Proof-of-concept Unity application using arbitrary voice commands to control the placement of objects on the screen.
Copyright (c) 2016 Aaron Faucher MIT License
Wit.ai has received a major overhaul since Facebook Messenger's bot release earlier this year. Currently, Wit3D uses the legacy API response format, in which JSON responses are parsed into
entities. I will be working in the coming months to reformat Wit3D to work with
actions, the new Wit.ai features. Until then, unless you have a pre-existing Wit.ai app using the legacy reponse format, Wit3D won't work for you. Sorry for the inconvenience, and stay tuned!
View a demo of Wit3D in action here: https://www.youtube.com/watch?v=QRx37mivPiQ
Augmented reality proof-of-concept demonstration: https://www.youtube.com/watch?v=34RkapT_IXQ
- Download and open the Unity project folder.
- Open the
- Run the scene.
- Voice a command to the scene by:
- Press the spacebar
- Voice your command i.e. "Put the box on the chair."
- Release the spacebar
How it works
While the spacebar is being held, Unity records a sample of your voice from the microphone. On release of the spacebar, it streams this file to Wit.ai, where the command is processed and interpreted. Wit.ai returns a JSON response containing a 'subject' [i.e. box] and 'destination' [i.e. chair] from the command. This JSON response is parsed by Unity, which identifies the GameObjects by name in the scene.
While this is a relatively simple example, building a bridge between Unity and Wit.ai allows developers to leverage the powerful Wit.ai NLP engine for their AR/VR applications. End users can now interact with AR/VR scenes using their voice, with Wit.ai taking on the role of interpreting these commands.