Media Understanding

Use Gemini's multimodal capabilities to analyze local video and audio files. Video covers both the picture and the audio track; audio covers speech, music, and ambient sound.

Directory layout

media-understanding/
├── SKILL.md                        # This file
└── scripts/
    ├── analyze_video.py            # Local video file → analysis
    └── analyze_audio.py            # Local audio file → analysis

What this skill can do