Features
Multimodal input: text, up to 9 images, 3 videos, 3 audio
Image-to-video generation
Native audio sync: dialogue, SFX, ambience
4K resolution output on paid plans
30fps stable motion with realistic physics
Conversational in-chat editing with plain English
Multi-shot story building from single prompt
Character consistency across shots
Commercial license on paid plans
No watermark on paid plans
Private generation on paid plans
Multiple AI video models available
AI image generation included
Credit-based system with adjustable quantity on Ultra
Full-length song generation with Lyria 3
AI music video generation via Veo
Stem split and audio effects
Remix and remaster tracks
Personalized style learning
Vibe-code custom audio plugins and games
Publish songs and playlists
Multi-format export (mp3, wav, m4a)
Image and video generation
Concurrent generation support (2-16 tiers)
Member events and early access
Chat with Producer assistant
Create custom DAW instruments
