OpenAI WebRTC Audio Session Adds GPT-Realtime-2 and Document Context
Original: OpenAI WebRTC Audio Session, now with document context
Simon Willison updated his browser audio playground with GPT-Realtime-2 support and optional pasted document context for voice conversations.
Simon Willison revisited his OpenAI WebRTC Audio Session tool, originally built in December 2024 to test OpenAI’s realtime audio API. The update lets users choose GPT-Realtime-2, a newer realtime voice model OpenAI described as having GPT-5-class reasoning. It also adds a document-context box, allowing users to paste text before starting a browser-based voice session and discuss that material conversationally.
Simon Willison has updated his OpenAI WebRTC Audio Session playground, a browser-based tool he first built in December 2024 to experiment with OpenAI’s then-new WebRTC API for realtime audio model interaction. The tool is designed as a practical interface for starting an audio conversation with OpenAI’s realtime models directly in the browser, using an OpenAI API token, a selected voice, and a selected model.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Simon Willison's Weblog →Summaries are AI-generated; the original article is authoritative.