That's expensive, slow (listen to a screenreader user some time to see how quickly they operate) and likely only works online.

I'm also not going to shirk my responsibilities as a developer based on a hope that the assistive tech will improve.

It’s expensive for now, slow for now, online for now, but it’s pretty clear that this is the future. If I were blind I’d want it to go here since it would just unlock so much more. Very little software or sites have good accessibility. Open source and indie stuff often has none.

A custom local model trained only for this task seems like a possibility, and could be way smaller than some general purpose model being instructed for this task. I’m thinking screen reader and UI assist only. Could probably be like a 7B quantized model. Maybe smaller.