Video OCR

Extracts frames from a video at a configurable FPS using ffmpeg, optionally deduplicates visually similar frames using perceptual hashing (aHash), then runs Apple Vision OCR on each kept frame in parallel.

When to use

Use this skill when the user wants to extract text from a video -- for example lecture recordings, tutorial screencasts, or presentation recordings where on-screen text changes over time.

Usage

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/video_ocr.py <video_file> \
  [-o output.jsonl] \
  [--fps 3.0] \
  [--workers 8] \
  [--dedupe] [--dedupe-threshold 0.15] [--hash-size 8] \
  [--frames-out <dir>] \
  [--markdown <output.md>] [--markdown-images]