{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Two excerpts of the same scene from two sung story-songs (Attachment 1 English inspiration, Attachment 2 Ukrainian candidate): the heroine waits for her daughter after dance class, meets an older woman with a smooth neck, asks what she uses, gets asked back, lists her products, is told to stop; compare how the question is sung (does the melody play with it), the laugh, the list, the stop, and whether the thoughts are separated by rests. Give timed landmarks (attachment, local seconds, quoted words). Then: restsHeard[{localSeconds,afterWords}], mechanismsMatched[{mechanism,attachment1,attachment2,matched(boolean)}], defects[{localSeconds,words,problem,severity}], wordsMisheardOrUnclear[], whatCandidateDoesWell[], remainingGaps[]. Return ONLY JSON (no prose outside JSON), <=1900 words, English. Required keys: mediaAccess(boolean), audioAccess(boolean), attachmentsHeard[{attachment,firstWordsHeard,lastWordsHeard,durationEstimateSeconds}], then the analysis keys listed. No script is supplied: quote only words you actually hear and mark uncertain words with (?). Use attachment number plus LOCAL seconds of that attachment. Do not rate quality with numbers, do not assume any language or attachment is better a priori, do not reward louder mastering, more notes or softer timbre. Identify concrete mechanisms, not taste."
        },
        {
          "text": "Attachment 1: Attachment 1; parent targ.mp4; EXACT parent range [79.7, 108.0]; 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 gopure-targ-uk-master.wav; EXACT parent range [69.5, 112.48]; 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"
    }
  }
}