Live Avatar
A real-time streaming avatar of unlimited length. Suits live broadcasts and dialogue, but needs powerful server hardware.
- Developer
- Alibaba (Quark), China
- First release
- Dec 2025
- Latest release
- Jan 2026
- Sizes
- 14B
- License
- Commercial use allowedApache 2.0
- Ready-made builds
- GGUF
- Running
- On your own serverNeeds a GPU
- Industries
- Customer support, Retail and marketplaces, Education
What it does
- Live avatar for customer dialogue
- Endless broadcasts with a presenter
- Interactive characters
Where it is used
Hardware requirements
Versions
- Live Avatar v1.1 (FP8)
- Live Avatar
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.
Frequently asked questions
Can Live Avatar be used in a commercial project?
Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.
What hardware does Live Avatar need?
At minimum: One GPU with 16–80 GB — mid-size 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 Live Avatar support Russian?
Language does not matter for this model: it does not work with text.
Where can I download Live Avatar and what does it cost?
The Live Avatar 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
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
A series of audio-driven talking portraits: from short clips to hour-long 4K videos. Hallo-Live is built for real-time use.
DetailsAvatarsMultiTalk / InfiniteTalkMeituan · ChinaCommercial use allowedDubbing and talking characters built on Wan: MultiTalk handles dialogue between several people, InfiniteTalk re-dubs videos of any length with facial and body motion.
DetailsAvatarsMuseTalkTencent Music (Lyra Lab) · ChinaCommercial use allowedReal-time lip sync: matches the mouth in a video to new audio. Suits video translation and live avatars.
DetailsSource: github.com/Alibaba-Quark/LiveAvatar. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


