News for hackers. Stuff that matters.

A comment on Neural audio codecs: how to get audio into LLMs. Parent comment

Re:Neural audio codecs: how to get audio into LLMs by idonotknowwhy on Tuesday October 21, 2025 @10:44AM (#45656467)
Qwen3 omni transcriber can do this. It can describe the voice, emotion very well
[ Parent | on HN ]
Re:Neural audio codecs: how to get audio into LLMs by 85392_school on Tuesday October 21, 2025 @11:27AM (#45657007)
I've also had luck with Gemini. If I made a few noises and asked which one was higher pitched, it could easily tell.
[ Parent | on HN ]