- Motion-2 advanced lip-sync (lips, head pose, micro-expressions)
- One-shot animation: photo + audio -> talking video
- Voice cloning from short audio samples
- Multilingual text-to-speech (40+ languages/accents)
- Image-to-video and text-to-video models (Wan, Veo, Sora, Seedance)
- Avatar generator with 40+ artistic styles and 50+ presets
- Avatar library and two-character dialogue support
- API access (openapi) for developers and Motion-2 model