Last Update: 2025/3/26

LLMVision Speech API

The LLMVision Speech API allows you to convert text to speech using OpenAI's SDK. This document provides an overview of the API endpoints, request parameters, and response structure.

Endpoint

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

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body

The request body should be a JSON object with the following parameters:

Parameter	Type	Description	Note
model	string	The model to use (e.g., SenseTTS-Fusion-20250324).
input	string	The text to generate audio for. The maximum length is 4096 characters.
voice	string	The voice to use (girl_naisheng, girl_pingjing, girl_yingqior guy_qingshuang).	View the full voice list
response_format	string	(Optional) The format of the audio response (mp3, wav, wav_stream ).	wav_stream: 流式音频返回.
speed	number	(Optional) The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.
language	string	(Optional) The language of the input text.
volume	number	(Optional) The volume of the generated audio. Select a value from 0.0 to 1.0. 1.0 is the default.
pitch	number	(Optional) The pitch of the generated audio. Select a value from -1.0 to 1.0. 0.0 is the default.
stream	bool	(Optional) Whether to return the audio as a stream. Default is false.
reference_voice_wav	string	(Optional) The file path of the reference WAV audio.	参考音频
timber_weights	map[string]float	(Optional) The file paths and corresponding weights of WAV audio generated by the Sovits model.(must be = 1)	融合音频

Example Request

{
  "model": "SenseTTS-Fusion-20250324",
  "input": "人之初，性本善",
  "voice": "guy_shuaiqi"
}

Response

The API returns an audio file in the requested format.

Example Request

Shell

curl -X POST https://platform.llmprovider.ai/v1/audio/speech \
-H "Authorization: Bearer $YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "SenseTTS-Fusion-20250324",
  "input": "Hello, how are you today?",
  "voice": "girl_naisheng",
}' \
--output speech.mp3

nodejs

const axios = require('axios');
const fs = require('fs');

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/audio/speech';

const data = {
    model: 'SenseTTS-Fusion-20250324',
    input: 'Hello, how are you today?',
    voice: 'girl_naisheng'
};

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json',
    'responseType': 'arraybuffer'
};

axios.post(url, data, { headers })
.then(response => {
    fs.writeFileSync('speech.mp3', response.data);
    console.log('Audio file saved as speech.mp3');
})
.catch(error => {
    console.error('Error:', error);
});

python

import requests

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/audio/speech'

headers = {
    'Authorization': f'Bearer {api_key}',
    'Content-Type': 'application/json'
}

data = {
    'model': 'SenseTTS-Fusion-20250324',
    'input': 'Hello, how are you today?',
    'voice': 'girl_naisheng',
}

response = requests.post(url, headers=headers, json=data)

if response.status_code == 200:
    with open('speech.mp3', 'wb') as f:
        f.write(response.content)
    print('Audio file saved as speech.mp3')
else:
    print('Error:', response.status_code, response.text)

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