Understand your videos with local frames and audio.
Extracts video frames and optional local transcripts to help explain a video's contents.
When to use it
Use to understand a video, transcribe its audio locally, or extract frames for visual analysis without API keys.
Give it a local video file; it produces extracted frame images and JSON containing video metadata and optional transcription data.
What you provide
Requires Python 3 to run the bundled video-processing script.
Requires ffmpeg for frame and audio extraction.
This skill
frame_%04d.jpg
Overwrites existing extracted frame images (irreversible)
openai-whisper
Installs openai-whisper after prompting