AI Disruption

AI Disruption

Share this post

AI Disruption
AI Disruption
OmniTalker: Free to Use! Alibaba's Tongyi Model Upgraded with SOTA Ultra-Realistic Audio-Video Generation
Copy link
Facebook
Email
Notes
More

OmniTalker: Free to Use! Alibaba's Tongyi Model Upgraded with SOTA Ultra-Realistic Audio-Video Generation

OmniTalker: Free AI video generator by Alibaba. Create ultra-realistic digital humans with voice & expressions from any reference video.

Meng Li's avatar
Meng Li
Apr 17, 2025
∙ Paid
2

Share this post

AI Disruption
AI Disruption
OmniTalker: Free to Use! Alibaba's Tongyi Model Upgraded with SOTA Ultra-Realistic Audio-Video Generation
Copy link
Facebook
Email
Notes
More
1
Share

"AI Disruption" Publication 5900 Subscriptions 20% Discount Offer Link.


Recently, Alibaba's Tongyi Laboratory launched a new digital human video generation model called OmniTalker. By simply uploading a reference video, it can learn the expressions and voice of the person in the video and even mimic their speaking style.

Compared to traditional digital human production workflows, this method effectively reduces production costs, enhances the realism and interactive experience of generated content, and meets a broader range of application needs.

Currently, the project has opened access for public testing on the ModelScope community and HuggingFace, providing over a dozen templates that anyone can use for free.

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 Meng Li
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More