General skillMedia, audio and video
watch-video
Download, transcribe, and selectively inspect videos for agent analysis
- Stars
- 3
- Forks
- 0
- Updated
- Updated Jun 2, 2026
MIT
Download, transcribe, and selectively inspect videos for agent analysis
watch-video uses yt-dlp to fetch videos or accept local files, takes captions when available, falls back to local whisper.cpp transcription, and extracts adaptive video frames with ffmpeg. The agent receives metadata, a transcript, and a frame index so it can inspect only the visuals needed for an answer, with fast, balanced, and accurate modes controlling cost. No API key or third-party transcription service is required, but local tools and an optional Whisper model are needed; Claude Desktop is not supported.
Resource types
Use cases
Platforms
Runtime
Turn character references into prompts for game gameplay videos.
Download audio from one Bilibili video or an uploader's full catalog.
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Animate routes, locations, and regions into editorial map videos
Create finished AI videos across multiple models from one Claude Code workflow.