Hey, so I am trying to create a program that combines face tracker with a voice recognition to text software to create an app in which the speech that someone is saying appears as a mask on their face in real time. I have been looking into windows API, open mind speech, and IBM Watson API. I have a mac so I believe IBM Watson API will work the best but am new to coding and am not sure how to bring this program in, most posts that I have been reading have mentioned this may be complicated. If anyone has advice or tips for using voice recognition with a text output on a mac with Xcode I'm all ears. Thanks.