I just want to know if Riva and the STT and TTS can be integrated to an 3D model Avatar in VRM o GLB, what I want to do is a chat bot that can lipsync the audio produced by Riva in real time with the Avatar. Is for an mobile app.
I’m not a AI developer, but I want to start a business based on this. So what I want to know is how can I integrate Riva with a 3D model and how can I use the Riva Models in the app I want to develope.
I just want to know what I need to start this project.