# Claude Video Vision

Lets Claude 'watch' a video: extracts frames via ffmpeg and transcribes audio (Gemini, local Whisper or OpenAI) with timestamps.

* Page: https://agentcut.dev/tools/claude-video-vision/
* Source: https://github.com/jordanrendric/claude-video-vision
* Works with: FFmpeg
* Type: Claude Code plugin (MCP)
* Setup difficulty: easy
* Supported versions: Node.js 24+; yt-dlp optional
* Price: free
* License: MIT
* GitHub stars: 1380
* Last updated: 2026-10-14
* Checked: 2026-10-17

Setup steps:

1. Install Node 24+ and ffmpeg.
2. Install the plugin; the MCP server auto-installs via npx.
3. Set GEMINI_API_KEY or install whisper-cpp.
4. Run /watch-video on a file.

Safety notes:

* Gemini or OpenAI backends send audio to that provider and need an API key; local Whisper keeps it on-device.

More FFmpeg tools: https://agentcut.dev/ffmpeg-mcp/

---
AgentCut: https://agentcut.dev/ · All tools as JSON: https://agentcut.dev/tools.json · Overview for agents: https://agentcut.dev/llms.txt