Video Content Extractor

Extract key frames and text content from video files using ffmpeg and Tesseract OCR.

274326424 Updated

File contents

Video Content Extractor

Extracts key frames from MP4 videos, runs Tesseract OCR, and generates structured Markdown reports.

Usage

In Codex CLI, invoke the skill.

Parameters

Parameter Type Description Default
video_path string Path to the video file required
output_dir string Output directory same as video
interval integer Frame interval in seconds 30
lang string OCR language chi_sim+eng

Requirements

  • FFmpeg on PATH
  • Tesseract OCR with language packs
  • Python 3.8+

274326424/video-content-extractor/tree/main/skills/video-content-extractor commit 3c0dc0aa4b

Frequently asked questions

npx skillmds@latest add 274326424/video-content-extractor-2