Open-source video generation models and world simulators
Create product videos from links and facts with synthetic presenters
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Freemium
Freemium
Pricing
Free plan: $0/month with 250 lifetime credits. Lite plan: 1,200 credits per month. Standard plan: 5,000 credits per month. Mochi video generation costs 100 credits; replay video costs 50 credits.
Free: script generator and hook generator. Paid subscriptions with monthly credits: Starter $19/month (180 credits), Creator $49/month (540 credits), Studio $99/month (1,200 credits). Quarterly and Yearly billing available at discounts. One-time credit packs: Pack XS $2.99 (20 credits), Pack S $12.9
Key features
Text-to-video generation from written descriptions
Local execution and customization via open-source repository
ComfyUI integration for tailored experience
Interactive playground for testing capabilities
Commercial usage rights on paid plans
MP4 video format with H.264 encoding
Videos up to 5.4 seconds at 30fps
Video download for 30 days after generation
Watermark removal on paid plans
High queue priority for paid users
Import product details from links or enter manually
Edit generated hooks and scripts
Generate 10s or 15s vertical 9:16 videos
Two quality options: Draft 480p or Standard 720p
Review credit cost before rendering
Download completed videos as MP4 files
Compare multiple hook and presenter combinations
Free script and hook generator tools
Review scripts against product facts before publishing
What makes it different
Apache 2.0 licensed open-source model for individual and commercial use
World simulator technology for embodied AI breakthroughs
Team with 55,000+ citations across foundational AI research
Run locally without vendor lock-in
State-of-the-art open text-to-video model
Turn product links directly into video without manual input
Revise messaging without scheduling another presenter shoot
Test multiple creative variations quickly with hook and presenter pairs
Synthetic presenters kept identifiable with responsible use guidelines