigh"}, {"start_s": 17.5, "end_s": 18.5, "type": "breath"}], "overall_note": "Global summary is largely accurate, but several emotion tags mismatch the confrontational delivery, and breath events overlap redundantly."}, "usage": {"promptTokenCount": 5860, "candidatesTokenCount": 774, "totalTokenCount": 6634, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 559}, {"modality": "TEXT", "tokenCount": 5301}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0072975, "model_version": "gemini-3.8-flash", "response_id": "vmrLasaxOLWjnsEP3vz6yAM", "weighted_score": 3.0, "annotation_sha256": "42c903865249c0e113ee2b2f678d26cd682de179925b6748c4cf3ae90f94e90f", "audio_sha256": "405774f159a213349e0c818791f2fc38f2d22238b6d5696b15d790da4d69a1af", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-07521", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 4, "note": "Tone is comforting and intimate rather than showing strong appreciation/gratitude."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "The label 'very explicit' for content appropriateness is completely inaccurate; delivery is soft and reassuring."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 4, "note": "Isolated word 'you' continuation; again mislabeled as explicit content."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 4, "note": "The speaker expresses reassurance, not 'terror'; the text mentions being terrified but the speaker's affect is calm."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Gentle, calm alleviation/reassurance fits well."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "'Emotional blunting' misrepresents the intentional soothing warmth."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Same mischaracterization as emotionally blunted."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 4, "note": "Hope/optimism fits moderately well, delivered softly."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "'Insensitivity' is contradictory to the delicate, soothing delivery."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Gentle pacing, not insensitive."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 4, "note": "'Romantic desire' is an over-interpretation of ASMR/whisper intimacy."}, {"segment_id": "segment-012", "emotion_fit": 2, "delivery_fit": 4, "note": "Intended to comfort/soothe, not clearly romantic desire."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Warm reassurance and relief."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 3, "note": "Infatuation is inaccurate; delivery is quiet and reassuring."}], "audible_events": [{"start_s": 3.2, "end_s": 3.7, "type": "breath"}, {"start_s": 7.0, "end_s": 7.5, "type": "breath"}, {"start_s": 20.3, "end_s": 21.6, "type": "breath"}], "overall_note": "The speaker delivers a soft, ASMR-style comforting monologue. The annotation frequently confuses words mentioned in the script (e.g. 'terrified' leading to a label of terror) with the speaker's actual calming affect, and adds ungrounded labels like romantic desire, infatuation, and emotional blunting. The burst events between 19.7s and 21.5s are duplicate/overlapping entries for the single prolonged breath."}, "usage": {"promptTokenCount": 6651, "candidatesTokenCount": 1014, "totalTokenCount": 7665, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 6025}, {"modality": "AUDIO", "tokenCount": 626}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00879075, "model_version": "gemini-3.8-flash", "response_id": "vmrLaqi5ML_Y7M8PtYypiAQ", "weighted_score": 3.2, "annotation_sha256": "8da75c655dcd373c0c37395ea9bd118276801c8a5d98b449a78e3d26c917c998", "audio_sha256": "2b28a971ef0a228b47cd54ab199c30379fda81cbab4f00faaae45e36560d391f", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-07644", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Labeling as contentment/lightness misses the strained, breathless tone."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Delivery is strained whisper rather than pleasant contentment."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as lighthearted fun, but it is delivered as a grim, strained whisper."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Fatigue and quiet delivery match well."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet, breathy, tired delivery accurately reflected."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Vocal groan/gasp of pain rather than purely emotional blunting."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Short groan/exhale matches physical exhaustion."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathless, strained whisper fits burnout/fatigue."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Matches labored breathing and vocal fatigue."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "More frustrated/shivering than pure disgust."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Shivering repetition with cold distress."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Tense and throaty shivering fits well."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered exhaustion matches the audible shivering whisper."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Shivering and exhausted whisper matches well."}], "audible_events": [{"start_s": 2.2, "end_s": 2.7, "type": "gasp / inhalation"}, {"start_s": 8.35, "end_s": 9.4, "type": "shivering pant / breath"}, {"start_s": 10.2, "end_s": 10.9, "type": "groan / exhale"}, {"start_s": 14.1, "end_s": 15.0, "type": "groan / breath"}, {"start_s": 19.3, "end_s": 20.2, "type": "gasp / shivering pant"}, {"start_s": 25.1, "end_s": 25.8, "type": "shivering exhale"}], "overall_note": "The global caption captures the cold, breathy, shivering acting performance accurately. However, earlier segments are mistakenly tagged with positive emotions (lightness, lighthearted fun), and several burst events heavily overlap directly with spoken words rather than strictly marking isolated nonverbal vocalizations."}, "usage": {"promptTokenCount": 7090, "candidatesTokenCount": 1048, "totalTokenCount": 8138, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 6440}, {"modality": "AUDIO", "tokenCount": 650}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0092475, "model_version": "gemini-3.8-flash", "response_id": "wWrLap-YB8ulvdIPxpCB4AY", "weighted_score": 3.3000000000000003, "annotation_sha256": "a9193b12191d4c790c65f7d9a27fcca397a5100c88bdbce378f85e998d939c07", "audio_sha256": "9fb0e040a4d9e50870ae0c6b4e567f9ebb9f5ccbaf02794df30f873f24b2bb17", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-07790", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Formal delivery matches well; numb tag is overstated."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Short transition; playful mocking is inappropriate."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone remains firm rather than teasing."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Flat and matter-of-fact; existential label is excessive."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Direct interjection; clemency does not fit."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Firm command; affection tag is inaccurate."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Serious instruction; sexual lust tag is incorrect."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Exasperation fits the audible tension reasonably well."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Firm delivery aligns with exasperated descriptors."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Gratitude tag matches text but delivery is subdued."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Quiet reinforcement; void tag is exaggerated."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Earnest advice; reverence tag is somewhat misplaced."}], "audible_events": [{"start_s": 9.15, "end_s": 9.55, "type": "breath"}], "overall_note": "Acoustic baseline and pacing are well-captured, but multiple segment-level emotion tags introduce spurious affective states."}, "usage": {"promptTokenCount": 5738, "candidatesTokenCount": 754, "totalTokenCount": 6492, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5118}, {"modality": "AUDIO", "tokenCount": 620}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.007131, "model_version": "gemini-3.8-flash", "response_id": "xWrLaqrjHYzk7M8P3Oib0Aw", "weighted_score": 2.85, "annotation_sha256": "e8adff63ef910e9b49fd8654d594508b3f3847594805af271ef06d1bd387ec3b", "audio_sha256": "8029da89cc235bc87b229527903fac902db9a45ee3e6f64841e1a2e650b78fdb", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-07830", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 1, "delivery_fit": 4, "note": "Tagged as 'sexual lust', but the delivery is gentle, warm, and soothing caretaking."}, {"segment_id": "segment-002", "emotion_fit": 1, "delivery_fit": 4, "note": "Tagging as sexual lust is completely ungrounded in the gentle, protective delivery."}, {"segment_id": "segment-003", "emotion_fit": 1, "delivery_fit": 3, "note": "Labeling addressing a child with sexual lust is completely inaccurate."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Warmth and ASMR intimate delivery are well supported."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "'Oh' is vocalized breathily; 'thin' delivery matches the light head voice."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Gratitude and soft tone are well captured."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Vulnerable shivering tone, stoicism is somewhat misrepresentative of the cold/shivering affect."}, {"segment_id": "segment-008", "emotion_fit": 1, "delivery_fit": 4, "note": "'Feeling turned on' is an inappropriate projection onto a gentle maternal/caretaking delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 4, "note": "Fondness/concern is audible; whispered ASMR delivery is accurate."}, {"segment_id": "segment-010", "emotion_fit": 1, "delivery_fit": 3, "note": "Labeling as 'explicit lust' is unsupported by the acoustic delivery, which remains soft and gentle."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 4, "note": "Soft, vulnerable, and frightened tone; longing/pining is somewhat off."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Solace/soothing hushed tone is accurate."}, {"segment_id": "segment-013", "emotion_fit": 1, "delivery_fit": 3, "note": "'Carnal desire' completely misinterprets the calming lullaby cadence."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Reassurance, relief, and relaxed delivery fit well."}], "audible_events": [{"start_s": 5.8, "end_s": 6.8, "type": "sigh/vocalization ('Oh')"}, {"start_s": 12.0, "end_s": 13.5, "type": "sigh/exhalation"}, {"start_s": 18.25, "end_s": 18.95, "type": "breath"}], "overall_note": "The speaker performs a gentle, breathy dialogue with ASMR/whispered intimacy. However, multiple local segments are severely mislabeled with tags related to sexual lust, carnal desire, and explicit sexual arousal that are completely unsupported by the audible comforting/caretaking tone."