AURA 1.3B vs PAN 2
Compare documented capabilities and access. A dash means a comparable figure is unavailable.
| Specification | ||
|---|---|---|
| Task | Speech-driven portrait animation | World simulation |
| Published capabilities | A four-step causal model animates a portrait from streaming speech, rendering chunks from the available audio. | Predicts what happens after an action in a starting scene. |
| Model size | 1.3B parameters | — |
| Access | Public student checkpoints and inference code | Public weights, full training code and inference code |
| Result | — | Simulated video conditioned on a scene and action |
| Operating limits | Kyutai reports 20.7 fps end to end on one H100 at 576p for 16 Hz playback. | — |
| Sources | Model weights | Publisher documentation |
| Inputs | Images, Audio | Text, Images |
| Weights | Open weights · CC BY-NC 4.0 | Open weights · Apache-2.0 |
| Released | Nov 20, 2026 | Nov 10, 2026 |