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
Text-to-video generation up to 60 seconds
Animate static images into video
Extend and fill existing video footage
Temporal consistency across frames
Complex scene composition with multiple characters
Realistic physics and lighting simulation
Dynamic camera movements (pan, zoom, track)
High-resolution output up to 1080p
Object permanence for long sequences
Support for detailed text prompts and styles
