Official documentation
Text to speech (OpenAI API guide)
OpenAI, 2026
Read the originalRead on October 17, 2026
- What it is
- OpenAI's developer guide to its speech endpoint, which turns written text into spoken audio with its GPT-4o mini TTS model. It lists the output formats, the built-in voices and the TTS model options.
- How much weight it carries
- The vendor's own documentation for its API, so it is authoritative for what that API does on the date read. Model names, voices and prices change, and the guide does not describe any Whisper model.
Facts taken from this source
- OpenAI's Audio API provides a speech endpoint based on its GPT-4o mini TTS model, which turns written text into spoken audio.
“The Audio API provides a speech endpoint based on our GPT-4o mini TTS (text-to-speech) model” (Introduction)