ZMIME
Meituan (LongCat) · video model · Released Nov 15, 2026

LongCat-Video-Avatar 1.6

Animates speakers from audio and optional reference imagery, including multi-person scenes and continued shots.

  • Video model
  • Open weights
  • Text to video
  • Image to video
  • Audio input
Arena score
—Not enough votes yet
Starting price
—Not published
Longest clip
—Not published
Resolution
—Audio unconfirmed
Quality & price

How it rates and what it costs

LongCat-Video-Avatar 1.6 does not have enough arena votes for a quality score yet.

Specifications

The details

Lab
Meituan (LongCat)
Task
Audio-driven character animation
Published capabilities
Animates speakers from audio and optional reference imagery, including multi-person scenes and continued shots.
Access
Downloadable checkpoint and reference inference implementation
Type
Video model
Released
Nov 15, 2026
Inputs
Text prompts, Reference images, Audio
Output
Video
Can do
Text to video, Image to video, Audio input
Availability
Not on the API hosts we track

Meituan (LongCat) documentation

Questions

About LongCat-Video-Avatar 1.6

Who makes LongCat-Video-Avatar 1.6?

LongCat-Video-Avatar 1.6 is a video model from Meituan (LongCat), released Nov 15, 2026.

What can LongCat-Video-Avatar 1.6 do?

LongCat-Video-Avatar 1.6 accepts text prompts, reference images and audio and produces video. In practice: text to video, image to video and audio input.

Is LongCat-Video-Avatar 1.6 open source?

Yes. Meituan (LongCat) publishes the weights under the MIT, so you can run it on your own hardware.

Where can I use LongCat-Video-Avatar 1.6?

Downloadable checkpoint and reference inference implementation

What are the alternatives to LongCat-Video-Avatar 1.6?

The closest video models from other labs, by release date, are Avatar 6 (HeyGen, —), H3-Tiny-14B-OKD-Ref2VA-v0.1 (H3-Tiny, Nov 19, 2026), AURA 1.3B (Kyutai, Nov 20, 2026), PAN 2 (MBZUAI Institute of Foundation Models, Nov 10, 2026) and Viggle Remake (Viggle AI, Nov 2, 2026).