OpenAI Releases Three Realtime Audio Models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper in the Realtime API

OpenAI launched three new Realtime API audio models: GPT-Realtime-2 for reasoning-heavy voice agents, GPT-Realtime-Translate for live speech translation, and GPT-Realtime-Whisper for transcription.

The company also moved the Realtime API from beta to general availability, signaling production readiness.

The update gives developers lower-friction tools to build real-time voice products with better latency control, reasoning, translation, and transcription.