AI Voice/Image Tool for Documentation

Description: I deal with a lot of products/inventory and constantly need to document details about them, descriptions, condition notes, categorization. Doing this manually by typing everything out takes forever. I'm looking for someone to build me a simple tool where I can either speak into it or upload a photo of a product, and the AI automatically generates a written description, suggests a category, and flags any notable details, turning a photo or voice note into ready-to-use text. What I need: Upload a photo or record a short voice note about a product AI generates a clean written description automatically Suggests category/tags based on what it sees or hears Simple interface, doesn't need to be fancy, just functional Open to suggestions on the best approach. Timeline: Quick turnaround preferred