I want to have an experience where you act out a scene from your favorite play or movie or TV show in VR and get points for getting the lines right using voice recognition. Due to licensing restrictions, however, I must demonstrate this using something that is in the public domain. So, I will be using the well known balcony scene from Romeo and Juliet by William Shakespeare. You will play Romeo and be looking up at Juliet on the balcony.
You will see all the words in your line but they will not be in order. For example, you might see the following words floating around in space in front of you:
felt never that scars he a jests wound he
The actual line from the scene is "He jests at scars that never felt a wound." So, you will have to say out loud "He" and then using Android speech recognition, I will detect that you got the first word correct and put it into place. Then you will say the second word. This will go on until you have assembled the entire line. Then you will read the whole line once (and I will record the audio of that.)
I will repeat this basic pattern through all the lines of the scene. Then I will generate the whole scene using your audio and a voice actress playing Juliet. If I have time, I will allow you to share this on Facebook.
Log in or sign up for Devpost to join the conversation.