We have a web application which loads a 3D model(Build in MAYA) in the browser using Three.js. I need the following things to be added,
- Text To Speech using Amazon Polly.
- Get the Speech Marker from Amazon Polly and then the 3D model needs to use the Speech Marks and Whispering features that are available in Amazon Polly.
I have googled regarding it and found https://aws.amazon.com/sumerian/features/. In Amazon sumerian we have a feature called Sumerian Hosts, but it has predefined models.
So my question is it possible to integrate TTS with speech marks using Amazon Polly for 3D model build in MAYA using Three.js for web application build in nodejs.