Voice Clone (Voice Clone)

Voice cloning interface - upload an audio sample to clone a specific voice. Cloned voices can be used for speech synthesis to achieve personalized TTS.

API Endpoints

POST/voice_clone

Create voice clone task

GET/voice_clone/list

Get list of cloned voices

Request Parameters

Parameter	Type	Required	Description
`file_id`	string	Required	Uploaded audio file ID
`voice_name`	string	Required	Voice name
`description`	string	Optional	Voice description

Request Example

{
  "file_id": "file_xxxxx",
  "voice_name": "我的音色",
  "description": "基于示例音频克隆的音色"
}

Response Example

{
  "voice_id": "voice_clone_xxxxx",
  "voice_name": "我的音色",
  "status": "completed",
  "created_at": 1234567890
}

Code Examples

import requests

# 步骤1：上传音频文件
upload_url = "https://your-proxy-domain.com/v1/files/upload"
headers = {"Authorization": "Bearer YOUR_API_KEY"}

files = {"file": open("voice_sample.mp3", "rb")}
data = {"purpose": "voice_clone"}
upload_resp = requests.post(upload_url, headers=headers, files=files, data=data)
file_id = upload_resp.json()["file_id"]

# 步骤2：克隆音色
clone_url = "https://your-proxy-domain.com/v1/voice_clone"
clone_data = {
    "file_id": file_id,
    "voice_name": "我的音色",
    "description": "基于示例音频克隆的音色"
}
clone_resp = requests.post(
    clone_url,
    headers={**headers, "Content-Type": "application/json"},
    json=clone_data
)
print(clone_resp.json())