}, "usage": {"promptTokenCount": 6689, "candidatesTokenCount": 1018, "totalTokenCount": 7707, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 676}, {"modality": "TEXT", "tokenCount": 6013}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00883425, "model_version": "gemini-3.8-flash", "response_id": "x2rLauzxHrrjxN8P45fXsQU", "weighted_score": 2.95, "annotation_sha256": "acfd03eb33ccefecb919620fcec6b212ce4856f0a01fc3a59c682229b1b6c208", "audio_sha256": "694ace40ba38aeb8a8a59adfd47681403add29dff38ef23d378f398f17529295", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-07903", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Commercial read starts with cheerful delivery."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Maintains cheerful, bright commercial tone."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Tags overstate affection; tone is standard promo read."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Spoken aside asking for feedback, not reverence."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Casual studio acknowledgment."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Brief transitional filler, neutral tone."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Standard conversational pause for headphones."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Indifference label is mildly unfitting for functional aside."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 3, "note": "Restart of the read with renewed energy."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 3, "note": "Bright commercial performance."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Energetic promotional style rather than deep tenderness."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Warm commercial finish with good energy."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 3, "note": "Spoken aside to engineer, not self-conscious."}], "audible_events": [{"start_s": 11.2, "end_s": 12.3, "type": "breath"}], "overall_note": "Script captures both promotional takes and conversational outtakes, but misinterprets technical interjections as exaggerated emotional states."}, "usage": {"promptTokenCount": 5801, "candidatesTokenCount": 778, "totalTokenCount": 6579, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5215}, {"modality": "AUDIO", "tokenCount": 586}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00726825, "model_version": "gemini-3.8-flash", "response_id": "yGrLaui6GZaLxN8PjuukqQo", "weighted_score": 3.0, "annotation_sha256": "73062a62c20b3232dffca5681662aa9f285b1c0c783d35d76a4bcc42324bb3a0", "audio_sha256": "008a0844e97a69aa609906daa0a5ef2e8b0b27677c81a240494a3d6b8794e358", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-08566", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 3, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone is didactic and dry rather than amazed."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Short direct address, not expressing amazement."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Single connective word lacking strong emotion."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Firm delivery rather than amazement."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Mild exasperation aligns well with delivery."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Conversational transition, fulfillment tag is off."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Brief segment closing phrase, neutral affect."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Instructional tone rather than fulfillment."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 4, "note": "Attentive question, fits relaxed delivery."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 2, "note": "Nostalgic instructional delivery, not news-anchor."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 3, "note": "Deliberate emphasis rather than apathy or rushing."}, {"segment_id": "segment-012", "emotion_fit": 2, "delivery_fit": 3, "note": "Evocative closing line, not shock."}], "audible_events": [{"start_s": 5.95, "end_s": 7.15, "type": "sigh"}], "overall_note": "Acoustic style descriptions are reasonable, but many segment emotion tags like amazement or shock do not match the dry instructional delivery."}, "usage": {"promptTokenCount": 5764, "candidatesTokenCount": 745, "totalTokenCount": 6509, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 639}, {"modality": "TEXT", "tokenCount": 5125}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00711675, "model_version": "gemini-3.8-flash", "response_id": "yGrLaqqZJ5O5nsEPpOGhMA", "weighted_score": 2.85, "annotation_sha256": "dc667635b01065d63a916a6061e5d7cd7e3294f89eb4ff180b40f755bc25e1a5", "audio_sha256": "24315cffb29663bd2c293f7ed6f768c6498d6049f41b29d56ae1eb51fdee3b3d", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-09242", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 3, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone is friendly rather than displaying tartness."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Short question followed by a light chuckle; emotion label is slightly mismatched."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Playful teasing fits moderately well."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Amusement tag reasonably captures the tone."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Awe is somewhat overstated for this tender phrase."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Single word segment split artificially; emotion fits broad context."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Short fragmented segment carries minimal standalone affect."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Fragmented word segment with moderate delivery fit."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Sincere affection matches the spoken sentiment."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Vulnerable and bittersweet tone is generally captured."}], "audible_events": [{"start_s": 3.5, "end_s": 4.15, "type": "chuckle"}, {"start_s": 7.85, "end_s": 8.65, "type": "laughter"}, {"start_s": 23.6, "end_s": 24.5, "type": "sigh"}], "overall_note": "Annotation covers the recording reasonably well, though burst events contain duplicates and some segments are over-fragmented."}, "usage": {"promptTokenCount": 5388, "candidatesTokenCount": 725, "totalTokenCount": 6113, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 4764}, {"modality": "AUDIO", "tokenCount": 624}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00675975, "model_version": "gemini-3.8-flash", "response_id": "zWrLasTYLLmIvdIPvqS2kAc", "weighted_score": 3.0500000000000003, "annotation_sha256": "3a0c22436350483e2892829e987201f709311e536beca40de99480a33624851c", "audio_sha256": "cd464332fb47d14e45481b5e1d22797787c9eff0401a1d611109507721cd3778", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-09554", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Tone is appreciative and gentle."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Maintains appreciative tone."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Playful and lightly teasing."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Affectionate and teasing with an audible laugh at the end."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Casual questioning."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Light tag question."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Direct, calm remark."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Direct conclusion to the phrase."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Intimate, thoughtful opening."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Very short conjunction, thoughtful context."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, reflective, tender tone."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, intimate delivery."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Affectionate and grounded."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as indifference, but delivery is tender and fond rather than numb."}, {"segment_id": "segment-015", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged as revulsion/disgust, but tone is warmly affectionate and teasing."}, {"segment_id": "segment-016", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagged as revulsion/disgust, which completely misidentifies the fond sentiment."}, {"segment_id": "segment-017", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as boredom, but tone is wistful and devoted."}, {"segment_id": "segment-018", "emotion_fit": 4, "delivery_fit": 4, "note": "Gently teasing and grounded practical delivery."}], "audible_events": [{"start_s": 3.75, "end_s": 4.35, "type": "chuckle"}, {"start_s": 7.85, "end_s": 8.6, "type": "laughter"}, {"start_s": 24.5, "end_s": 25.5, "type": "sigh"}, {"start_s": 30.0, "end_s": 30.6, "type": "chuckle"}, {"start_s": 32.2, "end_s": 32.8, "type": "breath"}], "overall_note": "Several burst events are duplicated/overlapping in the script annotations (such as double sighs and double prep breaths), inflating the event list. Additionally, segments 15-16 are mislabeled as 'revulsion/disgust' despite being clearly tender and affectionate."}, "usage": {"promptTokenCount": 8505, "candidatesTokenCount": 1143, "totalTokenCount": 9648, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 862}, {"modality": "TEXT", "tokenCount": 7643}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.010665, "model_version": "gemini-3.8-flash", "response_id": "zmrLar6POKKxnsEP79DTCA", "weighted_score": 3.45, "annotation_sha256": "e4a7847663e87c101179acee8afe89fc61d3be5cb5147cc2ef8979abf28b9f09", "audio_sha256": "cb621219e546687cd0949d05b5643d20c1a2c5788c7f66331702760095b3b500", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-10100", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "The speaker shouts with rallying determination, not extreme confusion or perplexity."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Short energetic call-out; appropriate restrained tag."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Trailing off abruptly due to megaphone failure, confusion tag fits."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 3, "note": "Realization/interruption 'Wait', fits."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Muttered frustration fits repulsion/disgust tag."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Continuation of muttering."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Flat, sullen realization fits well."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 3, "note": "Direct, rallying command."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Determined and firm, insensitivity tag is slightly off."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Rising conviction and defiance."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 4, "note": "Chanting rallying question, disorientation/confusion is inaccurate."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 4, "note": "Firm response, not really contempt/disapproval towards the listener."