Kyutai open-sources AURA: real-time lip-synced face for voice AI on a single GPU

alexcovo_eth · x · 2026-11-21

Kyutai Labs released AURA, a real-time face for voice AI: pick or upload a face, start talking, and it responds with live-generated lip-synced video on a single GPU. A demo is available and the entire project is open-sourced.

Original post →

More from Multimodal

Multimodal channel →