ScribeMe

This is the utility I have been waiting for to combine extracted text with image descriptions. It inserts the images for each page at the end of the text.
You will need to pay for a subscription of 250 or 500 images a month before testing this app. I think it has potential, but needs to expand more before it's ready for prime time. For example, you can browse your file history, and read your already generated files, but there is no way to directly export them. You can use VoiceOver's ccopy speech to clipboard feature since, at least for me in braille, the text shows up as one element. I've been able to use copy speech to clipboard and then paste the content into an email or note.
Having the share sheet so that I could export the file to, for example, Dropbox for use elsewhere would be helpful. Good idea, but it needs a bit more development.