Basic features free. VIP package from $1K with custom features, full body motion capture, multiplayer, action recording, advanced lens, iPhone capture, 3D scene, avatar effect improvements, and one-to-one service. Contact for details.
Key features
Text-to-video generation
Image-to-video with start and end frames
Generated dialogue and sound effects
Multiple resolution options up to 4K
Vertical and widescreen formats
Multiple model tiers with different quality levels
Longer videos with MiniMax H3 Max
Credit-based pricing system
Automatic refunds for blocked generations
OBS virtual camera for streaming to multiple platforms
40+ pre-built VTuber avatar models
Animation and emote editor with customizable props and effects
AI mocap animation from video with VMotion
Anime pose reference gallery
Weekly content updates with new avatars and assets
What makes it different
Generates sound with video in one pass—dialogue, sound effects and ambient audio all created together with the picture
Independent platform providing access to Google's Veo 3.1 models along with other AI models
Failed generations automatically refunded with credits restored
Can animate photos of adults using image-to-video capability
Advanced facial and hand tracking technology more accurate than open source alternatives
Modular software architecture optimized for performance and lightweight resource usage
Free basic features with unlimited commercial use on VIP plan
Served over 1 million VTubers, Streamers, YouTubers and Artists globally
Veo Video
Live3D