In this project, I created a system where I was able to use spoken commands to control what my screen displays.
In particular, I implemented the following three behaviors: "draw rectangle", “draw circle", and "on" / "off".
Implementation
I sent the audio from my microphone to the Google Speech API so that it could be parsed and returned to me. If that response contained the phrase, “draw circle,” “draw rectangle,” etc, I would call the corresponding function in my code that handled drawing the shape on the screen or turning the display on/off.
