It's interesting to read that you conceptualize screen readers as rendering a 2-D environment as audio. I'm a very visual/spatial person, but I've always conceptualized them as rendering a tree of GUI widgets, rather than a visual environment. I guess it's the difference between thinking of my desk as a visual collection of objects, and more as an object with an Arduino/RPI in the top drawer, papers and folders in the second, etc. Not saying either is wrong, just that maybe it's a matter of conceptualizing UIs as groups of collected and organized widgets, rather than as laid out on a map. I've come to enjoy developing with React because I can say "here's my workspace for a given task. It has a toolbar containing these related functions, these two loosely-related larger workspaces, etc." Then I let a visual designer come along after and make things look better. :)

Anyhow, I look forward to reading more about your SDK. Where can I learn more? I'm building an app that could benefit from a conversational UI on top of the traditional one and would be interested in reading up on what you offer, particularly as it's meant for blind users too.