{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Blind local AUDIO inspection. Attachments1–4 are candidate A: opening, practical pickup/dialogue, product/application, final coda through file end. Attachments5–6 are B opening and coda. Attachments7–8 are English original opening and pickup/dialogue. Local seconds reset for each clip; exact source ranges are given beside assets. No expected lyric sheet is provided. Transcribe actual Ukrainian words including brand/ingredients as heard; mark stressed vowel with an acute when reliable, alternative readings when uncertain. Do not guess a familiar skincare brand. Do not import the English source words into Ukrainian. Do NOT fill blanks from a story template.\nReturn ONLY JSON <=2400words: mediaAccess boolean,audioAccess boolean,clips:[{attachment,heardTextWithStress,uncertainWordsAndAlternatives,actualFirstSungWord,wordOnsetLocalSeconds,firstAudibleEvent,instrumentalPickupBeforeVoice,cutWordAtBoundary,actualWordAttacksAndReleases,melodicVsSpoken,pausesAndInstrumentAnswers}],openingDecisionAandB:{safeStartLocalSeconds,reason,uncertainty},candidateAWordShapeVsSource:{pickupAction,questionPlay,whereStillRounded},endingAandB:{completeFinalWords,voiceAndInstrumentTail,brandPhonetics,anyStressIssue},limits. Do not assume every clip starts on a word or first waveform peak is voice. Distinguish whole-take opening clips1/5/7 from clips cut in a phrase. A brand transcription in Latin can be correct; phonetic identity still needs actual listening. No numeric quality score and no owner approval.\nBlind auditory scope: actual-word-shape; selective-melodic-play; continuous-text-pressure; musical-responses-and-transitions. The source-bound plan was validated but its expected words are withheld from this review. Transcribe only what is audible, including uncertainties and alternative phonetic readings. Do not guess words from context or invent silence from a hold. No score or preference for softness is requested.\n"
        },
        {
          "text": "Attachment 1: Attachment 1; parent take_articulation01_1.mp3; EXACT parent range [0, 9]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 2: Attachment 2; parent take_articulation01_1.mp3; EXACT parent range [71, 96]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 3: Attachment 3; parent take_articulation01_1.mp3; EXACT parent range [103, 125]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 4: Attachment 4; parent take_articulation01_1.mp3; EXACT parent range [181, 209.988979]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 5: Attachment 5; parent take_articulation01_2.mp3; EXACT parent range [0, 9]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 6: Attachment 6; parent take_articulation01_2.mp3; EXACT parent range [180, 210.804979]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 7: Attachment 7; parent targ.mp4; EXACT parent range [0, 9]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        },
        {
          "text": "Attachment 8: Attachment 8; parent targ.mp4; EXACT parent range [79, 109]; local audio starts0. Use attachment number and local seconds, never concatenate timestamps. Fixed gain, no retiming."
        },
        {
          "inlineData": {
            "mimeType": "audio/mpeg",
            "data": "[base64 of frozen bytes; see inputs.json]"
          }
        }
      ]
    }
  ],
  "stream": true,
  "generationConfig": {
    "thinkingConfig": {
      "includeThoughts": false,
      "thinkingLevel": "high"
    }
  }
}