HKUST-C4G/AnyTalker
Generates multi-person talking videos from audio
View on index · View in 3D Map
Related repos
- Create videos of multiple characters having conversations or singing together, all driven by audio input
- Generates talking videos of any length from audio
- Chat with videos through long-context processing
- turn a photo and audio into a talking video with AI
- Generates talking faces from audio at 40 FPS
- Framework for video understanding and generation
- Generates talking faces from audio with motion transfer
- generates synchronized talking head videos from audio and reference images
- audio-driven video dubbing with unlimited length and accurate lip sync
- speech-to-text with WhisperPlus, YouTube audio support
