OpenAI GPT-Realtime-2: Voice Agents Enter a New Era of Reasoning and Real-Time Translation
Published on 08.05.2026
GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper: OpenAI's Big Voice API Push
TLDR: OpenAI released three new streaming audio models — GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper — available now in the Realtime API. GPT-Realtime-2 brings what OpenAI calls "GPT-5-class reasoning" to voice agents, with a 128K context window and adjustable reasoning effort levels. This is a meaningful step forward for developers building production voice agents.
[AINews] GPT-Realtime-2, -Translate, and -Whisper: new SOTA realtime voice APIs