First month for free!

Get started

Easy-to-use AI API

Whisper API

The most affordable Whisper API on the market. Accurately and quickly transcribe audio to text with our state-of-the-art speech recognition AI model.

Get StartedRead Docs

Latest AI Model

The Whisper v3-large is a powerful AI model for speech recognition. It was trained on 5 million hours of diverse audio data to deliver exceptional accuracy and efficiency.

Build Your AI Features

Transcribe and translate audio in over 100 languages. Easily build your own AI features, such as automated customer support or meeting summaries.

Lowest Price

Our Whisper API is the most affordable speech-to-text API on the market. It's priced at just $0.50 per 3 hours of audio.

Simple API Setup

The Whisper API is simple to use. You can get started in just a few minutes.

const body = new FormData();
body.append('file', '');
// instead of providing a URL you can also upload a file object:
// body.append('file', new Blob([await fs.readFile('/path/to/audio.mp3')]));
body.append('language', 'english');
body.append('response_format', 'json');

fetch('', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY'
  body: body
.then(response => response.json()).then(data => {
.catch(error => {
  console.error('Error:', error);
Read Docs

Frequently Asked Questions

Get Started

Other APIs: SDXL API, Speech-to-Text API, Mistral API