It's so capable at some things, and others are garbage.
I uploaded a photo of some words for a spelling bee and asked it to quiz my kid on the words. The first word it asked, wasn't on the list. After multiple attempts to get it to start asking only the words in the uploaded pic, it did, and then would get the spellings wrong in the Q&A. I gave up.
Will you offer this without a subscription fee?
I like it but for this it should just be a small voice model running on device, not cloud - especially given you don't use APIs.
I think you'll get a lot of adoption if it doesn't have a subscription or cloud requirement.