Fact · Speech recognition
OpenAI's Audio API provides a speech endpoint based on its GPT-4o mini TTS model, which turns written text into spoken audio.
Checked against its source on October 17, 2026
In the source's own words
“The Audio API provides a speech endpoint based on our GPT-4o mini TTS (text-to-speech) model”
Text to speech (OpenAI API guide), OpenAI, 2026, Introduction.
Open the original- What it measures
- This is OpenAI's text-to-speech guide, read on 2026-10-17. It is a separate guide from the speech-to-text guide that documents the Whisper model in the API.
- What it does not show
- Vendor documentation for one API on one date. Model names and voice options change, so check the guide before you build on it.