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 4, "note": "Rallying call, skepticism tag is mismatched."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Shouted imperative 'Now!'."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Urgent command to the crowd."}, {"segment_id": "segment-016", "emotion_fit": 4, "delivery_fit": 4, "note": "Rallying call, dignified/proud tone fits."}, {"segment_id": "segment-017", "emotion_fit": 4, "delivery_fit": 4, "note": "Commanding and inspiring delivery."}, {"segment_id": "segment-018", "emotion_fit": 4, "delivery_fit": 4, "note": "Punchy concluding command."}], "audible_events": [{"start_s": 2.7, "end_s": 3.2, "type": "gasp"}, {"start_s": 4.15, "end_s": 4.75, "type": "sigh"}, {"start_s": 6.88, "end_s": 7.3, "type": "inhalation"}, {"start_s": 10.7, "end_s": 11.1, "type": "inhalation"}, {"start_s": 12.05, "end_s": 12.45, "type": "inhalation"}, {"start_s": 14.65, "end_s": 15.02, "type": "inhalation"}], "overall_note": "The proposed burst events contain several duplicates covering identical or overlapping time intervals (e.g., 3.26-3.86 overlaps with the word 'wait' at 3.24-4.08, and 4.08-4.64 overlaps with 4.36-4.96). In reality, the sound after 'wait' is an exasperated sigh/exhale rather than two separate sharp intakes. In the chants, emotions like confusion and skepticism are erroneously tagged for confident rhetorical questions."}, "usage": {"promptTokenCount": 7736, "candidatesTokenCount": 1245, "totalTokenCount": 8981, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 7233}, {"modality": "AUDIO", "tokenCount": 503}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01047075, "model_version": "gemini-3.8-flash", "response_id": "0WrLaofQAuOpnsEP1tXjuAE", "weighted_score": 3.35, "annotation_sha256": "0d0e1345bbd81af72455b3b1e6e10568db8ebcfa9c3e7bedc5c8e0cecbf87f3e", "audio_sha256": "c816c968bedd93a34fe31eb87be3c1b41d0c678694fcb0f3920cf23257a99755", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-10289", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "The speaker sighs/groans 'Oh' in anticipation; tagging as 'burnout' fatigue is misleading."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery conveys yearning and anticipation rather than exhaustion/burnout."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "A very short transitional syllable spoken breathily."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Spoken with quiet desire, not burnout."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Anticipatory whispery tone, tags repeat burnout."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered soft delivery matches 'It looks so sweet.'"}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Sudden revulsion and panic fits astonishment/tension tags well."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 3, "note": "Perplexity fits the bewildered questioning tone."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 3, "note": "Cough/gasp reaction conveys visceral disgust/pain."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Tense disgust and pain are well captured by loathing."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Strain and pain are accurately captured."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Urgent and distressed request, missing emotion tag."}, {"segment_id": "segment-013", "emotion_fit": 3, "delivery_fit": 3, "note": "Tense and distressed, left untagged for emotion."}, {"segment_id": "segment-014", "emotion_fit": 3, "delivery_fit": 3, "note": "Expresses disgust, pain, and constriction; 'exhaustion' is an approximate fit."}], "audible_events": [{"start_s": 0.05, "end_s": 0.85, "type": "groan/sigh"}, {"start_s": 2.2, "end_s": 2.9, "type": "gasp/inhalation"}, {"start_s": 8.0, "end_s": 9.2, "type": "sigh/groan"}, {"start_s": 12.0, "end_s": 12.5, "type": "gasp"}, {"start_s": 14.7, "end_s": 15.6, "type": "cough/choke"}, {"start_s": 21.6, "end_s": 22.2, "type": "inhalation"}], "overall_note": "The general description accurately portrays the transition from anticipation to visceral revulsion and burning throat discomfort. However, the first half of the script is repeatedly mislabeled with 'burnout' (fatigue), and several proposed burst events overlap directly with each other or with spoken words."}, "usage": {"promptTokenCount": 6877, "candidatesTokenCount": 1069, "totalTokenCount": 7946, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 6267}, {"modality": "AUDIO", "tokenCount": 610}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0091665, "model_version": "gemini-3.8-flash", "response_id": "0WrLaturMYWAxs0P8_zh2Qg", "weighted_score": 3.45, "annotation_sha256": "15bde5d78255bce35af10de4379ca200702726aee56f5d6291ad448dc36ac1b9", "audio_sha256": "2d52b368573f2435d5edcaa965485efd9441731f7e99cb87a37eed9db2ce0185", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-10969", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Sharp, commanding shoo matches authoritative disdain."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Gruff, stern command delivered with solid chest resonance."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "A brief realization pause, less explicitly teasing than claimed."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Disbelieving and skeptical question, consistent with teasing."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Rough, amused dismissive ribbing fits well."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Pondering, amused delivery fits bantering."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet amused tone continues cleanly."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 2, "note": "Delivered as a flat, deadpan question/statement rather than pure astonishment; pace does not rapidly accelerate."}, {"segment_id": "segment-009", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagging 'hope' is inaccurate; the speaker is skeptical and dismissive."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Weary, tired tone matches burnout description."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Single word connector leading into reconsideration."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Playful, calculating, slightly teasing rhetorical question."}], "audible_events": [{"start_s": 4.15, "end_s": 4.5, "type": "inhalation"}, {"start_s": 8.0, "end_s": 9.4, "type": "throat-clearing cough"}, {"start_s": 15.6, "end_s": 16.1, "type": "chuckle"}, {"start_s": 20.6, "end_s": 21.1, "type": "inhalation"}, {"start_s": 25.1, "end_s": 26.2, "type": "chuckle"}], "overall_note": "The script contains significant burst timing mismatches and overlaps. For instance, an exhalation is tagged overlapping the start of 'Nice try' (18.828s), and around 25-26s two overlapping bursts are claimed where there is primarily one breathy chuckle. Several emotion tags (notably 'hope' on segment-009) mischaracterize the cynical/skeptical delivery."}, "usage": {"promptTokenCount": 6550, "candidatesTokenCount": 1155, "totalTokenCount": 7705, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5777}, {"modality": "AUDIO", "tokenCount": 773}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00924375, "model_version": "gemini-3.8-flash", "response_id": "12rLapm3B-K3nsEP2MnlyAw", "weighted_score": 3.35, "annotation_sha256": "a9f2dc7da5ec745b450627d578617383dc72f7663e573fa2ac70bad0a560783c", "audio_sha256": "d380d44888e62a22f322002bd0fc5001c3f29981724dd66a8ec1ce323345c35f", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-12110", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Fairly accurate tags; delivery aligns with whispery quality."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Labeling emotion as contentment misses the underlying somber tone."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Very short word; tagged traits are overstated."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Fondness is partly supported by tone, but breathiness dominates."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Emotion label is acceptable; delivery fits breathy cue."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Quiet resolution fits general tone well."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 3, "note": "Mortification appropriately reflects the vocal anguish."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Fear tag is reasonable, though distress is the primary tone."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Short isolated word matches preceding segment delivery."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Dejection fits the mournful tone nicely."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Arousal and volume drop well described."}], "audible_events": [{"start_s": 5.2, "end_s": 5.9, "type": "breath"}, {"start_s": 7.8, "end_s": 8.6, "type": "breath"}, {"start_s": 12.1, "end_s": 13.0, "type": "sigh"}, {"start_s": 16.3, "end_s": 17.3, "type": "sigh"}, {"start_s": 20.6, "end_s": 22.1, "type": "sigh"}], "overall_note": "Acoustic and performance descriptions are largely faithful, though some local emotion tags diverge slightly from the prevailing somber affect, and burst timings show minor overlaps with speech."}, "usage": {"promptTokenCount": 5902, "candidatesTokenCount": 844, "totalTokenCount": 6746, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5237}, {"modality": "AUDIO", "tokenCount": 665}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0075915, "model_version": "gemini-3.8-flash", "response_id": "12rLaqWnJoqFxN8P17Xv6Qs", "weighted_score": 3.4000000000000004, "annotation_sha256": "532dd2e66303054994fa4b26c3e03562d21f8202a787889e0507d749d735c239", "audio_sha256": "48b27894b70e1be19d2db87f650b8092bcceb7fc36397fb3842a6ae0a7636bc8", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-13004", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 2, "burst_timing_fit": 2, "event_precision": 2, "event_coverage": 3, "transcript_fidelity": 5, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Segment starts with an audible breath before speech at around 0.5s; emotion is mildly conversational rather than full astonishment."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Engaging storytelling tone; 'surprise' is slightly overstated for this premise setup."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "A rhetorical tag question delivered with an amused upward lilt."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagging 'very sharpness / sourness' does not match the amused, humorous delivery."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Short phrase transitioning smoothly; not sour or sharp."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 4, "note": "Amused description of the whistling sound; delivery is smiling and rhythmic."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Preceded by an audible breath/chuckle pause, but emotion is playful irony, not sourness."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Good pacing shift and comedic punchiness describing the charge."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Punchline delivery delivered with clipped timing and amusement."