Avatars

MuseTalk

Real-time lip sync: matches the mouth in a video to new audio. Suits video translation and live avatars.

Developer
Tencent Music (Lyra Lab), China
First release
Apr 2024
Latest release
Mar 2025
Sizes
under 1B
License
Commercial use allowedMIT (code), weights allowed for any purpose including commercial
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Education, Media and production, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Dubbing video into another language
  • Live avatar in a video chat
  • Editing speech in a finished video

Where it is used

EducationMediaCustomer support

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. MuseTalk 1.5
  2. MuseTalk 1.0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can MuseTalk be used in a commercial project?

Yes. License: MIT (code), weights allowed for any purpose including commercial. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does MuseTalk need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does MuseTalk support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download MuseTalk and what does it cost?

The MuseTalk weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

AvatarsLivePortraitKuaishou (Kling) · ChinaCommercial use allowed

Animates a portrait from a reference video: an actor's facial expressions and head turns are transferred to the photo. Runs fast even on a weak GPU.

DetailsAvatarsMultiTalk / InfiniteTalkMeituan · ChinaCommercial use allowed

Dubbing and talking characters built on Wan: MultiTalk handles dialogue between several people, InfiniteTalk re-dubs videos of any length with facial and body motion.

DetailsAvatarsSadTalkerXi'an Jiaotong University and Tencent AI Lab · ChinaCommercial use allowed

An older lightweight talking-head model: one photo plus audio becomes a video. Runs on weak hardware, but quality is noticeably below newer models.

Details

Source: github.com/TMElyralab/MuseTalk. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.