ToolsThe story, in brief
OpenAI's new voice model brings GPT-5-level reasoning to real-time conversations
Real-time reasoning just went voice-native. OpenAI ships GPT-5-level conversation without the latency.
The KeyNews take
Why it matters
OpenAI is collapsing the gap between text and voice reasoning—three new models (GPT-Realtime-2, Translate, Whisper) enable enterprises to deploy reasoning agents in live conversations at scale, shifting how voice AI gets deployed beyond transcription.
The key facts
5 to knowThree new models: GPT-Realtime-2, GPT-Realtime-Translate, GPT-Realtime-Whisper
GPT-Realtime-2 delivers GPT-5-level reasoning in real-time
GPT-Realtime-Translate supports 70+ languages
Real-time speech transcription and translation capability
Published May 7, 2026
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: OpenAI is shipping three new voice models—GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper—that can reason in real time, translate across 70+ languages, and transcribe live speech. GPT-Realtime-2 brings reasoning that OpenAI says matches GPT-5.