The project is simple in concept: build an interactive audio game that runs on a mobile device using voice commands to move from scene to scene (altering environmental sound as the player moves about the audio environment).

I need to know if Pd can handle voice Recognition using either the native API of the device or some sort of patch, to trigger branched dialogue selection. Also, how easy is it to port over to Android or iOS?

My other main concern is time. I have until December to get an example rolling, and I need to know if I'm going to need to learn multiple programming languages and coding tricks before I can even think about getting a small dialogue tree working. If so, I'll probably just program it in the native API...