Released on May 7, 2026
OpenAI announced this model on 2026-05-07. API: v1/realtime · API: v1/realtime/translations · API: v1/realtime/transcription_sessions.
- Hosting route
- First-party API
- Affected scope
- API: v1/realtime · API: v1/realtime/translations · API: v1/realtime/transcription_sessions
- Announced
- May 7, 2026
- First seen by ModelClock
- Oct 3, 2026
What the provider published
developers.openai.com ↗Feature · Model: gpt-realtime-2 · Model: gpt-realtime-translate · Model: gpt-realtime-whisper · API: v1/realtime · API: v1/realtime/translations · API: v1/realtime/transcription_sessions
Released GPT-Realtime-2, a new realtime voice model with configurable reasoning for speech-to-speech agents, along with GPT-Realtime-Translate for streaming speech translation and GPT-Realtime-Whisper for streaming speech-to-text.
Updated the Realtime and audio guide, added a dedicated Realtime translation guide, refreshed Realtime transcription for streaming transcripts, and moved realtime prompting guidance into Using realtime models.
Read from the provider's text; the quote is the provider's exact lines.