LongCat-Video-Avatar 1.6
Meituan, the Chinese delivery and services company, released a free-to-download tool that makes realistic talking-person videos from audio, useful for creators building avatar videos.
Key facts
- Released
- Nov 15, 2026
- What it does
- Makes video: Creates video clips from a description or a picture.
Can I use it?
In an app
No app mentioned so far.
For developers
No developer access mentioned so far.
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
How it scores
Not in the independent rankings yet. New models usually show up within a few weeks, and this page updates when they do.
Compare LongCat-Video-Avatar 1.6 with
The details
Meituan's new Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open". upgrade to its LongCat-Video-Avatar model, which turns audio into talking human video with more natural lip sync and stable videos over 10 minutes long. Its own human preference study ranks it second among six systems, behind OmniHuman-2.0.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
meituan-longcat/LongCat-Video-Avatar-1.6Timeline
/Hugging FaceOfficialFirst signal
Get alerts like this the moment they happen.
From Meituan and every other major lab.