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

AURA 1.3B vs H3-Tiny-14B-OKD-Ref2VA-v0.1

Newest: AURA 1.3B · Native audio: H3-Tiny-14B-OKD-Ref2VA-v0.1. 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-14B-OKD-Ref2VA-v0.1

    Released Nov 19, 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.

  • NewestAURA 1.3BAURA 1.3B Nov 20, 2026 · H3-Tiny-14B-OKD-Ref2VA-v0.1 Nov 19, 2026
  • Widest inputsSame inputsAURA 1.3B: Reference images, Audio · H3-Tiny-14B-OKD-Ref2VA-v0.1: Text prompts, Reference images
  • Native audioH3-Tiny-14B-OKD-Ref2VA-v0.1Generates an audio track with the video: AURA 1.3B unconfirmed · H3-Tiny-14B-OKD-Ref2VA-v0.1 yes
  • Image to videoBoth animate imagesStarts from an uploaded image: AURA 1.3B yes · H3-Tiny-14B-OKD-Ref2VA-v0.1 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-14B-OKD-Ref2VA-v0.1: 0
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

AURA 1.3B vs H3-Tiny-14B-OKD-Ref2VA-v0.1 specifications side by side
SpecificationAURA 1.3BKyutaiH3-Tiny-14B-OKD-Ref2VA-v0.1H3-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 video and synchronized sound from reference imagery using a pruned MiniMax H3 transformer.
Model size1.3B parameters13.99B 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 19, 2026
03 — Questions

Which should you choose?

Which is better, AURA 1.3B or H3-Tiny-14B-OKD-Ref2VA-v0.1?

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-14B-OKD-Ref2VA-v0.1?

AURA 1.3B is a video model from Kyutai (Nov 20, 2026), taking reference images and audio and producing video. H3-Tiny-14B-OKD-Ref2VA-v0.1 is a video model from H3-Tiny (Nov 19, 2026), taking text prompts and reference images and producing video with sound.

Which is newer?

AURA 1.3B Nov 20, 2026; H3-Tiny-14B-OKD-Ref2VA-v0.1 Nov 19, 2026.

Which generates video with sound?

Generates an audio track with the video: AURA 1.3B unconfirmed; H3-Tiny-14B-OKD-Ref2VA-v0.1 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).