Last Update: 2025/3/26

LLMVision Clone Voice API

Endpoint

POST https://platform.llmprovider.ai/v1/audio/clone

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	multipart/form-data

Request Body

Parameter	Type	Required	Description
input	string	Yes	The text content to generate audio from.
prompt	string	Yes	The reference text for the audio sample, used to guide the model's style or continue a previous audio segment.
model	string	Yes	The ID of the model to use, e.g., whisper-1.
file	file	No	The sample audio file in one of the following formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
response_format	string	No	The output format of the transcript. Options: json, text, srt, verbose_json, or vtt. Default is json.
stream	boolean	No	Whether to enable streaming. Default is false.
audio_base64	string	No	The Base64-encoded audio file content.
duration	int64	No	The duration of the audio file (in seconds). This is used internally and is not a request parameter.

Additional Notes:

• Either file or audio_base64 must be provided, but not both.
• When stream is set to true, the server will return audio data in a streaming format, suitable for real-time applications.
• The prompt parameter can provide stylistic guidance, influencing the generated audio output.

Response Body

The transcription object or a verbose transcription object.

Example Request

{
  "model": "lmp-clone-20250310",
  "input": "收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般笼放。",
  "prompt": "我觉得最近北京的天气真的是哈，比较难难以预料吧，就昨天我们在马上就要结束的时候，突然就开始下大雨。",
  "file": "./参考音频.wav"
}

Response

The API returns an audio file in the requested format.

Example Request

Shell

curl -X POST https://platform.llmprovider.ai/v1/audio/clone \
    -H "Authorization: Bearer $YOUR_API_KEY" \
    -H "Content-Type: multipart/form-data" \
    -F file="@audio.mp3" \
    -F model="lmp-clone-20250310"

nodejs

const FormData = require('form-data');
const fs = require('fs');
const axios = require('axios');

const formData = new FormData();
formData.append('file', fs.createReadStream('audio.mp3'));
formData.append('model', 'lmp-clone-20250310');

axios.post('https://platform.llmprovider.ai/v1/audio/clone', formData, {
    headers: {
        'Authorization': `Bearer ${YOUR_API_KEY}`,
        ...formData.getHeaders()
    }
})
    .then(response => {
        console.log(response.data);
    })
    .catch(error => {
        console.error('Error:', error);
    });

python

import requests

audio_file = open("audio.mp3", "rb")
files = {
        "file": audio_file
}
headers = {
        "Authorization": f"Bearer {YOUR_API_KEY}"
}

response = requests.post(
        "https://platform.llmprovider.ai/v1/audio/clone",
        headers=headers,
        files=files,
        data={
                "model": "lmp-clone-20250310"
        }
)

print(response.json())

For any questions or further assistance, please contact us at [email protected].