Vibe Coding Discoverclaude-video-vision
View on GitHubGive Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis
A Claude Code plugin and MCP server that extracts video frames with ffmpeg and provides audio transcripts or event analysis using Gemini, Whisper, or OpenAI. Supports local processing, YouTube URLs, and timestamp-focused video inspection.
Use Cases
Summarize videosInspect video framesFind on-screen text at a timestampTranscribe speech with timestampsAnalyze YouTube videosReview screen recordings and bug reports
Built With
- Language
- TypeScript
- Frameworks
- Model Context Protocol · Claude Code
Tags
video analysis · multimodal · Claude Code · MCP server · frame extraction · audio transcription · YouTube · local inference