SiliconFlow
API REFERENCE

Upload a Voice

Upload user-provided voice style, which can be in base64 encoding or file format.

POST
/uploads/audio/voice

Authorization

AuthorizationBearer <token>required

Set the header 'Authorization: Bearer {your API key}' for authentication

In: header

Request Body

modelstringrequired

Predefined voice style model name

Example"FunAudioLLM/CosyVoice2-0.5B"
customNamestringrequired

User-defined voice style name

Example"your-voice-name"
textstringrequired

Corresponding text content for the audio

Example"在一无所知中, 梦里的一天结束了，一个新的轮回便会开始"
audiostring

Audio file encoded in base64 with the header format of data:audio/mpeg;base64

Example"data:audio/mpeg;base64,aGVsbG93b3JsZA=="
modelstringrequired

Predefined voice style model name

Example"FunAudioLLM/CosyVoice2-0.5B"
customNamestringrequired

User-defined voice style name

Example"your-voice-name"
textstringrequired

Corresponding text content for the audio

Example"在一无所知中, 梦里的一天结束了，一个新的轮回便会开始"
filefile

File to upload

Formatbinary
Example"/path/to/audio.mp3"

Response Body

Successful response

TypeScript Definitions

Use the response body type in TypeScript.

uristring
Example"speech:your-voice-name:xxx:xxx"

curl -X POST "https://api.siliconflow.cn/v1/uploads/audio/voice" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@test.mp3" \
  -F "model=IndexTeam/IndexTTS-2" \
  -F "customName=your-voice-name" \
  -F "text=慢工出细活，再给我两分钟，你马上就能见识到超梦分析的厉害了"

import requests

url = "https://api.siliconflow.cn/v1/uploads/audio/voice"
headers = {
    "Authorization": "Bearer YOUR_API_KEY"
}
files = {
    "file": open("test.mp3", "rb")
}
data = {
    "model": "IndexTeam/IndexTTS-2",
    "customName": "your-voice-name",
    "text": "慢工出细活，再给我两分钟，你马上就能见识到超梦分析的厉害了"
}

response = requests.post(url, headers=headers, files=files, data=data)
print(response.text)

{
  "uri": "speech:your-voice-name:xxx:xxx"
}
{
  "code": 20012,
  "message": "string",
  "data": "string"
}
"Invalid token"
"Forbidden"
"404 page not found"
{
  "message": "Request was rejected due to rate limiting. If you want more, please contact contact@siliconflow.cn. Details:TPM limit reached.",
  "data": "string"
}
{
  "code": 50505,
  "message": "Model service overloaded. Please try again later.",
  "data": "string"
}
"string"

Image Generation POST

Creates an image response for the given prompt. The URL for the generated image is valid for one hour. Please make sure to download and store it promptly to avoid any issues due to URL expiration.

Create a Speech POST

Generate audio from input text. The data generated by the interface is the binary data of the audio, which requires the user to handle it themselves.

Upload a Voice