analyze-video

What problem does it solve?

Audio transcripts lack visual context, making it hard to understand the full story of a video. This Skill enriches transcripts with detailed visual descriptions, providing a comprehensive overview for intelligent editing.

Core Features & Use Cases

• Frame Extraction: Uses FFmpeg to intelligently extract key frames from video files.
• AI Visual Analysis: Analyzes extracted frames to generate descriptive text about subjects, settings, and actions.
• Visual Transcript Creation: Integrates visual descriptions directly into the audio transcript, creating a "visual transcript" for rough cut generation.
• Use Case: After transcribing a product review video, use this skill to add descriptions like "Close-up of product packaging" or "User demonstrating feature" at relevant timestamps, making the transcript much more useful for editing.

Quick Start

Analyze the video at '/path/to/my/product_review.mov' and add visual descriptions to its transcript for the 'product-launch' library.