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Narrative pacing remains amused and light; 'curiosity' is an odd emotion tag here."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Climax of the anecdote delivered with vivid narrative inflection."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Dry, humorous deadpan resolution; 'very letdown / disappointment' misses the comedic understatement."}], "audible_events": [{"start_s": 0.05, "end_s": 0.5, "type": "breath"}, {"start_s": 7.0, "end_s": 7.3, "type": "snort/laughter"}, {"start_s": 9.75, "end_s": 10.15, "type": "laughter/breath"}, {"start_s": 16.5, "end_s": 17.1, "type": "chuckle/laughter"}], "overall_note": "The speaker delivers a humorous story with amused vocal fry, smiling voice, and several breathy chuckles. The annotation hallucinates multiple redundant, overlapping chuckle events (particularly around 16.0-17.5s, where three separate chuckles are claimed), and inappropriately assigns 'sourness' and 'disappointment' tags to playful comedic lines."}, "usage": {"promptTokenCount": 6408, "candidatesTokenCount": 973, "totalTokenCount": 7381, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 611}, {"modality": "TEXT", "tokenCount": 5797}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00845475, "model_version": "gemini-3.8-flash", "response_id": "2WrLasT0JrWjnsEP3vz6yAM", "weighted_score": 3.1500000000000004, "annotation_sha256": "c1ad850a298e76cf6d6dadac3ebae6f3a227bbbb256ba9be3a63d754507c943c", "audio_sha256": "98ba3e168d99ceab5a161d9c3a92937c37cbae52b005557e282d5b45476b6bc6", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-13064", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Starts over initial breath; overly dramatic emotion tag."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Intimate tone fits, descriptors slightly exaggerated."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Brooding tag is an odd match for reassurance."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery fits soft, intimate vocal tone."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Emotion tag is overly sexualized for the calm delivery."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Accurately notes the whispered ASMR quality."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Distrust tag contradicts the reassuring intent."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone is soft and steady."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Speech continues steadily; minor overlap with chuckle."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery remains warm rather than dark."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Short tag matches the gentle tag question."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 3, "note": "Soft, relaxing conclusion matches well."}], "audible_events": [{"start_s": 0.04, "end_s": 0.92, "type": "breath"}, {"start_s": 2.48, "end_s": 3.42, "type": "laughter"}, {"start_s": 8.1, "end_s": 9.14, "type": "sigh"}, {"start_s": 20.7, "end_s": 21.44, "type": "laughter"}], "overall_note": "Acoustic and style descriptions are solid, but local emotion tags contain several inaccurate and overly dramatic descriptors."}, "usage": {"promptTokenCount": 5885, "candidatesTokenCount": 833, "totalTokenCount": 6718, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5227}, {"modality": "AUDIO", "tokenCount": 658}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0075375, "model_version": "gemini-3.8-flash", "response_id": "2mrLapbWCKzhnsEP1YKU2Q8", "weighted_score": 3.4000000000000004, "annotation_sha256": "1e50c4a3f450a9c030b9629222820670e0ba83cd3ba6aa46e7bcc1b06f0b878a", "audio_sha256": "6de8a7b96cb2d9f067c47050fbb9ea2ad7cb9b61e5a197c65e9add8adf2f9867", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-14243", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 4, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Speaker says 'Hey' followed by an audible groan/sigh."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Short word 'Kid', reasonably fatigued."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Direct command with fatigued/groggy tone."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Prominent groaning sound/vocalization."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Pained utterance continued from groan."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Finishes 'back' in a strained tone."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "False start 'w- what', shows groggy confusion."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Tired, questioning delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Quiet, groggy questioning."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Exasperated, mildly sarcastic commentary."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 3, "note": "Rhetorical question, slightly confrontational yet tired."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 3, "note": "Flat, dry refusal."}, {"segment_id": "segment-013", "emotion_fit": 3, "delivery_fit": 3, "note": "Short command followed by a groaning sigh."}, {"segment_id": "segment-014", "emotion_fit": 3, "delivery_fit": 3, "note": "Weary complaint about cold floor."}, {"segment_id": "segment-015", "emotion_fit": 3, "delivery_fit": 3, "note": "Resigned statement."}, {"segment_id": "segment-016", "emotion_fit": 4, "delivery_fit": 3, "note": "Sarcastic, weary remark preceded by a sigh."}], "audible_events": [{"start_s": 0.44, "end_s": 1.15, "type": "sigh/groan"}, {"start_s": 3.76, "end_s": 4.86, "type": "groan"}, {"start_s": 5.1, "end_s": 5.96, "type": "groan"}, {"start_s": 6.35, "end_s": 7.15, "type": "groan"}, {"start_s": 11.0, "end_s": 12.1, "type": "sigh/chuckle"}, {"start_s": 18.9, "end_s": 20.15, "type": "sigh/groan"}, {"start_s": 25.7, "end_s": 26.6, "type": "sigh"}], "overall_note": "The audio features a tired, aching speaker complaining in the middle of the night. Several proposed nonverbal events are heavily duplicated/split into overlapping intervals where only a single continuous sigh or groan occurs (e.g. 11.0-12.12s, 18.92-20.14s, 25.74-26.86s)."}, "usage": {"promptTokenCount": 7784, "candidatesTokenCount": 1169, "totalTokenCount": 8953, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 7082}, {"modality": "AUDIO", "tokenCount": 702}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01022175, "model_version": "gemini-3.8-flash", "response_id": "32rLasWjBLmensEPyrn8iAU", "weighted_score": 3.5500000000000003, "annotation_sha256": "01969257f6b54829cae740ba184af6f5896a072ad9d1b3136fa45692a58ff908", "audio_sha256": "2c048740b6fa2b702fdf22131765e50da70797c3811702fdd2263f7d63308440", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-14983", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Slow, quiet, whispery delivery is captured well, though 'desire' is an exaggerated tag."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery remains whispery and slow, but text repetition and internal breath cuts make bounds slightly messy."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 4, "note": "Intimate and quiet reading fits."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 4, "note": "Whispery, slow paced delivery matches."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 2, "note": "'Very full' and 'insensitivity' do not match the intimate, soft whispered vocal tone."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 4, "note": "Breathy, contemplative delivery matches ASMR/whisper tags well."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 4, "note": "Very short isolated conjunction, tags are inherited."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 4, "note": "Intimate whispered phrase matches delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 4, "note": "Short isolated segment accurately marked as whispery."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Soft whispered delivery aligns well with ASMR descriptors."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Tender, quiet resolution matches the delivery well."}], "audible_events": [{"start_s": 3.25, "end_s": 3.9, "type": "breath"}, {"start_s": 6.5, "end_s": 7.3, "type": "breath"}, {"start_s": 9.4, "end_s": 10.1, "type": "breath"}, {"start_s": 12.1, "end_s": 13.0, "type": "breath"}, {"start_s": 17.1, "end_s": 17.8, "type": "breath"}, {"start_s": 24.1, "end_s": 25.2, "type": "breath"}], "overall_note": "Several burst events are duplicated with heavily overlapping timestamps (e.g. 0000/0001, 0002/0003, 0006/0007, 0008/0009), creating redundant and misaligned event spans. Segment 005 has unfitting acoustic/emotion tags ('very full', 'insensitivity')."}, "usage": {"promptTokenCount": 6514, "candidatesTokenCount": 952, "totalTokenCount": 7466, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5804}, {"modality": "AUDIO", "tokenCount": 710}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0084555, "model_version": "gemini-3.8-flash", "response_id": "4GrLaoOUNIfFnsEPkqHPAQ", "weighted_score": 3.35, "annotation_sha256": "571e8d33d89450608b9e2b3422d7594002e0797fc497c28eadbd8ccbb819646d", "audio_sha256": "8921de66228e13b8b79c4474e7012aba3b0cdb737e32b1d7f28b1f6e028b0f05", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-15782", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Short introductory particle; labels are heavily carried over from whole sentence context."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Casual narrative tone accurately captures the recount of the meeting."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Brief connecting word tagged with identical full-clause descriptors."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Speaker delivers this mildly, contemplation tag is slightly overstated."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Tone shifts toward mild exasperation rather than didactic/teacherly style."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Speaker sounds bored/weary, continuing 'teacherly' label is a mismatch."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Speaker sounds annoyed and fatigued rather than curious."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Hesitant false start well characterized by fatigue/weariness."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Burnout and fatigued delivery fit the resigned conversational style."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Dismissive and bored delivery accurately labeled."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Tagged as 'relief' but tone is flat and resigned/apathetic rather than truly relieved."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Decelerating pace and indifference accurately capture the trailing off ending."}], "audible_events": [{"start_s": 10.8, "end_s": 12.15, "type": "sigh"}, {"start_s": 17.2, "end_s": 17.7, "type": "inhale"}, {"start_s": 22.9, "end_s": 23.8, "type": "groan"}], "overall_note": "The non-speech vocal bursts contain several redundant duplicated overlapping intervals (pairs HVA_EVENT_0000/0001 and HVA_EVENT_0003/0004 cover the exact same single sigh and groan events twice). Segment 012 also includes an inline breath detection that overlaps with spoken speech. The speech transcription and overall narrative description are otherwise solid."