AvatarsVideo

LatentSync

Matches lip movements in an existing video to a new voice track. Version 1.6 works at 512 pixels and produces a sharper face.

Developer
ByteDance, China
First release
Jan 2025
Latest release
Jun 2025
Sizes
requires 8–18 GB of VRAM
License
Commercial use with conditionsWeights are OpenRAIL++ (commercial use with usage restrictions), code is Apache 2.0; the built-in InsightFace face detector is non-commercial and must be replaced for business use
Running
On your own serverNeeds a GPU
Industries
Media and production, Marketing and content, Education
Deploy on your server Hugging Face GitHub

What it does

  • Dubbing videos into another language with lip sync
  • Editing lines in finished video without reshooting
  • Talking avatars for training courses

Where it is used

Video productionMarketingOnline learning

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. LatentSync 1.6 (512 пикселей)
  2. LatentSync 1.5
  3. LatentSync 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 LatentSync be used in a commercial project?

With conditions. License: Weights are OpenRAIL++ (commercial use with usage restrictions), code is Apache 2.0; the built-in InsightFace face detector is non-commercial and must be replaced for business use. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does LatentSync 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 LatentSync support Russian?

Language does not matter for this model: it does not work with text.

Where can I download LatentSync and what does it cost?

The LatentSync 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

AvatarsMuseTalkTencent Music (Lyra Lab) · ChinaCommercial use allowed

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

DetailsAvatarsWav2LipIIIT Hyderabad · IndiaNon-commercial only

The classic lip-to-audio sync model, still popular in hobbyist setups. Lip movements are accurate but the face looks blurry; the license is non-commercial.

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.

Details

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