OpenAI Audio Models
Every OpenAI Audio speech and audio model, explained in plain English. OpenAI's speech models — voice, transcription and the realtime audio models.
What are the OpenAI Audio models?
OpenAI releases new AI models regularly, and the announcements are usually written for engineers. We explain each model in language anyone can follow: what it does well, what it costs, what it can handle, and how it compares to the one before it.
Models, newest first
- GPT Live Transcribe 2026-07-28 GPT Live Transcribe explained →
- GPT Transcribe 2026-07-28 GPT Transcribe explained →
- GPT Realtime 2.1 Mini 2026-07-06 GPT Realtime 2.1 Mini explained →
- GPT Realtime 2.1 2026-07-06 GPT Realtime 2.1 explained →
- GPT Realtime Whisper 2026-05-07 GPT Realtime Whisper explained →
- GPT Realtime Translate 2026-05-07 GPT Realtime Translate explained →
- GPT Realtime 2 2026-05-07 GPT Realtime 2 explained →
- GPT Audio 1.5 2026-02-23 GPT Audio 1.5 explained →
- GPT Realtime 1.5 2026-02-23 GPT Realtime 1.5 explained →
- GPT-4o Mini TTS 2025-12-15 GPT-4o Mini TTS explained →
- GPT-4o Mini Transcribe 2025-12-15 GPT-4o Mini Transcribe explained →
- GPT Audio Mini 2025-12-15 GPT Audio Mini explained →
- GPT Realtime Mini 2025-12-15 GPT Realtime Mini explained →
- GPT-4o Audio Preview 2024-10-17 GPT-4o Audio Preview explained →
Want a heads-up when OpenAI Audio updates?
We email you the moment a new OpenAI Audio version drops — plus plain-English release notes like these. No spam.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Google Calendar