What problem does it solve? Understanding what a video contains normally requires watching it manually or paying for cloud transcription APIs. This Skill analyzes video files entirely on your local machine, extracting representative frames and transcribing speech without any API keys or external services. ## Core Features & Use Cases - Frame Extraction: Pull key frames using scene-change detection, codec keyframes, or fixed intervals, with automatic subsampling to a configurable frame limit. - Local Audio Transcription: Convert speech to timestamped text using OpenAI Whisper running locally, with selectable model sizes from tiny to large. - Structured JSON Output: Receive video metadata, frame paths with timestamps, and transcript segments in a single machine-readable JSON document. - Use Case: Given a screen recording of a product demo, extract scene-change frames and a full transcript so an AI can visually inspect the frames and summarize the demo content without watching the video. ## Quick Start Analyze the video file demo.mp4 by extracting its key frames and transcribing its audio locally.
