Media Understand

Media Understanding

Analyze multimedia content via Maxgent FAL API proxy, using the default route.

Supported Formats

Prerequisites

1. MAX_API_KEY environment variable (auto-injected by Max)
2. Bun 1.0+ (built into Max)

Routing

1. default
   • Endpoint: openrouter/router/openai/v1/chat/completions
   • Model: DEFAULT_MM_MODEL, defaults to google/gemini-2.5-pro (override with --model)

Usage

bun skills/media-understand/media-understand.js \
  --media PATH_OR_URL --prompt "PROMPT" \
  [--language chinese|english] [--model MODEL_ID] \
  [--max-tokens N] [--temperature X]

Parameters:

• --media: local file path or YouTube URL
• --prompt: analysis question
• --language: chinese (default) or english
• --model: override the default model
• --max-tokens: max output tokens (default 4096)
• --temperature: sampling temperature (default 0.2)

Examples

# Image OCR
bun skills/media-understand/media-understand.js --media ./screenshot.png --prompt "extract all text from this image" --language english

# Video summary (YouTube)
bun skills/media-understand/media-understand.js --media "https://youtube.com/watch?v=xxx" --prompt "summarize this video" --language english

# Local audio analysis
bun skills/media-understand/media-understand.js --media ./meeting.m4a --prompt "summarize key points and list action items" --language english

Instructions

1. Check MAX_API_KEY.
2. Identify media type and validate size limits.
3. Analyze using the default route; override the model with --model if needed.
4. Local images/videos/audio are auto-uploaded via FAL upload proxy before analysis.
5. On success, return readable text.
6. On failure:
   • HTTP 402 (insufficient credits): Stop immediately. Do NOT retry. Tell the user their API credits are exhausted.
   • Other errors: retry once with a different model. If it fails again, stop and clearly indicate whether it's an upload / proxy / model parameter issue.