News for hackers. Stuff that matters.

A comment on Bagel: The Open-Source Unified Multimodal Model. Parent comment

Re:Bagel: The Open-Source Unified Multimodal Model by amrrs on Monday May 26, 2025 @06:39AM (#44096014)
Google Gemini Live is pretty good.

If you want to try only voice, Try unmute.sh by Kyutai which will be eventually open-sourced

[ Parent | on HN ]
Re:Bagel: The Open-Source Unified Multimodal Model by spuz on Tuesday May 27, 2025 @07:24AM (#44105839)
Thanks - it seems that Gemini Live is pretty far behind advanced voice mode at the moment. For example, I can't get it to speak slower when I want to understand what it is saying.

I'm still interested in what keyword I could use to search for the latest research in voice models.

[ Parent | on HN ]