Seed Audio 1.0：支援預設聲音與參考音訊的文字轉音訊模型和 API | RunComfy

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/bytedance/seed-audio-1.0/text-to-audio \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "Welcome back to the late-night show. Settle in, pour something warm, and let's ease into the next track together."
  }'

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

{
  "type": "object",
  "title": "輸入結構",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "title": "提示詞",
      "description": "要合成的文字。請依序使用 @Audio1、@Audio2、@Audio3 引用參考音訊片段。",
      "type": "string",
      "default": "Welcome back to the late-night show. Settle in, pour something warm, and let's ease into the next track together."
    },
    "voice": {
      "title": "聲音",
      "description": "用於合成的預設聲音。",
      "type": "string",
      "enum": [
        "vivi_mixed_en_zh_ja_es_id",
        "mindy_en_es_id_pt_zh",
        "kian_en_zh",
        "cedric_en_zh",
        "sophie_en_zh",
        "jean_en_zh",
        "magnus_en_zh",
        "mabel_en_zh",
        "nadia_en_zh",
        "opal_en_zh",
        "pearl_en_zh",
        "quentin_en_zh",
        "corinne_mixed_en_zh",
        "esther_mixed_en_zh",
        "lyla_mixed_en_zh",
        "tracy_es_zh",
        "sandy_es_mixed_en_zh",
        "felix_zh",
        "celeste_zh",
        "monkey_king_zh"
      ],
      "default": "vivi_mixed_en_zh_ja_es_id"
    },
    "audio_urls": {
      "title": "參考音訊 URL",
      "description": "最多可加入 3 段參考音訊，並在提示詞中以 @Audio1、@Audio2、@Audio3 引用。每段最長 30s、最大 10MB，支援 wav/mp3/pcm/ogg_opus。",
      "type": "array",
      "items": {
        "type": "string",
        "format": "audio_uri"
      },
      "maxItems": 3
    },
    "image_url": {
      "title": "參考圖片 URL",
      "description": "一張參考圖片（jpeg/png/webp，最大 10MB）。不能與參考音訊同時使用。",
      "type": "string"
    },
    "output_format": {
      "title": "輸出格式",
      "description": "輸出音訊的容器格式。",
      "type": "string",
      "enum": [
        "wav",
        "mp3",
        "pcm",
        "ogg_opus"
      ],
      "default": "mp3"
    },
    "sample_rate": {
      "title": "取樣率 (Hz)",
      "description": "輸出音訊的取樣率，以 Hz 為單位。",
      "type": "integer",
      "enum": [
        8000,
        16000,
        24000,
        32000,
        44100,
        48000
      ],
      "default": 24000
    },
    "speed": {
      "title": "語速",
      "description": "朗讀速度。1.0 為正常速度，0.5 為半速，2.0 為雙倍速度。",
      "type": "number",
      "minimum": 0.5,
      "maximum": 2,
      "default": 1
    },
    "volume": {
      "title": "音量",
      "description": "輸出音量。1.0 為正常音量，0.5 為一半，2.0 為兩倍。",
      "type": "number",
      "minimum": 0.5,
      "maximum": 2,
      "default": 1
    },
    "pitch": {
      "title": "音高",
      "description": "以半音為單位調整聲音音高。0 為正常音高，-12 降低一個八度，12 提高一個八度。",
      "type": "integer",
      "minimum": -12,
      "maximum": 12,
      "default": 0
    }
  }
}