ZMIME
Video model comparison · 2 models · Updated Nov 21, 2026

AURA 1.3B vs LongCat-Video-Avatar 1.6

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.

  1. Kyutai

    AURA 1.3B

    Released Nov 20, 2026

    • Image to video
    • Audio input
    • Arena—
    • From—
    • Max length—
  2. Meituan (LongCat)

    LongCat-Video-Avatar 1.6

    Released Nov 15, 2026

    • Text to video
    • Image to video
    • Audio input
    • Arena—
    • From—
    • Max length—
  3. Add a model

    Make it a three-way comparison.

01 — At a glance

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 1.3BAURA 1.3B Nov 20, 2026 · LongCat-Video-Avatar 1.6 Nov 15, 2026
  • Widest inputsLongCat-Video-Avatar 1.6AURA 1.3B: Reference images, Audio · LongCat-Video-Avatar 1.6: Text prompts, Reference images, Audio
  • Native audioNative audio unconfirmedGenerates an audio track with the video: AURA 1.3B unconfirmed · LongCat-Video-Avatar 1.6 unconfirmed
  • Image to videoBoth animate imagesStarts from an uploaded image: AURA 1.3B yes · LongCat-Video-Avatar 1.6 yes
  • Self-hostingAll open weightsDownloadable weights (CC BY-NC 4.0 and MIT)
  • Most API hostsSame reachAURA 1.3B: 0 · LongCat-Video-Avatar 1.6: 0
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

AURA 1.3B vs LongCat-Video-Avatar 1.6 specifications side by side
SpecificationAURA 1.3BKyutaiLongCat-Video-Avatar 1.6Meituan (LongCat)
TaskSpeech-driven portrait animationAudio-driven character animation
Published capabilitiesA four-step causal model animates a portrait from streaming speech, rendering chunks from the available audio.Animates speakers from audio and optional reference imagery, including multi-person scenes and continued shots.
Model size1.3B parameters—
AccessPublic student checkpoints and inference codeDownloadable checkpoint and reference inference implementation
Operating limitsKyutai reports 20.7 fps end to end on one H100 at 576p for 16 Hz playback.—
SourcesModel weightsModel weights · Additional documentation
Output
ProducesVideoVideo
Resolutions576p—
Highest resolution—
Inputs
Text promptsNoYes
Start image (image to video)YesYes
Video inputNoNo
Audio inputYesYes
Access
WeightsOpenCC BY-NC 4.0OpenMIT
ReleasedNov 20, 2026Nov 15, 2026
03 — Questions

Which should you choose?

Which is better, AURA 1.3B or LongCat-Video-Avatar 1.6?

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 AURA 1.3B and LongCat-Video-Avatar 1.6?

AURA 1.3B is a video model from Kyutai (Nov 20, 2026), taking reference images and audio and producing video. 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.

Which is newer?

AURA 1.3B Nov 20, 2026; LongCat-Video-Avatar 1.6 Nov 15, 2026.

Which generates video with sound?

Generates an audio track with the video: AURA 1.3B unconfirmed; LongCat-Video-Avatar 1.6 unconfirmed.

Can I run any of these on my own hardware?

All open weights. Downloadable weights (CC BY-NC 4.0 and MIT).