Are there any remotely comparable open source models? Fully multimodal, audio-to... | Hacker News

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

		ilaksh on May 13, 2024 \| parent \| context \| favorite \| on: GPT-4o Are there any remotely comparable open source models? Fully multimodal, audio-to-audio?

BrutalCoding on May 13, 2024 [–]

Hmm, there’s this Gazelle that can take in audio, but to get audio back out you’d have to use something else (e.g. Piper).

https://github.com/tincans-ai/gazelle?tab=readme-ov-file

https://tincans.ai/slm

https://github.com/rhasspy/piper

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