Features
Multimodal video search across speech, visuals, and on-screen text
Single API endpoint (POST /v1/search) returns timestamped grounded results
Optional AI-generated answer from matched evidence
Relevance scores (0.0–1.0) for each result
Tracking links that redirect to original video source
Keyframe preview thumbnails
Transcript alignment with visual timeline
Desktop app for local media indexing (Mac)
Global overlay and local REST API in desktop app
YouTube and podcast search in desktop app
Open source self-hosting option
Encryption and no-training commitment on user data
Auto-recharge and top-up credit mechanism
Free daily searches (10/day) for evaluation
Mochi 1 open-source text-to-video model
High-fidelity motion with strong prompt adherence
Interactive playground for prompt testing
Open-source code on GitHub and Hugging Face
ComfyUI integration for custom workflows
Command-line interface for batch video generation
Quickstart script (quickstart.sh) for local setup
Credit-based usage (Free, Lite, Standard tiers)
Mochi video generation costs 100 credits
Replay video generation costs 10 credits
No watermark on paid tiers
Commercial usage rights on paid tiers
Early model access on Standard tier
Active research blog with model updates
