AI-powered hardcoded subtitle extraction and structured notes converter
Enterprise video AI powered by multimodal intelligence for semantic search, analysis, and understanding
Stage
Not given
Established
Founded
Not given
2021
Based in
Not given
US
Pricing model
Freemium
Freemium
Pricing
Free Trial: $0 with 1,200 credits (no credit card required). Credit Packs: 3-Hour Pack $1.50 (1,800 credits), 10-Hour Pack $4 (6,000 credits), 50-Hour Pack $15 (30,000 credits), all one-time purchases. Hardcoded subtitle extraction costs 10 credits per minute, transcript generation 15 credits per mi
Free plan: $0/month with 3 GB storage and 600 minutes of video indexing. Plus plan: $29/month with 50 GB storage. Pro plan: $99/month with 200 GB storage. Custom plans available. Annual billing offers 17% discount.
Key features
Zero typo hardcoded subtitle extraction using AI vision
Converts video to structured markdown notes
Processes 1-hour video to markdown in 20 minutes
Supports 50+ languages
YouTube URL support for direct processing
Automatically deletes videos 24 hours after processing
Generates transcript with proper punctuation and formatting
Audio recognition fallback for videos without subtitles
Semantic video search across entire libraries using natural language
Automatic content segmentation with scene change detection
Compliance and policy risk identification at scale
Automated highlight generation from video libraries
Video insight analysis and pattern detection
Fast indexing at ~60x real-time speed
API and SDK with multiple language support
Jockey AI agent for video search in Claude and ChatGPT
SOC 2 Type II certification and encrypted data handling
What makes it different
Continuous video reading ensures zero missed subtitle frames instead of sampling at fixed intervals
Perfect reconstruction of hardcoded subtitles with background clutter filtering
Structured markdown output ready for Obsidian and knowledge management systems
Same high-accuracy AI engine across all plans
Video-native foundation models trained specifically for video understanding
Processes vision, audio, speech, and on-screen text together in one index
Reasons across full temporal sequences up to two hours, not just frame sampling
Spatiotemporal embeddings make every video moment findable by actual content, not metadata
VidFoil
TwelveLabs