OpenAI WebRTC Audio Session, now with document context
Simon Willison updated his OpenAI WebRTC audio playground to support the new GPT-Realtime-2 model, described as OpenAI's first voice model with GPT-5-class reasoning and a September 2024 knowledge cut-off. The tool now also accepts document context, enabling audio conversations about pasted information. The update was motivated by the model not yet appearing in the ChatGPT iPhone app.
Developers can now experiment with GPT-Realtime-2's voice reasoning in a browser with custom document context.


