Vidu S1: A Real-Time Interactive Video Generation Model

2026-07-03

AI Summary

This work proposes the first video generation system capable of unlimited-duration, high-fidelity synthesis with real-time voice-driven interactive control, overcoming existing limitations in duration, visual quality, and latency. Built upon the TurboDiffusion generative architecture and the TurboServe inference engine, the system delivers blur-free, drift-free video at up to 42 FPS in 540p resolution on consumer-grade GPUs. Users can dynamically modify content through spoken commands and personalize digital avatars by uploading custom images—such as photographs of real people, anime characters, or pets—and combining them with diverse voice timbres. Comprehensive experiments demonstrate that the method achieves state-of-the-art performance across all evaluation metrics while meeting stringent real-time inference requirements. An interactive online demo platform has been deployed to showcase its capabilities.

Abstract

We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment through voice instructions. Vidu S1 supports infinite-length real-time video generation without blurring, drift, or visual distortion. Built with TurboDiffusion and TurboServe, Vidu S1 outputs 540p real-time videos at up to 42 FPS on regular consumer GPUs. Users can upload custom images of real people, anime, and pets, and choose different voice tones for personalized experiences. Experiments show that Vidu S1 achieves the best performance across all test metrics while fully meeting real-time inference requirements. A playable online demo is available at https://vidu.com/vidu-stream.

Problem

• real-time video generation
• interactive video
• voice control
• infinite-length video
• visual consistency

Innovation

• real-time video generation
• voice-controlled interaction
• TurboDiffusion
• infinite-length generation
• personalized digital characters