Image to text Transcription

Hi community and coda team.
I was wondering if there is a way to put a transcript image to text tool within the document (maybe APIs?). Or maybe suggest something like this in the near future.

Sometimes is a book, sometimes is a client reaching out from a different channels. Getting to document the text of those prints and photos is very helpful for me. I wonder if this could be helpful for someone else.

Ref.(log messages of an interaction with a client, along with his file)

Bump on this - I would like to be able to transcribe text from image too.

The are many LLM models with that capabilitiy and also several packs to use them from a doc.