}, "usage": {"promptTokenCount": 6417, "candidatesTokenCount": 914, "totalTokenCount": 7331, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 723}, {"modality": "TEXT", "tokenCount": 5694}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00824025, "model_version": "gemini-3.8-flash", "response_id": "4WrLar3qHfee3boPgNH1sQg", "weighted_score": 3.35, "annotation_sha256": "655bb6b2aaf7d1ca9cdb32a365832cad4e22625816ffabdbe38e1d4dd0b11d33", "audio_sha256": "333262590ae081620dbd836ff15a5b2b028131a1bbdb3e63233a02037769d18b", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-15998", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 2, "note": "Tagged as mumbled and disorganized, but speech is audible and open."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Mildly astonished tone, not particularly scattered."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "High arousal and pitch movement are present."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Irritability tag does not match the appreciative delivery."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Positive valence fits the sweet description."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Warm, infatuated tone matches well."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Conversational observation rather than clear startlement."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 3, "note": "Sigh-like exclamation fits breathy adoration."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, appreciative delivery aligns with description."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 3, "note": "Short-tempered tag misidentifies enthusiastic insistence."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Contented, positive tone matches well."}], "audible_events": [{"start_s": 0.04, "end_s": 0.78, "type": "sigh"}, {"start_s": 6.1, "end_s": 6.9, "type": "breath"}, {"start_s": 10.3, "end_s": 10.7, "type": "breath"}, {"start_s": 13.6, "end_s": 14.3, "type": "sigh"}, {"start_s": 17.2, "end_s": 17.7, "type": "sigh"}], "overall_note": "Global traits are well captured, though negative emotional tags like irritability appear inappropriately on enthusiastic segments."}, "usage": {"promptTokenCount": 5699, "candidatesTokenCount": 824, "totalTokenCount": 6523, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 568}, {"modality": "TEXT", "tokenCount": 5131}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00736425, "model_version": "gemini-3.8-flash", "response_id": "5WrLauSEH9euxN8Pvcm3mAY", "weighted_score": 3.4000000000000004, "annotation_sha256": "29ad9918c7ab2c66e6f4a2524cef84392bbe8249a8a8b143444f47bbb57c8103", "audio_sha256": "3881710cd71a089a7c4511f934ebe5be6e9c25c17922c7dba3f607479954a84d", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-16375", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Speaker sounds restrained and somber rather than displaying overt mortification."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Delivery is emotionally pained and hurt rather than direct horror."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "High tension and sharp emotional intensity are well noted."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Fading energy fits, but the emotion is grief and vulnerability rather than meek discomfiture."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Accusatory tone and emotional anguish captured reasonably well with tension and anger tags."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Husky, strained bitterness fits the delivery accurately."}, {"segment_id": "segment-007", "emotion_fit": 1, "delivery_fit": 3, "note": "Tagging 'Please' with teasing or provoking is completely inaccurate; it is a desperate plea."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet resignation and flat delivery match 'Right.'"}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Bitterness and defeat fit this resigned question."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Detachment, exhaustion, and fading energy suit the final line well."}], "audible_events": [{"start_s": 0.04, "end_s": 0.85, "type": "sigh"}, {"start_s": 5.85, "end_s": 6.45, "type": "breath"}, {"start_s": 9.45, "end_s": 10.35, "type": "breath"}, {"start_s": 15.65, "end_s": 16.25, "type": "breath"}, {"start_s": 18.5, "end_s": 19.8, "type": "sigh"}, {"start_s": 25.65, "end_s": 26.85, "type": "sigh"}, {"start_s": 33.1, "end_s": 34.3, "type": "sigh"}], "overall_note": "The global description captures the sorrowful, dramatic acting performance well. However, multiple redundant and duplicate overlapping burst events are hallucinated (e.g., repeating breaths around 6s, 9.8s, and 33-35s), and segment-007 severely misinterprets 'Please' as teasing."}, "usage": {"promptTokenCount": 6886, "candidatesTokenCount": 938, "totalTokenCount": 7824, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 5957}, {"modality": "AUDIO", "tokenCount": 929}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.008682, "model_version": "gemini-3.8-flash", "response_id": "6GrLatMMlYfbyg_I38nICg", "weighted_score": 3.35, "annotation_sha256": "d6efa70ec93c1996b6ba5ffcf050823cd013cbb224c633751c43d45395837676", "audio_sha256": "ff994f2885934a270a055223f6074dbf9acefd4d2aa361edceeaf4507fdb62a9", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-16625", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 3, "note": "Gravelly delivery is accurately captured, but pride cue is slightly off."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Matches the dry, grim vocal performance fairly well."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Relaxation tag is passable though performance stays gritty."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Disgust and tension are reasonable matches for the strained groan."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Segment is very short and matches the preceding strained tone."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 3, "note": "Contempt and dark tone match the spoken batch comment."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 3, "note": "Fits the bitter, biting spoken insult well."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Breathy, shivered delivery is captured reasonably well."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Playful mocking is slightly overstated, but teasing fit is acceptable."}], "audible_events": [{"start_s": 0.0, "end_s": 0.45, "type": "grunt/breath"}, {"start_s": 9.2, "end_s": 10.3, "type": "groan/breath"}, {"start_s": 10.9, "end_s": 11.6, "type": "grunt"}, {"start_s": 16.0, "end_s": 17.3, "type": "breath/sigh"}, {"start_s": 18.2, "end_s": 19.5, "type": "laughter/gasp"}], "overall_note": "Accurate overall acoustic description, though burst events contain multiple redundant duplicate intervals."}, "usage": {"promptTokenCount": 5495, "candidatesTokenCount": 762, "totalTokenCount": 6257, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 564}, {"modality": "TEXT", "tokenCount": 4931}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00697875, "model_version": "gemini-3.8-flash", "response_id": "6GrLavK6BIGBxs0PweDzqAo", "weighted_score": 3.45, "annotation_sha256": "4f0162bd9dedbe3f71e9aa3f26a0ed42d7c357f179011d71f071d1d25456ce22", "audio_sha256": "d1489af37d42fded6b4c4358766b11f29cafb154f8c53f70a5750564ac52d864", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-17449", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy sensual opening sigh/utterance."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Relaxed and sensual tone fits well."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 4, "note": "Sexual lust tag is somewhat overstated/interpretive, though the delivery is breathy and intimate."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Whispered and intimate delivery matches, infatuation tag is plausible but slightly speculative."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "Short isolated word within continuous speech."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Intimate tone continuing before shift."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Missing a direct alarm/surprise tag when realizing trouble."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 2, "note": "Tagged as insensitivity/emotional numbness, but it is clear shock and rising panic."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as indifference, whereas the speaker is panicking."}, {"segment_id": "segment-010", "emotion_fit": 2, "delivery_fit": 2, "note": "Burnout/exhaustion tag mischaracterizes acute urgent panic."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 2, "note": "Metallic delivery tag is inaccurate; emotion is fearful astonishment."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 3, "note": "Desperation tag captures the helpless panic well."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 3, "note": "Breathy and desperate fearful tone matches well."}, {"segment_id": "segment-014", "emotion_fit": 3, "delivery_fit": 3, "note": "Shouted command, missing explicit anger/panic tags."}, {"segment_id": "segment-015", "emotion_fit": 3, "delivery_fit": 2, "note": "Bright/metallic tags do not fit the angry/frantic shout."}, {"segment_id": "segment-016", "emotion_fit": 3, "delivery_fit": 2, "note": "Desperate final shout; metallic tag is poorly fitting."}], "audible_events": [{"start_s": 0.0, "end_s": 0.6, "type": "sigh"}, {"start_s": 3.0, "end_s": 3.4, "type": "breath"}, {"start_s": 4.9, "end_s": 5.4, "type": "breath"}, {"start_s": 9.4, "end_s": 9.9, "type": "gasp"}, {"start_s": 10.6, "end_s": 10.9, "type": "gasp"}, {"start_s": 11.3, "end_s": 11.6, "type": "gasp"}, {"start_s": 12.3, "end_s": 12.6, "type": "gasp"}, {"start_s": 13.1, "end_s": 13.5, "type": "gasp"}, {"start_s": 14.6, "end_s": 15.0, "type": "gasp"}, {"start_s": 16.6, "end_s": 17.2, "type": "gasp"}, {"start_s": 18.3, "end_s": 18.7, "type": "gasp"}, {"start_s": 19.4, "end_s": 19.8, "type": "gasp"}], "overall_note": "Several burst events in the second half directly overlap spoken words (e.g., 18.72 to 19.32 covering 'Damn it') rather than true pauses, and some segments in the panic phase are misclassified with numbness/indifference/metallic tags."}, "usage": {"promptTokenCount": 7732, "candidatesTokenCount": 1328, "totalTokenCount": 9060, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 518}, {"modality": "TEXT", "tokenCount": 7214}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.010779, "model_version": "gemini-3.8-flash", "response_id": "6GrLas72GI_5nsEPmOu4KA", "weighted_score": 3.3000000000000003, "annotation_sha256": "3a8152fd247e46859c4d15f4125346f8c17df43611512bc63f0718f68a5e484e", "audio_sha256": "a358b434cfb6489894decdeb8c2886c3f74508ba8dec22113a4ba403262bcec9", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-17663", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 1, "burst_timing_fit": 1, "event_precision": 1, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 2, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 2, "note": "Spoken word 'Oh'. Tagged as very jerky, but it is a single isolated syllable."