Last Update: 2025/3/26

SenseFlow Audio API

The SenseFlow Audio API allows you to convert text to audio and audio back to text .

Endpoints

Text to Audio

POST https://platform.llmprovider.ai/v1/agent/text-to-audio

Convert text to speech audio.

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body

Parameter	Type	Description
model	string	agent name
message_id	string	(Optional) Message ID for content lookup
text	string	Text to convert (used if message_id not provided)
user	string	End user identifier

Response Headers

Header	Value
Content-Type	audio/wav

Example Request

Shell

curl -X POST 'https://platform.llmprovider.ai/v1/agent/text-to-audio' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
    "text": "Hello, this is a test message",
    "user": "abc-123"
}' \
--output audio.wav

Python

import requests

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/agent/text-to-audio'

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

data = {
    'text': 'Hello, this is a test message',
    'user': 'abc-123'
}

response = requests.post(url, headers=headers, json=data)
with open('audio.wav', 'wb') as f:
    f.write(response.content)

Node.js

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

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/agent/text-to-audio';

const data = {
    text: 'Hello, this is a test message',
    user: 'abc-123'
};

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

axios.post(url, data, {headers, responseType: 'arraybuffer'})
    .then(response => {
        fs.writeFileSync('audio.wav', response.data);
    })
    .catch(error => console.error(error));

Audio to Text

POST https://platform.llmprovider.ai/v1/agent/audio-to-text

Convert speech audio to text.

Request Headers

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

Request Body

Parameter	Type	Description
model	string	agent name
file	file	Audio file (mp3, mp4, mpeg, mpga, m4a, wav, webm). file maxsize <= 20M
user	string	End user identifier

Response

Field	Type	Description
text	string	Transcribed text

Example Request

Shell

curl -X POST 'https://platform.llmprovider.ai/v1/agent/audio-to-text' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--form '[email protected]' \
--form 'user=abc-123'

Python

import requests

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/agent/audio-to-text'

headers = {
    'Authorization': f'Bearer {api_key}'
}

files = {
    'file': open('audio.mp3', 'rb')
}

data = {
    'user': 'abc-123'
}

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

Node.js

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

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/agent/audio-to-text';

const form = new FormData();
form.append('file', fs.createReadStream('audio.mp3'));
form.append('user', 'abc-123');

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    ...form.getHeaders()
};

axios.post(url, form, {headers})
    .then(response => console.log(response.data))
    .catch(error => console.error(error));

Example Response

{
  "text": "Hello, this is the transcribed text."
}