Skip to main content

Audio API Reference

Generate natural-sounding speech from text (TTS) and transcribe audio to text (STT) using OpenAI’s Whisper model. Both endpoints follow the OpenAI Audio API format.

Text-to-Speech (TTS)

Convert text into lifelike spoken audio.

Endpoint

Request Body

Supported Voices

Supported Formats

Models

Request Examples

cURL

JavaScript

Python

Response

Returns binary audio data with these headers:

Speech-to-Text (Transcription)

Transcribe audio files into text using OpenAI’s Whisper model.

Endpoint

Request Body (multipart/form-data)

Supported Audio Formats

  • MP3 (.mp3)
  • MP4 (.mp4, .m4a)
  • MPEG (.mpeg, .mpga)
  • WAV (.wav)
  • WebM (.webm)
  • OGG (.ogg)
  • FLAC (.flac)
Max file size: 25 MB

Response Formats

Pricing

Request Examples

cURL

JavaScript

Python

Response (JSON format)

Response (verbose_json format)

Error Responses

400 Bad Request

400 File Too Large

400 Unsupported Format

Rate Limits