Question

A field-service team photographs handwritten equipment inspection notes on tablets. A developer wants to build a lightweight app in Azure AI Foundry that accepts each photo, reads the handwritten text, and returns a plain-text transcription that a technician can review. The developer wants to send the image directly to a deployed model in a single prompt without building a separate document-parsing pipeline. Which approach best fits this requirement?

Accepted Answer

Deploy a multimodal model in Foundry and pass the image as visual input in the prompt, asking the model to transcribe the handwritten text

Answer

Deploy a text-only generative model and paste the handwritten note contents into the user prompt as plain text

Answer

Deploy a text-to-speech model in Azure Speech to convert the notes into an audio transcription

Answer

Deploy an image-generation model and prompt it to recreate the handwritten note as a new image