Which LLM can generate text so quickly a real-time conversation is viable?
Re:OpenAI's WebRTC Problem
by bensyverson on Saturday May 09, 2026 @02:31PM
(#48077111)
There are now realtime “speech-to-speech” models [0]. I believe they skip text to streamline the architecture.
but, if it's trying to respond in a natural way, with interruptions in both directions, it may still be a good idea. if there's a delay between you stopping and it starting talking, it feels weird
(you might be able to fake some of that on the client, but then you need a thicker client)