Which LLM can generate text so quickly a real-time conversation is viable? | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

Kwpolska 29 days ago | parent | context | favorite | on: OpenAI’s WebRTC problem

Which LLM can generate text so quickly a real-time conversation is viable?

bensyverson 29 days ago [–]

There are now realtime “speech-to-speech” models [0]. I believe they skip text to streamline the architecture.

[0]: https://openai.com/index/introducing-gpt-realtime/

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact