Home / AI Research / AURA: AUdio-dRiven streaming Avatar
AUAI Research
AURA: AUdio-dRiven streaming Avatar
by kyutai · Nathaniel Cohen, Nicolas Dufour, Amélie Royer, Alasdair Newson, Patrick Pérez
Current audio-driven video diffusion models can synthesize realistic talking-head videos but generally require dozens of diffusion denoising steps over multi-second video chunks, making them unsuitable for streaming applications such as voice assistants and virtual avatars, where low-latency and online causal generation are required properties. AURA generates video chunk by chunk with a rolling KV cache, requiring only the audio of the current chunk to start generating, rather than a multi-second audio look-ahead like bidirectional models. It comes in two sizes: AURA 1.3B streams 576p video in real time on a single GPU (20.7 fps for a 16 Hz playback rate), making it suited to interactive…
Upvotes3
Comments2
Published18 Nov 2026