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.
More from Multimodal
- WavLate aligns words to audio moments with MaxSim, keeping 32 vectors per 10s clip — IgorCarron · 2026-11-21
- Ex-TensorFlow early member founds TensorScale, betting world models will beat LLMs — TerryTangYuan · 2026-11-21
- Cinematographer Tests Minimax's Cinestill 800T Emulation for a Blade Runner Look in Neon Rain — Purple-Let4907 · 2026-11-21
- 15-year electronic producer built an agentic DAW with Claude and made a full album — yawnxyz · 2026-11-21
- Self-hosted cloud GPUs beat Higgsfield and Runway APIs on cost and flexibility — Al_Grigor · 2026-11-21
- Gaussian splat top-down scan shows how Fable plans object placement in pixel apartment — XRarchitect · 2026-11-21