Saturday, May 9, 2026·1 sources tracked
OpenAI Introduces New Real-Time Voice Models
OpenAI has announced the release of three new voice models, significantly expanding its real-time audio processing capabilities. The new additions include GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper. These models aim to enhance applications requiring immediate voice interaction and translation.
Source-linked headlines
OpenAI Unveils GPT-Realtime-2 and Two New Voice API Models
TNW | Openai · Friday, May 8, 2026
OpenAI has introduced three new voice models to its API offerings. These include GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, designed for enhanced real-time audio processing.
Why it matters: The introduction of these models expands OpenAI's suite of real-time voice AI tools, potentially enabling more dynamic and responsive applications in areas like live translation and interactive voice agents.
