claude-video-vision

claude-video-vision

Empowers Claude with the ability to view and understand videos, supporting frame extraction and multimodal audio analysis.

MCPDevOpen source
Type
MCP
Transport
stdio
Open source
Yes
GitHub Stars
★ 1.0k
Source
mcp-github

Overview

Claude Video Vision is a Claude Code plugin that extracts video frames using ffmpeg and processes audio through multiple backends (Gemini API, local Whisper, or OpenAI API). Claude can directly see video frames and read audio transcriptions with timestamps. This plugin functions as a perception layer, not an interpretation layer. Users can configure it via a setup wizard and analyze videos using the `/watch-video` command. Ideal for developers needing AI to understand video content.

Capabilities

  • Multimodal perception: viewing video frames and reading audio transcriptions
  • Supports direct input of YouTube URLs
  • Flexible choice between cloud APIs or local processing
  • Adaptive frame extraction parameter tuning
  • Automatic installation of Whisper model
  • Interactive configuration wizard

Use cases

Analyzing language in tutorial videosSummarizing long-form video contentDetecting specific text within videosExtracting information from YouTube videos

Setup

Requires: Node.js 20+ffmpegyt-dlp (可选)API Key (根据后端)
Run the following commands in Claude Code: "\plugin marketplace add https://github.com/jordanrendric/claude-video-vision" and "/plugin install claude-video-vision"

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I configure the backend?

Run the "/setup-video-vision" wizard to configure.

Which backends are supported?

Supports Gemini API, local Whisper, and OpenAI API.

Do I need an API Key?

An API key may be required depending on the selected backend.

Related skills