Model · OpenAI · Text-To-Speech
GPT-4o mini TTS
OpenAI's GPT-4o-mini-based text-to-speech model, which replaced the older tts-1 line. Deprecated 2026-10-01 with shutdown 2027-01-06; OpenAI points to gpt-realtime-2.1-mini instead.
- Modality
- Text-To-Speech
- License
- Proprietary (Proprietary)
- Released
- March 20, 2025
- Last verified
- October 28, 2026
- Runs locally
- No
Strengths
- Speech generation built on GPT-4o mini
- Lower-cost speech output than larger realtime/audio stacks
- Shares the same modern API surface as the rest of OpenAI's current models
Weaknesses
- Closed weights
- Speech generation only — no speech-to-text or full duplex realtime behavior
Try it
| Where | Type | Notes |
|---|---|---|
| OpenAI API | hosted-api | API key required |
Official sources
- Model docs docs
Change log
- — Deprecated — OpenAI announced deprecation 2026-10-01, shutdown 2027-01-06; lab replacement gpt-realtime-2.1-mini (not catalogued).
- — Verified current against OpenAI's models overview — still listed under speech.
- — Verified current. The base alias now points to the gpt-4o-mini-tts-2025-12-15 snapshot; the 2025-03-20 snapshot retires 2026-07-23.
- — Added after verification of the current OpenAI speech generation lineup.
Esc