Question

I want to be able to record a word/words that I can then later use as a voice command. I've seen examples of how to set up the voice commands but can you use the same engine to output the voice input as text?

BTW I'm using the Kinect for windows sdk

Was it helpful?

Solution

You want to look into the SAPI (Microsoft Speech API). It's what the speech to text and text to speech capabilities in Windows and Kinect both use. I'll let you read up on it, but yes you can output voice into text although this works much more accurately with a predefined dictionary of words to recognize.

Licensed under: CC-BY-SA with attribution
Not affiliated with StackOverflow
scroll top