Claude Video Vision
A perception layer that gives Claude Code the ability to watch and understand videos. Extracts frames via ffmpeg and processes audio through multiple configurable backends (Gemini API, local Whisper, or OpenAI Whisper API). Claude receives the frames as images plus an audio transcription with timestamps and reasons about them together. Includes an interactive setup wizard, adaptive extraction (fps, resolution, and time ranges automatically adjust to the user's question), and auto-download of Whi
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Productivity — see all ranked ›
Work: Video editing
Who it is for: Creator / video
“Only tested on macOS with whisper.cpp, says so; YouTube transcript precedence is ordered”
- tashan score: 71.0
- Expertise: 86.0 (deep)
- Adoption: 1 repos
- Health: active
- GitHub stars: 1,044
- Contributors: 6
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:jordanrendric/claude-video-vision/claude-video-vision
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›