👁️
Vision
Analyze photos with AI
Included
Send a photo and your MONO analyzes it. Identifies products, reads text, describes scenes, extracts data.
About this skill
Vision uses multimodal models to understand images. Can read receipts, identify products to search prices, extract text from photographed documents, describe scenes, and more.
What's included
OCR — extract text from photos
Identify products and search prices
Read receipts and tickets
Describe scenes and images
Example
Photo of menu → 'The cheapest dish is the salad at $89'
Frequently asked questions
How does Vision work in MONO?
Vision uses multimodal models to understand images. Can read receipts, identify products to search prices, extract text from photographed documents, describe scenes, and more.
How much does Vision cost?
Vision is included free in all MONO plans.
Does Vision work on WhatsApp?
Yes. Vision works directly from WhatsApp, Telegram, and Discord. Just send a message to your MONO and it handles everything.