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Spoken word 'Huh.' followed by a quiet laugh/breath."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 2, "note": "Splits single clause artificially on 'I'. Rating of extreme amazement is an overstatement."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery is conversational admission, not extreme amazement."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 3, "note": "Expresses qualification and doubt reasonably well."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 2, "note": "Isolated conjunction 'but' with trailing pause/breath."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 3, "note": "Casual concession fits the doubt/skepticism tag somewhat."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 2, "note": "Tagged as very apathy, but delivery is ironic/rueful realization."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Single word segment 'Look' from an unnatural phrase chop."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 2, "note": "Extremely brief chop on 'just' (0.04s) is broken timing."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Part of 'forget I said that'."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 2, "note": "Final word 'that.' followed by breath, unnaturally fragmented."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 3, "note": "Clear, grounded conversational turn yielding to Dave."}], "audible_events": [{"start_s": 1.25, "end_s": 1.7, "type": "laughter"}, {"start_s": 4.15, "end_s": 4.5, "type": "breath"}, {"start_s": 7.8, "end_s": 8.35, "type": "breath"}, {"start_s": 16.2, "end_s": 16.85, "type": "sigh"}], "overall_note": "The script contains excessive hallucinated and overlapping burst events, including classifying speech words ('Oh') as bursts and multiplying chuckle events across 0.6s to 1.76s. Sentences are also overly fragmented into unnatural single-word chunks."}, "usage": {"promptTokenCount": 6534, "candidatesTokenCount": 960, "totalTokenCount": 7494, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 6022}, {"modality": "AUDIO", "tokenCount": 512}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.0085005, "model_version": "gemini-3.8-flash", "response_id": "7mrLaqLqO8i7vdIPzIWUiAs", "weighted_score": 2.9000000000000004, "annotation_sha256": "5ed9f74bf3806faa3d459ca0a5a2d25197dc4c439fdc1a74d9d583ada8cdeb36", "audio_sha256": "148b64f34dc0121d0f9fa72f0e3e81088f265ef45a15393a59ed7134b419c260", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-17999", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Captures the bitter, exasperated opening well."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Resentment fits the clipped, tense delivery."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Word 'ready' is spoken firmly; note that the sigh actually starts right after it around 8.8s rather than on the word itself."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 3, "note": "Tone softens to reflective/pondering; segment timing overlaps with the preceding audible sigh."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Pensive, slightly subdued delivery matches well."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 3, "note": "Gentle, nostalgic teasing is audible."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Affectionate memory, followed by a noticeable sigh in the pause."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, breathy resentment is accurate."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 3, "note": "Whispered completion of the phrase."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Vulnerable and conflicted rather than romantic 'butterflies in the stomach'."}], "audible_events": [{"start_s": 8.85, "end_s": 9.92, "type": "sigh"}, {"start_s": 19.15, "end_s": 20.35, "type": "sigh"}, {"start_s": 22.85, "end_s": 23.35, "type": "breath"}], "overall_note": "The pipeline double-counted single sighs by producing overlapping duplicate burst events (events 0000/0001 and 0002/0003 cover the same actual sighs around 8.9-9.9s and 19.2-20.3s). Segment timestamps also incorrectly subsume burst pauses directly into speech segments."}, "usage": {"promptTokenCount": 5575, "candidatesTokenCount": 820, "totalTokenCount": 6395, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 4890}, {"modality": "AUDIO", "tokenCount": 685}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00725625, "model_version": "gemini-3.8-flash", "response_id": "72rLaquJCKP5nsEPpP34kAM", "weighted_score": 3.35, "annotation_sha256": "b2f2a3429ca0547112738457fdcec378127b5d63ae06539342eb820712d430c1", "audio_sha256": "34712fdd83191c2fc961ee30f961ba0022873e3e00f57b2298a35617901f4500", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-18040", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 4, "burst_timing_fit": 4, "event_precision": 4, "event_coverage": 4, "transcript_fidelity": 3, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone is serious rather than an existential void."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Serious emphasis rather than audible boredom."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Firm delivery rather than boredom."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Firm emphasis rather than boredom."}, {"segment_id": "segment-005", "emotion_fit": 2, "delivery_fit": 3, "note": "Solemn delivery rather than gladness."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "Solemn tone rather than gladness."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 3, "note": "Spoken text says jury instead of Jerry."}, {"segment_id": "segment-008", "emotion_fit": 2, "delivery_fit": 3, "note": "Firm command rather than numbness."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 3, "note": "Pace is steady rather than accelerating."}], "audible_events": [], "overall_note": "Accurate overall performance description, but local emotion tags like boredom and gladness mischaracterize the serious delivery, and jury was misheard as Jerry."}, "usage": {"promptTokenCount": 4562, "candidatesTokenCount": 581, "totalTokenCount": 5143, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 567}, {"modality": "TEXT", "tokenCount": 3995}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00560025, "model_version": "gemini-3.8-flash", "response_id": "8GrLatmdKeXpnsEPk97E-AM", "weighted_score": 3.5, "annotation_sha256": "139351a502aa6663e8ac588d6b47f614a5b11e547565c8b447b1e18cbc2d2784", "audio_sha256": "c896d5aa4f4aff5b27a83a070fcd736b076661044e5df0384a06f7c77be60273", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-18796", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 4, "burst_description_fit": 4, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Well matched; the opening delivery is clear, thoughtful, and reflective."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Delivery fits well, though 'foreboding' / 'very negative' is slightly overstated for this reflective observation."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Accurately captures the disdainful, cynical tone and clean acoustic profile."}, {"segment_id": "segment-004", "emotion_fit": 3, "delivery_fit": 4, "note": "'Insensitivity' is a slight mischaracterization of the tone, which is dismissive and quiet."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 3, "note": "'Stoicism' does not fit; the speaker sounds startled and attentive after hearing something."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Perplexity and naturalistic questioning delivery are accurate."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Segment boundaries are heavily fragmented around the gasp and struggle; burnout tag does not capture acute panic."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, breathy struggle to breathe is represented adequately."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Helpless, breathless whisper-talk matches well."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Fits the breathless, terrified realization well."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Captures the acute distress and vulnerability."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Strained, choked delivery accurately reflects the tagging."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Final breathless resignation is captured appropriately."}], "audible_events": [{"start_s": 9.54, "end_s": 10.15, "type": "gasp"}, {"start_s": 13.92, "end_s": 14.52, "type": "gasp"}, {"start_s": 15.35, "end_s": 15.82, "type": "pant"}, {"start_s": 17.48, "end_s": 18.02, "type": "gasp"}, {"start_s": 19.55, "end_s": 20.2, "type": "gasp"}, {"start_s": 20.4, "end_s": 20.9, "type": "pant"}, {"start_s": 21.22, "end_s": 21.8, "type": "gasp"}, {"start_s": 22.95, "end_s": 23.55, "type": "groan"}], "overall_note": "The script breaks up words and overlapping breath events heavily in the latter half. Several burst annotations overlap with spoken words or are redundant duplicates (such as multiple overlapping breaths around 16.5-18.0s and 22.6-23.5s)."}, "usage": {"promptTokenCount": 6815, "candidatesTokenCount": 1110, "totalTokenCount": 7925, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 616}, {"modality": "TEXT", "tokenCount": 6199}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00927375, "model_version": "gemini-3.8-flash", "response_id": "8WrLapDoMJC7nsEPrsKN0Q0", "weighted_score": 3.6500000000000004, "annotation_sha256": "c64ef3c06de3708c43f579d6cad666c67d733700a3a4e3cb2bb45fbceca54866", "audio_sha256": "c7e8384ffb15de96a06ae46e58816a93a05a94ea0d89bd388f5155d510e68301", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-18876", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 2, "burst_timing_fit": 2, "event_precision": 2, "event_coverage": 3, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 3}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Hey is delivered softly and intimately, though labelling it as extremely weariness is somewhat exaggerated."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Soft and quiet delivery matches well, mild emotional fatigue."}, {"segment_id": "segment-003", "emotion_fit": 2, "delivery_fit": 3, "note": "Labelled as emotional blunting, but the voice sounds tender, vulnerable, and regretful rather than emotionally blunt."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Craving/longing fits the context and delivery well."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 4, "note": "Tags shyness/embarrassment, whereas the audible affect is more sorrowful regret and vulnerability."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 4, "note": "Tagging shyness is slightly off; it is sincere and emotionally warm pride."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Brief whisper-spoken tag 'infatuation' is a bit overly specific, but fits the tender tone."