{
  "schema_version": "2.0",
  "experiment": "6-5",
  "generated_at_utc": "2026-07-30T04:47:32.164712+00:00",
  "command_scope": {
    "providers": [
      "fishaudio",
      "openai"
    ],
    "configurations": [
      {
        "name": "tts1-alloy-1.0",
        "provider": "openai",
        "model": "tts-1",
        "voice": "alloy",
        "speed": 1.0
      },
      {
        "name": "fishaudio-s1-clone",
        "provider": "fishaudio",
        "model": "s1",
        "voice": "6df3c1e14c9440e9ac978556536bf116",
        "speed": 1.0
      }
    ],
    "corpus_ids": [
      "num",
      "polyphone",
      "long",
      "emotion"
    ],
    "expected_records": 8,
    "direct_audio_judge": true,
    "optional_asr_enabled": false
  },
  "reference_audio": {
    "path": "../../../../chapter9/controllable-tts/reference_audio/neutral_normal_formal.mp3",
    "sha256": "2cf4c64bb8222399ab54c63cc41049c572ea5f1b819ffdcbc496014daae004c0"
  },
  "rubric_dimensions": [
    "准确性",
    "自然度",
    "情感表达",
    "音色一致性"
  ],
  "completion": {
    "successful_records": 8,
    "direct_audio_four_dimension_records": 8,
    "expected_records": 8,
    "all_cells_complete": true,
    "multi_provider": true,
    "manuscript_core_complete": true
  },
  "records": [
    {
      "config": "tts1-alloy-1.0",
      "sample": "num",
      "challenge": "数字/百分比/日期",
      "provider": "openai",
      "ok": true,
      "error": null,
      "audio_path": "tts1-alloy-1.0__num.mp3",
      "audio_sha256": "954eca94164d5af7d4a849def397e16a192d22a86168fab86f76ccd2443fb3ed",
      "audio_bytes": 132960,
      "duration": 6.648,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.061371841155235,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 3,
        "音色一致性": 2
      },
      "reasons": {
        "准确性": "合成语音准确无误地朗读了原文，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿，特别是在数字和百分点的表达上。",
        "情感表达": "合成语音的语调和语速基本符合中性情感，但缺乏参考说话人语音中的自然感和情感表达。",
        "音色一致性": "合成语音的音色与参考说话人语音存在明显差异，音色不一致。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "tts1-alloy-1.0",
      "sample": "polyphone",
      "challenge": "多音字（行/长/重/还）",
      "provider": "openai",
      "ok": true,
      "error": null,
      "audio_path": "tts1-alloy-1.0__polyphone.mp3",
      "audio_sha256": "fa6e6ca29a3d17d33167c04c32b132d6aee2cb406d2acbf7bbeb13529af98abb",
      "audio_bytes": 130560,
      "duration": 6.528,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.28921568627451,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "合成语音与原文完全一致，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿和重音。",
        "情感表达": "语调和语速基本符合中性情感，但强调稍显不足。",
        "音色一致性": "合成语音的音色与参考说话人有一定差异，但总体还算接近。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "tts1-alloy-1.0",
      "sample": "long",
      "challenge": "长句/新闻文体",
      "provider": "openai",
      "ok": true,
      "error": null,
      "audio_path": "tts1-alloy-1.0__long.mp3",
      "audio_sha256": "c04786022e111c49f635eb361cb4cae3b786334291af86f7f36e69fff7909d1a",
      "audio_bytes": 273600,
      "duration": 13.68,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.45906432748538,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "合成语音与原文完全一致，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿和重音。",
        "情感表达": "语调和语速基本符合中性情感，但强调不够明显。",
        "音色一致性": "合成语音的音色与参考说话人有一些差异，但总体还算接近。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "tts1-alloy-1.0",
      "sample": "emotion",
      "challenge": "专有名词 + 感叹情感",
      "provider": "openai",
      "ok": true,
      "error": null,
      "audio_path": "tts1-alloy-1.0__emotion.mp3",
      "audio_sha256": "86215ce027003e1b0a721545b594ef0325745738a46bbf927a7843da3a15b514",
      "audio_bytes": 116160,
      "duration": 5.808,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 5.3374655647382925,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "没有漏读、错读、添读、数字、专名和多音字。",
