ainewsblitz.com

Breaking

Meituan's LongCat Team Open-Sources Avatar Model That Turns One Photo and Audio Into Talking Video

Meituan's LongCat Team Open-Sources Avatar Model That Turns One Photo and Audio Into Talking Video
  • Media Generation
  • Open Source
  • Foundation Models

Meituan's LongCat research team has released LongCat-Video-Avatar 1.5, an open-source framework that generates lip-synced talking videos from a single still image and an audio clip, and published the code and model weights under an MIT license. The system, unveiled on May 21, 2026, builds on the team's earlier LongCat-Video foundation model and is freely available on GitHub and Hugging Face.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year