Features
Text-to-motion-graphics generation from plain language
Voice cloning (up to 10 voices on Ultra plan)
Export to MP4 up to 4K 60fps
Upload images, Figma designs, Notion docs as input
Audio-to-kinetic-typography from podcasts or lectures
Brand-consistent style across multiple assets
Automatic scene layout, typography, transitions, timing
Edit without full regeneration (color, text, timing)
Native reading of Figma, Notion, YouTube links
Zero prompt anxiety: suggestions based on uploaded content
Supports multiple languages (prompts, voice, on-screen text)
Commercial usage rights on paid plans
Credit-based system with top-up packs
AI music generation from text or lyrics
AI music video generator with scene transitions
AI music extender (adds 30+ seconds)
AI cover song transformation
Add vocals to instrumentals
AI instrumental generator
Vocal remover with 13-stem separation
Voice cloning from short audio samples
AI singing photo (lip-sync from portrait)
AI rap generator (trap, boom bap, drill)
AI background music generation
AI music analyzer (BPM, key, mood, structure)