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Guilt tag accurately reflects the delivery of the apology."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Tender and reassuring tone, weariness is moderately present."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Stoicism tag is reasonable for 'I'm okay'."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 3, "note": "Emotional blunting and dissociation do not quite match the intimate, sincere tone."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 4, "note": "Short whispery connector word."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Comfort, warmth, and relief fit the tender conclusion."}], "audible_events": [{"start_s": 0.05, "end_s": 0.65, "type": "breath"}, {"start_s": 1.15, "end_s": 1.75, "type": "breath"}, {"start_s": 4.95, "end_s": 5.55, "type": "breath"}, {"start_s": 8.1, "end_s": 9.55, "type": "sigh"}, {"start_s": 11.85, "end_s": 12.75, "type": "breath"}, {"start_s": 15.5, "end_s": 16.35, "type": "breath"}, {"start_s": 19.0, "end_s": 20.3, "type": "sigh"}, {"start_s": 25.2, "end_s": 26.6, "type": "sigh"}], "overall_note": "The burst event list contains redundant duplicate events that heavily overlap each other (e.g., pairs of near-identical sighs at ~8.5-9.5s, ~19-20.5s, and ~25.5-26.7s), resulting in degraded burst precision and timing scores despite the sound events actually being real sigh/breath releases."}, "usage": {"promptTokenCount": 6636, "candidatesTokenCount": 1133, "totalTokenCount": 7769, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 715}, {"modality": "TEXT", "tokenCount": 5921}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00922575, "model_version": "gemini-3.8-flash", "response_id": "9WrLaqzDOOLrkdUPlPTquA8", "weighted_score": 3.1500000000000004, "annotation_sha256": "2404d75ccb1930d7fdd090b5dc10c1d5ad761d45836359a2c9b8ecf060133d21", "audio_sha256": "7ea92d63757870df2d98ef5ded4e0ab61eb1c4901f432991a0b69b0f85a48167", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "en-19162", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 2, "event_precision": 2, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 3, "note": "Clear transmission call sign opener, calm and serious."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivered slowly and with deliberate weight."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Low, sober delivery, appropriate."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Clear, somber radio transmission tone."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 2, "note": "Start time includes a substantial breath before the word 'Repeating'."}, {"segment_id": "segment-006", "emotion_fit": 3, "delivery_fit": 3, "note": "Steady and fatigued pace."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Reflective and quiet delivery fits contemplation."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Subdued afterthought, natural delivery."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Short, dry statement, not particularly accelerating."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Weary and resigned tone fits well."}, {"segment_id": "segment-011", "emotion_fit": 3, "delivery_fit": 3, "note": "Transcript mishears 'traffic jams' as 'traffic, James'."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft nostalgic reflection delivered with quiet weariness."}, {"segment_id": "segment-013", "emotion_fit": 3, "delivery_fit": 2, "note": "Start overlaps with a breath; delivery is inquiring rather than purely non-narrative."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 3, "note": "Gasped startle before the spoken utterance; timings overlap duplicate burst descriptions."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 3, "note": "Confused and startled tone."}, {"segment_id": "segment-016", "emotion_fit": 4, "delivery_fit": 3, "note": "Tense and urgent question."}, {"segment_id": "segment-017", "emotion_fit": 4, "delivery_fit": 4, "note": "Urgent and pleading tone."}, {"segment_id": "segment-018", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet pleading desperation."}], "audible_events": [{"start_s": 8.7, "end_s": 9.9, "type": "sigh/breath"}, {"start_s": 21.0, "end_s": 21.8, "type": "breath"}, {"start_s": 28.5, "end_s": 29.0, "type": "gasp"}], "overall_note": "The script hallucinates multiple duplicate breath events in overlapping time windows (around 8.3-10.2s and 28.4-29.4s). Transcript error at 00:23 ('traffic jams' transcribed as 'traffic, James'). Overall acoustic description is solid."}, "usage": {"promptTokenCount": 8199, "candidatesTokenCount": 1100, "totalTokenCount": 9299, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 853}, {"modality": "TEXT", "tokenCount": 7346}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01027425, "model_version": "gemini-3.8-flash", "response_id": "9mrLavrdIeGhnsEP2JavoAE", "weighted_score": 3.3000000000000003, "annotation_sha256": "276a2cfc6ce583b5d2908e7606b662b640187074f26878e6e933da8f5a47ee30", "audio_sha256": "f4711d9c441ca75bb18ea3490092b4e757fa63e5cd49ddcb55aba53b8a2ac673", "rubric_id": "humanness-annotator-audio-review-v1", "language": "en"}
{"id": "de-00093", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 1, "delivery_fit": 3, "note": "The speaker sounds stern and reproachful, not expressing longing or desire."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Tone is cold, hurt, and confrontational, not hopeful anticipation."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Delivery falters with confusion and sudden hesitation as labeled."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Bewildered and concerned question matching the delivery tags well."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet shocked whisper captures the sudden realization."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, stunned delivery fits the realization well."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery is soft, distressed, and horrified rather than smooth acerbity."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "A gasping whisper of shock rather than simple weariness."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Desperate, pleading whisper fits the tags well."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 3, "note": "Transcript mishears 'weinen' as 'weiten'; tone is tearful and pleading."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 3, "note": "Reassuring whisper, quiet and gentle."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Affectionate comforting whisper fits the tags reasonably."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Sorrowful, apologetic whisper matches shame and meek delivery."}], "audible_events": [{"start_s": 6.7, "end_s": 7.0, "type": "gasp"}, {"start_s": 9.8, "end_s": 10.5, "type": "gasp"}, {"start_s": 17.0, "end_s": 17.4, "type": "breath"}, {"start_s": 18.0, "end_s": 18.3, "type": "breath"}, {"start_s": 19.3, "end_s": 19.8, "type": "sigh"}, {"start_s": 24.0, "end_s": 24.6, "type": "sob"}], "overall_note": "The monologue shifts from cold confrontation to broken, whispered distress. In early segments, automated emotional tags ('desire', 'anticipation') completely miss the accusatory anger. Several burst events over-segment continuous speech or contain normal syllable releases, but captured gasps and sobs are genuinely present. Transcript contains a typo ('weiten' instead of 'weinen')."}, "usage": {"promptTokenCount": 6657, "candidatesTokenCount": 1031, "totalTokenCount": 7688, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 670}, {"modality": "TEXT", "tokenCount": 5987}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.008859, "model_version": "gemini-3.8-flash", "response_id": "-GrLar60NoWAxs0P8_zh2Qg", "weighted_score": 3.45, "annotation_sha256": "4856a0ae3abd48a87e84e645650cfec1767d343d12ea3d47609e1c06f117b3ed", "audio_sha256": "aec552a9ddc4077ef1414f3ce404d95755f065b52b2443e09b37291601265eec", "rubric_id": "humanness-annotator-audio-review-v1", "language": "de"}
{"id": "de-00725", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 4, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 4, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 5, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, breathy delivery fits well."}, {"segment_id": "segment-002", "emotion_fit": 4, "delivery_fit": 4, "note": "Short whispered word with audible inhalation."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Labored, strained whisper fits the exhaustion tags."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Displays distress and vulnerability as labeled."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, pain-tinged delivery matches well."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Delivery fits the physical pain context."}, {"segment_id": "segment-007", "emotion_fit": 4, "delivery_fit": 4, "note": "Despairing and helpless delivery matches tags."}, {"segment_id": "segment-008", "emotion_fit": 3, "delivery_fit": 3, "note": "Delivery remains strained and breathless rather than evenly paced."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, transitioning tone matches reasonably well."}, {"segment_id": "segment-010", "emotion_fit": 4, "delivery_fit": 4, "note": "Sense of mild release matches solace/relief tags."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet, gentle sad whisper."}, {"segment_id": "segment-012", "emotion_fit": 4, "delivery_fit": 4, "note": "Very short transitional segment, delivery fits."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Very quiet, still whispered delivery."}, {"segment_id": "segment-014", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, hushed ASMR-like delivery fits."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Short whisper continuation fits."}, {"segment_id": "segment-016", "emotion_fit": 4, "delivery_fit": 4, "note": "Quiet, contemplative, intimate finish."}], "audible_events": [{"start_s": 0.0, "end_s": 0.85, "type": "gasp"}, {"start_s": 1.7, "end_s": 2.5, "type": "inhalation"}, {"start_s": 2.6, "end_s": 3.3, "type": "gasp"}, {"start_s": 5.0, "end_s": 5.7, "type": "breath"}, {"start_s": 10.0, "end_s": 10.9, "type": "groan"}, {"start_s": 16.8, "end_s": 18.5, "type": "sigh"}, {"start_s": 20.0, "end_s": 20.7, "type": "inhalation"}, {"start_s": 22.8, "end_s": 23.8, "type": "sigh"}, {"start_s": 24.8, "end_s": 25.6, "type": "inhalation"}], "overall_note": "The global description captures the whispered, breathless, dramatic physical distress monologue accurately. However, several burst events overlap heavily with each other or directly over spoken speech segments rather than pauses."}, "usage": {"promptTokenCount": 8480, "candidatesTokenCount": 1161, "totalTokenCount": 9641, "promptTokensDetails": [{"modality": "AUDIO", "tokenCount": 834}, {"modality": "TEXT", "tokenCount": 7646}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01071375, "model_version": "gemini-3.8-flash", "response_id": "-WrLatPhJJfOnsEP9dOSoA8", "weighted_score": 3.75, "annotation_sha256": "fbdbcf8f0c8c465312990b22438d1e73740d5b64de27eef7f0a70e980197e2b0", "audio_sha256": "91abd4a6ecec36d54371212bb8e91b50cd370d1f1c7ff6d88b9da7fc9904483d", "rubric_id": "humanness-annotator-audio-review-v1", "language": "de"}
