Source: OpenAI Text-to-Speech Guide
OpenAI API guide to the Speech endpoint: deprecated TTS models and Realtime migration, built-in voices, instructions steering, output formats and the AI-voice disclosure rule.
Contents
- What: official API documentation (Text to speech guide)
- Author/publisher: OpenAI
- Date: living document; read 2026-11-14
- Original: Text to speech
Summary
Describes /v1/audio/speech, its voices and formats, and the move of TTS onto the Realtime API.
Key claims
tts-1,tts-1-hdandgpt-4o-mini-ttsshut down 2027-01-06; the migration target isgpt-realtime-2.1-minivia the Realtime API, which is a workflow change rather than a model swap.tts-1trades quality for lower latency thantts-1-hd.instructionsongpt-4o-mini-ttssteer accent, emotion, intonation, speed, tone, whispering.- 13 built-in voices (marin and cedar recommended); voices are tuned for English but language coverage follows Whisper.
- Output: mp3 (default), opus, aac, flac, wav, pcm (raw 24 kHz 16-bit LE). WAV/PCM give the fastest response.
- Audio streams via chunked transfer encoding so playback starts before generation ends.
- Custom voices require a consent recording from the speaker.
- Usage policy requires disclosing to end users that the voice is AI-generated.