Skip to main content
POST
Text to speech (TTS)
Synthesize text into natural-sounding speech.

Request

Parameters

Response

Returns a binary audio stream directly, with Content-Type matching the chosen response_format:

Python example

gpt-4o-mini-tts advanced

The next-gen TTS supports controlling tone via instructions:

Streaming playback

Synthesis may take ≥ 1 second; in a browser or client you can receive it as a stream:

Billing

Charged by input character count, regardless of the chosen model and format.