AISimon Willisonabout 3 hours ago
OpenAI WebRTC Audio Session, now with document context
1 min read
OpenAI's WebRTC Audio Session now supports document context, allowing users to paste text for audio conversations. The update also adds the GPT-Realtime-2 model, described as OpenAI's first voice model with GPT-5-class reasoning and a September 30, 2024 knowledge cut-off. The tool runs in a browser.
Level
Hype check
Tap to vote and see what everyone thinks.
