claude-video-vision
★ 616jordanrendric
This plugin extracts video frames via ffmpeg and audio via configurable backends (Gemini API, local Whisper, or OpenAI), sending both to Claude for direct multimodal understanding. It supports YouTube URLs, adaptive parameter selection based on user intent, and offers an interactive setup wizard for configuration.
2 commands · 1 agent · 1 skill · 1 MCP server
#video-analysis#multimodal-perception#ffmpeg#youtube-support