> Controlling lights is easily an entire second faster
How long time did it used to take VS how long time does it take now? I'm not sure "an entire second faster" is sarcasm here, big improvement or what.
How long time did it used to take VS how long time does it take now? I'm not sure "an entire second faster" is sarcasm here, big improvement or what.
I think the voice recognition is async now. It's streaming the data to a model. Before it would wait until the command was finished then send the .wav file off to a model.