FrontierThe story, in brief
OpenAI Releases Three Realtime Audio Models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper in the Realtime API
Three new audio models. OpenAI just made voice agents and real-time translation table stakes for every developer.
The KeyNews take
Why it matters
OpenAI expands its model portfolio with three specialized audio capabilities (reasoning, translation, transcription), raising the bar for competitors and enabling a new class of voice-first applications that developers can build immediately.
The key facts
5 to knowThree new models: GPT-Realtime-2, GPT-Realtime-Translate, GPT-Realtime-Whisper
GPT-Realtime-Translate supports 70+ languages
Models designed for live voice, reasoning agents, and streaming transcription
Available via Realtime API
Published May 8, 2026
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Three purpose-built audio models expand what developers can build with live voice: reasoning agents, speech translation across 70+ languages, and streaming transcription. The post OpenAI Releases Three Realtime Audio Models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper in the…