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

AURA 1.3B vs H3-Tiny-17B-Pruned-FL2VA

Native audio: H3-Tiny-17B-Pruned-FL2VA. 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. H3-Tiny

    H3-Tiny-17B-Pruned-FL2VA

    Released Nov 20, 2026

    • Text to video
    • Image to video
    • Native audio
    • 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.

  • NewestSame release dateAURA 1.3B Nov 20, 2026 · H3-Tiny-17B-Pruned-FL2VA Nov 20, 2026
  • Widest inputsSame inputsAURA 1.3B: Reference images, Audio · H3-Tiny-17B-Pruned-FL2VA: Text prompts, Reference images
  • Native audioH3-Tiny-17B-Pruned-FL2VAGenerates an audio track with the video: AURA 1.3B unconfirmed · H3-Tiny-17B-Pruned-FL2VA yes
  • Image to videoBoth animate imagesStarts from an uploaded image: AURA 1.3B yes · H3-Tiny-17B-Pruned-FL2VA yes
  • Self-hostingAll open weightsDownloadable weights (CC BY-NC 4.0 and MiniMax H3 Community License)
  • Most API hostsSame reachAURA 1.3B: 0 · H3-Tiny-17B-Pruned-FL2VA: 0
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

AURA 1.3B vs H3-Tiny-17B-Pruned-FL2VA specifications side by side
SpecificationAURA 1.3BKyutaiH3-Tiny-17B-Pruned-FL2VAH3-Tiny
TaskSpeech-driven portrait animationAudiovisual generation
Published capabilitiesA four-step causal model animates a portrait from streaming speech, rendering chunks from the available audio.Generates synchronized video and audio from a prompt or from first and last frames.
Model size1.3B parameters17.07B transformer parameters
AccessPublic student checkpoints and inference codeDownloadable transformer checkpoint for the H3 pipeline
Operating limitsKyutai reports 20.7 fps end to end on one H100 at 576p for 16 Hz playback.50 steps
SourcesModel weightsModel weights
Output
ProducesVideoVideo with sound
Resolutions576p—
Highest resolution—
Sound—Always generated
Inputs
Text promptsNoYes
Start image (image to video)YesYes
Video inputNoNo
Audio inputYesNo
Access
WeightsOpenCC BY-NC 4.0OpenMiniMax H3 Community License
ReleasedNov 20, 2026Nov 20, 2026
03 — Questions

Which should you choose?

Which is better, AURA 1.3B or H3-Tiny-17B-Pruned-FL2VA?

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 H3-Tiny-17B-Pruned-FL2VA?

AURA 1.3B is a video model from Kyutai (Nov 20, 2026), taking reference images and audio and producing video. H3-Tiny-17B-Pruned-FL2VA is a video model from H3-Tiny (Nov 20, 2026), taking text prompts and reference images and producing video with sound.

Which is newer?

AURA 1.3B Nov 20, 2026; H3-Tiny-17B-Pruned-FL2VA Nov 20, 2026.

Which generates video with sound?

Generates an audio track with the video: AURA 1.3B unconfirmed; H3-Tiny-17B-Pruned-FL2VA yes.

Can I run any of these on my own hardware?

All open weights. Downloadable weights (CC BY-NC 4.0 and MiniMax H3 Community License).