{"id": "de-01381", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 3, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 2, "burst_timing_fit": 2, "event_precision": 2, "event_coverage": 3, "transcript_fidelity": 5, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Tone is soft and melancholic rather than purely affectionate."}, {"segment_id": "segment-002", "emotion_fit": 3, "delivery_fit": 4, "note": "Breathy, wistful delivery fits well."}, {"segment_id": "segment-003", "emotion_fit": 4, "delivery_fit": 4, "note": "Yearning and sadness come through accurately."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged with liberation/relief, but tone remains sad and heavy."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Sadness tag fits the vulnerable delivery."}, {"segment_id": "segment-006", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, subdued whisper-like tone correctly captured."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 3, "note": "Brief completion word continuing the previous segment's sad tone."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 3, "note": "Conveys heartbreak and sorrow rather than mere longing."}, {"segment_id": "segment-009", "emotion_fit": 3, "delivery_fit": 3, "note": "Awe is overstated; the delivery is contemplative."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Gentle appreciation and wistfulness present, but awe is exaggerated."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Helplessness fits the quiet resigned tone."}, {"segment_id": "segment-012", "emotion_fit": 3, "delivery_fit": 3, "note": "Short rhetorical tag matching previous segment."}, {"segment_id": "segment-013", "emotion_fit": 2, "delivery_fit": 4, "note": "Tagged with envy, but the emotion is straightforward grief and sorrow."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 4, "note": "Also tagged with envy; speech sounds mournful and reflective."}, {"segment_id": "segment-015", "emotion_fit": 2, "delivery_fit": 3, "note": "Tagged as insensitivity/numbness, but delivery remains tender and emotional."}], "audible_events": [{"start_s": 0.0, "end_s": 0.8, "type": "sigh"}, {"start_s": 6.8, "end_s": 7.7, "type": "sigh"}, {"start_s": 13.6, "end_s": 14.5, "type": "sigh"}, {"start_s": 18.6, "end_s": 19.3, "type": "sigh"}, {"start_s": 25.0, "end_s": 26.2, "type": "sigh"}], "overall_note": "The speaker delivers a melancholic, intimate monologue in German. The annotation over-identifies nonverbal burst events, hallucinating non-existent chuckles and sniffling catches where only sighs and pauses exist, and mislabels grief as 'envy' and 'insensitivity'."}, "usage": {"promptTokenCount": 7682, "candidatesTokenCount": 1055, "totalTokenCount": 8737, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 6870}, {"modality": "AUDIO", "tokenCount": 812}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.00971775, "model_version": "gemini-3.8-flash", "response_id": "_mrLauKHBdX6xs0P5uTfyQ0", "weighted_score": 2.9000000000000004, "annotation_sha256": "c07edc7fe015d29795aaf7fb669bf982916d2b60e1b1985cf238c8b24368a096", "audio_sha256": "a01de9a40010670920da01124a9c48ec841db80653e9eacc4b25a86596d69f1a", "rubric_id": "humanness-annotator-audio-review-v1", "language": "de"}
{"id": "de-01938", "answer": {"ratings": {"global_caption_fidelity": 4, "global_emotion_fit": 4, "sentence_emotion_fit": 3, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 4, "transcript_fidelity": 4, "speech_timing_fit": 4, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 3, "delivery_fit": 4, "note": "Spoken tenderly and softly, 'slightly burnout' is an odd framing."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "The speaker sounds tender and pained, not irritable."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Hushed, intimate observation; 'curiosity' is slightly off but acceptable."}, {"segment_id": "segment-004", "emotion_fit": 4, "delivery_fit": 4, "note": "Very breathy and desperate whisper fits well."}, {"segment_id": "segment-005", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, whispered delivery fits 'nicht weggehen'."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 3, "note": "Not bored; gentle and sorrowful."}, {"segment_id": "segment-007", "emotion_fit": 2, "delivery_fit": 4, "note": "Soft and whispered, but 'indifference' completely misses the intimacy."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Whispered, sorrowful relief/helplessness fits well."}, {"segment_id": "segment-009", "emotion_fit": 4, "delivery_fit": 4, "note": "Gentle, whispered fading delivery matches."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 4, "note": "Quiet awe/tenderness rather than standard surprise."}, {"segment_id": "segment-011", "emotion_fit": 4, "delivery_fit": 4, "note": "Pain and distress are audible here."}, {"segment_id": "segment-012", "emotion_fit": 2, "delivery_fit": 3, "note": "A quiet sigh/word, definitely not insensitive."}, {"segment_id": "segment-013", "emotion_fit": 4, "delivery_fit": 4, "note": "Intimate, tender emotional grounding."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 2, "note": "Tagged as cold and detached, but the voice remains warm, broken, and intimate."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Soft, grateful, whispered sign-off."}], "audible_events": [{"start_s": 1.25, "end_s": 1.9, "type": "breath"}, {"start_s": 6.8, "end_s": 7.35, "type": "breath"}, {"start_s": 8.1, "end_s": 8.75, "type": "sigh"}, {"start_s": 12.35, "end_s": 13.1, "type": "breath"}, {"start_s": 17.5, "end_s": 18.25, "type": "sigh"}, {"start_s": 22.2, "end_s": 22.85, "type": "sigh"}, {"start_s": 24.6, "end_s": 25.4, "type": "breath"}, {"start_s": 28.3, "end_s": 28.8, "type": "breath"}], "overall_note": "The global description captures the intimate, whispered, ASMR-like German performance nicely. However, several segment-level emotion tags (e.g., irritability, indifference, coldness/detachment) are distinctly inaccurate given the persistently tender, mournful, and affectionate context. In addition, duplicate overlapping breath bursts were artificially created in multiple pauses."}, "usage": {"promptTokenCount": 7868, "candidatesTokenCount": 1167, "totalTokenCount": 9035, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 7115}, {"modality": "AUDIO", "tokenCount": 753}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01027725, "model_version": "gemini-3.8-flash", "response_id": "_mrLatfYNeHjkdUPxrn0IQ", "weighted_score": 3.45, "annotation_sha256": "a0c4b9805ca9b285adf2b2286f3d785b98c0a42b8f6b83c73d384736959a4f05", "audio_sha256": "858c66e837479064b32eeeda2b2bba7302aed945c5cb34160ddbc1e2ab01e862", "rubric_id": "humanness-annotator-audio-review-v1", "language": "de"}
{"id": "de-02578", "answer": {"ratings": {"global_caption_fidelity": 3, "global_emotion_fit": 2, "sentence_emotion_fit": 2, "utterance_talking_style_fit": 4, "sentence_delivery_fit": 3, "burst_description_fit": 3, "burst_timing_fit": 3, "event_precision": 3, "event_coverage": 3, "transcript_fidelity": 4, "speech_timing_fit": 3, "readability": 4}, "sentence_reviews": [{"segment_id": "segment-001", "emotion_fit": 2, "delivery_fit": 3, "note": "Whispered and low in intensity rather than fast or clearly enjoyable."}, {"segment_id": "segment-002", "emotion_fit": 2, "delivery_fit": 3, "note": "Short whispered syllable, not accelerating."}, {"segment_id": "segment-003", "emotion_fit": 3, "delivery_fit": 3, "note": "Cold whisper fits well, though not overly thin-chest."}, {"segment_id": "segment-004", "emotion_fit": 2, "delivery_fit": 3, "note": "Delivered as a strained whisper rather than an obvious triumph."}, {"segment_id": "segment-005", "emotion_fit": 3, "delivery_fit": 4, "note": "Breathy and whispered delivery fits well."}, {"segment_id": "segment-006", "emotion_fit": 2, "delivery_fit": 2, "note": "Segment is an isolated syllable with questionable boundary separation."}, {"segment_id": "segment-007", "emotion_fit": 3, "delivery_fit": 4, "note": "Tense and breathy whisper matches the frustrated line."}, {"segment_id": "segment-008", "emotion_fit": 4, "delivery_fit": 4, "note": "Fading whisper with fatigued quality matches speech."}, {"segment_id": "segment-009", "emotion_fit": 2, "delivery_fit": 4, "note": "Intimate ASMR whisper, but framing as carnal desire is overstated given the dark context."}, {"segment_id": "segment-010", "emotion_fit": 3, "delivery_fit": 3, "note": "Quiet, intense whisper rather than loud tension."}, {"segment_id": "segment-011", "emotion_fit": 2, "delivery_fit": 3, "note": "Whispered and bitter/ironic rather than bliss."}, {"segment_id": "segment-012", "emotion_fit": 2, "delivery_fit": 4, "note": "Close-mic whisper is accurate, romantic desire is an unfitting interpretation."}, {"segment_id": "segment-013", "emotion_fit": 3, "delivery_fit": 3, "note": "Flat whispered single word."}, {"segment_id": "segment-014", "emotion_fit": 2, "delivery_fit": 4, "note": "Whispered intimate delivery, but devotion does not match the bitter tone."}, {"segment_id": "segment-015", "emotion_fit": 4, "delivery_fit": 4, "note": "Breathy, whispered delivery conveying exhaustion fits well."}, {"segment_id": "segment-016", "emotion_fit": 3, "delivery_fit": 4, "note": "Detached whisper fits the utterance."}, {"segment_id": "segment-017", "emotion_fit": 3, "delivery_fit": 3, "note": "Short trailing whisper."}, {"segment_id": "segment-018", "emotion_fit": 3, "delivery_fit": 3, "note": "Final fading whisper."}], "audible_events": [{"start_s": 1.15, "end_s": 1.68, "type": "breath"}, {"start_s": 3.25, "end_s": 3.95, "type": "breath"}, {"start_s": 5.2, "end_s": 5.8, "type": "breath"}, {"start_s": 6.9, "end_s": 7.8, "type": "breath"}, {"start_s": 10.4, "end_s": 11.2, "type": "breath"}, {"start_s": 20.15, "end_s": 20.75, "type": "breath"}, {"start_s": 26.8, "end_s": 27.6, "type": "breath"}, {"start_s": 33.3, "end_s": 34.2, "type": "breath"}], "overall_note": "The speech is delivered in a sustained close-up ASMR whisper. The prompt invents a story about a hot beverage and erotic desire ('carnal desire', 'romantic desire', 'bliss'), when the tone and text clearly point to an injured/bitter reflection (blood in the mouth tasting like copper/defeat). Multiple burst event annotations duplicate overlapping intervals."}, "usage": {"promptTokenCount": 8700, "candidatesTokenCount": 1284, "totalTokenCount": 9984, "promptTokensDetails": [{"modality": "TEXT", "tokenCount": 7795}, {"modality": "AUDIO", "tokenCount": 905}], "serviceTier": "standard"}, "estimated_list_price_usd": 0.01134, "model_version": "gemini-3.8-flash", "response_id": "AmvLaobpAYfFnsEPkqHPAQ", "weighted_score": 2.85, "annotation_sha256": "25b0dc343b470db5b78cd8cfe91b2225193387eed6d42bb6335b56ada570f355", "audio_sha256": "81b2176510d543bc909e1167a2382b608beecee3c15f0968d52daf3806e576c8", "rubric_id": "humanness-annotator-audio-review-v1", "language": "de"}