音色快速复刻

{
  "contentType": "application/json",
  "properties": {
    "accuracy": {
      "description": "ASR 相似度阈值，默认 0.7，范围 [0, 1]。",
      "type": "number",
      "x-i18n": {
        "en-US": {
          "description": "ASR similarity threshold, default 0.7, range [0, 1]."
        }
      }
    },
    "aigc_watermark": {
      "description": "是否在试听音频末尾添加音频节奏标识",
      "type": "boolean",
      "x-i18n": {
        "en-US": {
          "description": "Whether to add an audio rhythm identifier at the end of the preview audio"
        }
      }
    },
    "audio_data": {
      "description": "待复刻音频的 base64 音频。（audio_url 或 audio_data 至少传一个）",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "The base64 audio of the audio to be cloned. (At least one of audio_url or audio_data must be provided)"
        }
      }
    },
    "audio_url": {
      "description": "待复刻音频的 URL 地址（http/https 链接）。音频规范：mp3 / m4a / wav，建议时长 10 秒–5 分钟，大小 ≤ 20MB。",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "The URL address of the audio to be cloned (http/https link). Audio specifications: mp3/m4a/wav, recommended duration 10 seconds to 5 minutes, size ≤ 20MB."
        }
      }
    },
    "clone_prompt": {
      "description": "示例音频对象，增强相似度和稳定性 上传示例音频所得",
      "type": "object",
      "x-i18n": {
        "en-US": {
          "description": "Example audio object to enhance similarity and stability, obtained from the uploaded example audio"
        }
      }
    },
    "file_id": {
      "description": "待复刻音频的 file_id，通过文件上传接口获得。音频要求：mp3/m4a/wav 格式，10秒-5分钟，<20MB",
      "type": "integer",
      "x-i18n": {
        "en-US": {
          "description": "The file_id of the audio to be cloned, obtained through the file upload interface. Audio requirements: mp3/m4a/wav format, 10 seconds to 5 minutes, <20MB"
        }
      }
    },
    "language_boost": {
      "description": "增强对指定语言/方言的识别能力。可设置为 auto 自动判断，或指定具体语言",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "Enhance recognition capabilities for a specific language/dialect. Can be set to auto for automatic detection or specify a specific language"
        }
      }
    },
    "model": {
      "description": "试听音频使用的语音模型 speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "Voice model used for the preview audio: speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo"
        }
      }
    },
    "need_noise_reduction": {
      "description": "是否开启降噪",
      "type": "boolean",
      "x-i18n": {
        "en-US": {
          "description": "Whether to enable noise reduction"
        }
      }
    },
    "need_volume_normalization": {
      "description": "是否开启音量归一化",
      "type": "boolean",
      "x-i18n": {
        "en-US": {
          "description": "Whether to enable volume normalization"
        }
      }
    },
    "output_format": {
      "description": "试听音频返回形式，默认 hex，可选 url / hex（url 有效期 24h）。",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "The return format of the preview audio, default hex, options are url / hex (url valid for 24h)."
        }
      }
    },
    "text": {
      "description": "复刻试听文本（限制 1000 字符，支持语气词标签）",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "Cloning preview text (limited to 1000 characters, supports filler word tags)"
        }
      }
    },
    "text_validation": {
      "description": "音频复刻样本的预期文本，≤ 200 字符；服务做 ASR 识别并比对相似度，低于 accuracy 则拒绝。",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "The expected text of the audio cloning sample, ≤ 200 characters; the service performs ASR recognition and compares similarity, and will reject if below accuracy."
        }
      }
    },
    "voice_id": {
      "description": "自定义音色 ID（长度 8-256，首字符必须为字母，允许数字/字母/-/，末位不可为 -/ ）",
      "type": "string",
      "x-i18n": {
        "en-US": {
          "description": "Custom voice ID (length 8-256, must start with a letter, allows numbers/letters/-/, cannot end with -/)"
        }
      }
    }
  },
  "required": [
    "file_id",
    "voice_id"
  ]
}

[
  "品牌平台/MINIMAX"
]