MultiTalk Articles

MultiTalk: A State-of-the-Art Model for Multi-Character Dialogue Generation with 98.7% Speech-Visual Alignment Accuracy!

2026-07-02 by boardor

Developed by Sun Yat-sen University, Meituan, and Hong Kong University of Science and Technology, MultiTalk enables the generation of multi-character dialogue videos. It achieves state-of-the-art performance in synchronizing speech with lip movements and supports interactions between characters, objects, and scenes through prompts. Related Links Homepage: https://meigen-ai.github.io/multi-talk/ Code: https://github.com/MeiGen-AI/MultiTalk Paper: https://arxiv.org/abs/2505.22647 Paper Introduction In recent years, … Read more

Cutting-Edge Technology on GitHub: MultiTalk Generates Movie-Level Dialogue Scenes from a Photo and Audio

2026-02-15 by boardor

Read to the end for the project address and follow for gifts! MultiTalk: A New Era of Audio-Driven Multi-Person Dialogue Video Generation In today’s rapidly advancing field of artificial intelligence, video generation technology is experiencing unprecedented breakthroughs. MultiTalk, developed by the MeiGen-AI team, is a dialogue video generation model that can create interactive dialogue videos … Read more

MeiGen-MultiTalk: Enabling Multi-Person Interactive Video Generation from a Single Photo

2025-12-21 by boardor

Reposted from Big Company Talk Recently, Meituan launched the audio-driven multi-person dialogue video generation framework MultiTalk, which has been open-sourced on GitHub. It introduces the innovative L-RoPE binding technology, which accurately addresses the challenges of multi-audio streams and character misalignment through label rotation positional encoding. This framework innovatively employs local parameter training and multi-task learning … Read more

MultiTalk: The Ultra-Realistic Digital Human for Group Conversations is Here! Essential for Karaoke, Covering Realistic Cartoon Animals, Easily Generate 15-Second Long Videos

2025-12-21 by boardor

❝ 🌹Hello everyone! Welcome toPoLang‘s homepage. Thank you for your support and encouragement. On the road of AIGC exploration, I willwalk with you. If you like it, pleasestar and follow PoLang or scan the code at the end of the article to join the discussion group! 1: Introduction to MultiTalk In previous articles, we introduced … Read more

Impressive! MultiTalk Open Source with Lip Sync Accuracy Exceeding 8.53 Points

2025-12-16 by boardor

This Article Overview Recently, the MultiTalk project, open-sourced by Sun Yat-sen University, Meituan, and Hong Kong University of Science and Technology, is a novel framework for audio-driven multi-person dialogue video generation. Given a multi-stream audio input, a reference image, and a prompt, MultiTalk generates a video that features interactions following the prompt, with lip movements … Read more

The First Multi-Character Digital Human Open Source Project MultiTalk: Supporting Karaoke, Realistic Cartoons, and Animal Generalization with Low-Cost Solutions

2025-12-11 by boardor

The First Multi-Character Digital Human Open Source Project MultiTalk: Supporting Karaoke, Realistic Cartoons, and Animal Generalization with Low-Cost Solutions The recently open-sourced multi-party dialogue audio-driven digital human projectMultiTalk has gained significant attention in the digital human community, natively supportingsingle,multi-party dialogue, capable of drivingrealistic,cartoon tasks, and can performkaraoke, with impressiveanimal generalization capabilities. My test results show … Read more

MultiTalk: A Quick Look at Realistic Multi-Person Dialogue and Singing with Cartoon and Animal Digital Avatars

2025-12-11 by boardor

❝ 🌹Hello everyone! Welcome to PoLang‘s homepage. Thank you for your support and encouragement. On the road of AIGC exploration, I will be with you all the way. If you like it, please star and follow PoLang or scan the code at the end of the article to join the discussion group! 1: Introduction to … Read more

MultiTalk: KJ Achieves Over 6x Acceleration with Ultra-Realistic Digital Singing Avatars! Supports Realistic Cartoon and Animal Generalization for 15-Second Long Videos

2025-12-11 by boardor

From Solo Comedy to Group Debate: Sun Yat-sen University & Meituan Open Source MultiTalk: A State-of-the-Art Model for Multi-Character Dialogue Generation with Voice-Visual Alignment Accuracy of 98.7%!

2025-12-07 by boardor

MultiTalk, open-sourced by Sun Yat-sen University, Meituan, and Hong Kong University of Science and Technology, enables the generation of multi-character dialogue videos. It achieves state-of-the-art performance in synchronizing voice with lip movements and supports interactions between characters, objects, and scenes through prompts. Related Links Homepage: https://meigen-ai.github.io/multi-talk/ Code: https://github.com/MeiGen-AI/MultiTalk Paper: https://arxiv.org/abs/2505.22647 Paper Introduction In recent years, … Read more