Choose Your Version
v2.0
Latest#1 Ranked AI Video Model
Unified multi-modal audio-video generation. Real face support, native audio, multi-shot editing, 2K resolution
2K resolution, 6 aspect ratios
Real face input support
Native audio-video generation
Up to 15s multi-shot editing
Learn More
v1.5 Pro
Native Audio-Visual Sync
4.5B parameters, millisecond-level audio-visual sync, 9-language lip-sync support
1080p HD output
Native audio sync
9 languages supported
60s fast generation
Learn More
v1.0
Basic Video Generation
Entry-level video generation with Text-to-Video and Image-to-Video support
720p resolution
Text-to-Video
Image-to-Video
30s generation
Learn More
Core Features
Audio Synchronization
Native audio-visual synchronization with multi-language lip-sync support, including English, Chinese, Japanese, and 6 other languages
HD Output
Native 1080p resolution output for professional video production needs
Fast Generation
Complete video generation within 60 seconds, significantly improving creative efficiency
Technical Specifications
Model Parameters4.5B
Video Resolution1080p
Audio SupportSupported
Max Duration60s