LongCat-Video-Avatar 1.6 vs AURA 1.3B
Newest: AURA 1.3B · Widest inputs: LongCat-Video-Avatar 1.6 · Native audio: Native audio unconfirmed. Not enough arena votes yet for a quality score, so this is a spec comparison.
Meituan (LongCat)
LongCat-Video-Avatar 1.6
- Arena—
- From—
- Max length—
Kyutai
AURA 1.3B
- Arena—
- From—
- Max length—
Add a model
Make it a three-way comparison.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- NewestAURA 1.3BLongCat-Video-Avatar 1.6 Nov 15, 2026 · AURA 1.3B Nov 20, 2026
- Widest inputsLongCat-Video-Avatar 1.6LongCat-Video-Avatar 1.6: Text prompts, Reference images, Audio · AURA 1.3B: Reference images, Audio
- Native audioNative audio unconfirmedGenerates an audio track with the video: LongCat-Video-Avatar 1.6 unconfirmed · AURA 1.3B unconfirmed
- Image to videoBoth animate imagesStarts from an uploaded image: LongCat-Video-Avatar 1.6 yes · AURA 1.3B yes
- Self-hostingAll open weightsDownloadable weights (MIT and CC BY-NC 4.0)
- Most API hostsSame reachLongCat-Video-Avatar 1.6: 0 · AURA 1.3B: 0
Every spec in one table
Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Task | Audio-driven character animation | Speech-driven portrait animation |
| Published capabilities | Animates speakers from audio and optional reference imagery, including multi-person scenes and continued shots. | A four-step causal model animates a portrait from streaming speech, rendering chunks from the available audio. |
| Model size | — | 1.3B parameters |
| Access | Downloadable checkpoint and reference inference implementation | Public student checkpoints and inference code |
| Operating limits | — | Kyutai reports 20.7 fps end to end on one H100 at 576p for 16 Hz playback. |
| Sources | Model weights · Additional documentation | Model weights |
| Output | ||
| Produces | Video | Video |
| Resolutions | — | 576p |
| Highest resolution | — | |
| Inputs | ||
| Text prompts | Yes | No |
| Start image (image to video) | Yes | Yes |
| Video input | No | No |
| Audio input | Yes | Yes |
| Access | ||
| Weights | OpenMIT | OpenCC BY-NC 4.0 |
| Released | Nov 15, 2026 | Nov 20, 2026 |
Which should you choose?
Which is better, LongCat-Video-Avatar 1.6 or AURA 1.3B?
Neither model has enough arena votes for a reliable quality score yet, so this page compares specs only. Run the same three or four prompts through each and judge the results.
What is the difference between LongCat-Video-Avatar 1.6 and AURA 1.3B?
LongCat-Video-Avatar 1.6 is a video model from Meituan (LongCat) (Nov 15, 2026), taking text prompts, reference images and audio and producing video. AURA 1.3B is a video model from Kyutai (Nov 20, 2026), taking reference images and audio and producing video.
Which is newer?
LongCat-Video-Avatar 1.6 Nov 15, 2026; AURA 1.3B Nov 20, 2026.
Which generates video with sound?
Generates an audio track with the video: LongCat-Video-Avatar 1.6 unconfirmed; AURA 1.3B unconfirmed.
Can I run any of these on my own hardware?
All open weights. Downloadable weights (MIT and CC BY-NC 4.0).