Tencent Opens Sources Hunyuan Voice Digital Human Model: Bringing Images to Life with Speech and Song - AI

7 x 24 Track global technological trends

Hot Topic

Day

News Topic

Tencent Opens Sources Hunyuan Voice Digital Human Model: Bringing Images to Life with Speech and Song

2025-05-29 / Read about 0 minute

Author：小编

Tencent's Hunyuan has unveiled and open-sourced its HunyuanVideo-Avatar voice digital human model. This innovative technology allows users to upload a single image of a person and an audio clip, enabling the model to produce a lifelike video of the individual speaking and singing naturally, complete with lip synchronization and fluid, coordinated movements.

Previous page：Meta Divides AI Department into Two Teams: One for...

Next page：After 25 Years of Refinement, Google's AI Lead: Wh...

Return to List

Hot Reading

2 day ago

Intuit to lay off over 3,000 employees to refocus on AI

2 day ago

Yearslong fight over users' right to tweak smart TV software heads to trial

2 day ago

NanoClaw creator turns down $20M buyout offer, raises $12M seed instead

2 day ago

Google Stitch Launches Real-Time AI Agent, Multiplayer Editing: Figma Charges $15/Seat