        "自然度": "有一些机器感，但总体流畅度较好。",
        "情感表达": "语调和语速表现出兴奋，但强调不够明显。",
        "音色一致性": "音色与参考说话人有一些差异，但总体相似。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "fishaudio-s1-clone",
      "sample": "num",
      "challenge": "数字/百分比/日期",
      "provider": "fishaudio",
      "ok": true,
      "error": null,
      "audio_path": "fishaudio-s1-clone__num.mp3",
      "audio_sha256": "6e9717e58f422db10b8e9538aa3812de456a1dde4bd9028fde928c2eaac42ad3",
      "audio_bytes": 101981,
      "duration": 6.373813,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.236082859663439,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "合成语音准确无误地朗读了原文，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿和重音。",
        "情感表达": "合成语音的语调和语速基本符合中性情感，但强调不够明显。",
        "音色一致性": "合成语音的音色与参考说话人有一些差异，但总体还算相似。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "fishaudio-s1-clone",
      "sample": "polyphone",
      "challenge": "多音字（行/长/重/还）",
      "provider": "fishaudio",
      "ok": true,
      "error": null,
      "audio_path": "fishaudio-s1-clone__polyphone.mp3",
      "audio_sha256": "6bff6109ec7682f85680d8b60ea58dd48fbe5b3eeda59fb326d2288d250c85b5",
      "audio_bytes": 95293,
      "duration": 5.955813,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.701289311803443,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "合成语音与原文完全一致，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿和重音。",
        "情感表达": "语调和语速基本符合中性情感，但强调稍显不足。",
        "音色一致性": "合成语音的音色与参考说话人有一定差异，但总体还算接近。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "fishaudio-s1-clone",
      "sample": "long",
      "challenge": "长句/新闻文体",
      "provider": "fishaudio",
      "ok": true,
      "error": null,
      "audio_path": "fishaudio-s1-clone__long.mp3",
      "audio_sha256": "89542f05312bac767d5151f7552d0c75065cc7ecdf739dcc180b3c92a67b21c5",
      "audio_bytes": 206052,
      "duration": 12.87825,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.7366684137984585,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "合成语音与原文完全一致，没有漏读、错读、添读、数字、专名和多音字的问题。",
        "自然度": "合成语音流畅度较好，但有一些不自然的停顿和重音。",
        "情感表达": "合成语音的语调和语速基本符合中性情感，但缺乏一些细微的情感变化。",
        "音色一致性": "合成语音的音色与参考说话人有一些差异，但总体上还算相似。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    },
    {
      "config": "fishaudio-s1-clone",
      "sample": "emotion",
      "challenge": "专有名词 + 感叹情感",
      "provider": "fishaudio",
      "ok": true,
      "error": null,
      "audio_path": "fishaudio-s1-clone__emotion.mp3",
      "audio_sha256": "81608431645b08be6bf7171dbb250f391b1ba7f5714d535c0e2ce323d7f6ca29",
      "audio_bytes": 104488,
      "duration": 6.5305,
      "hypothesis": null,
      "cer": null,
      "asr_accuracy": null,
      "speed": 4.746956588316362,
      "scores": {
        "准确性": 5,
        "自然度": 4,
        "情感表达": 4,
        "音色一致性": 3
      },
      "reasons": {
        "准确性": "没有漏读、错读、添读、数字、专名和多音字。",
        "自然度": "有轻微的机器感，但总体流畅度较好。",
        "情感表达": "语调和语速表现出兴奋，但强调稍显不足。",
        "音色一致性": "音色与参考说话人有明显差异。"
      },
      "judge_model": "mistral/voxtral-small-latest",
      "evidence_mode": "direct-audio-with-reference",
      "judge_provider_attempts": [
        {
          "provider": "Mistral Voxtral API",
          "model": "voxtral-small-latest",
          "status": "ok",
          "attempts": 1
        }
      ]
    }
  ],
  "summary": [
    {
      "config": "fishaudio-s1-clone",
      "n_ok": 4,
      "n": 4,
      "cer": null,
      "asr_accuracy": null,
      "准确性": 5,
      "自然度": 4,
      "情感表达": 4,
      "音色一致性": 3
    },
    {
      "config": "tts1-alloy-1.0",
      "n_ok": 4,
      "n": 4,
      "cer": null,
      "asr_accuracy": null,
      "准确性": 5,
      "自然度": 4,
      "情感表达": 3.75,
      "音色一致性": 2.75
    }
  ]
}