GPT-4o Mini TTS
GPT-4o Mini TTS is a deprecated speech-synthesis model built on GPT-4o Mini. It turns text into audio and has a documented maximum input of 2,000 tokens.
Deprecated API; check access details
Input length limits the spoken passage
The model's December 2025 snapshot is distinct from the text-only GPT-4o Mini API. The 2,000-token input limit applies to this speech model; the language model's larger context limit must not be substituted for it.GPT-4o Mini TTS official model documentation
Review an existing integration
Practical guidance. Divide long narration at meaningful sentence or section boundaries. Review continuity of pace and pronunciation across those sections. Keep the full approved text as the authority for the narration, rather than reconstructing it from generated audio.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Deprecated API; check access details |
| Access | API |
| Model identifiers | gpt-4o-mini-ttsgpt-4o-mini-tts-2025-12-15 |
| Provider status | Deprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4o Mini TTS official model documentation |
Related models
TTS-1 converts written text into speech and was designed for low-delay delivery.
Launch date not confirmedDeprecated API; check access detailsAPIA deprecated text-to-speech model focused on audio quality.
Launch date not confirmedDeprecated API; check access detailsAPI