media-understand - AI Media Understanding for Images, Videos, and Audio
Uses AI to understand and analyze multimedia content including images, videos, and audio.
Tags
Updated: 2026-02-18Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Describe images
- Extract text from images
- Analyze videos
- Transcribe audio
- Summarize content
- Answer questions about videos
- Detect speakers
Inputs
- Media file path or URL
- MAX_API_KEY
- Prompt text
- Language parameter
Outputs
- Media analysis results
- Text transcripts
- Content descriptions
- Question answers
- Summary text
Requirements
- MAX_API_KEY environment variable
- Bun 1.0+ runtime
- Supported media formats
- Gemini 2.5 Flash access