Not only can you use text-to-speech with Amazon Sumerian, Hosts also speak the custom text within the Speech component. This is all done using Amazon Sumerian and the Amazon Polly API to synthesize the speech from the text you provide.
You’ll learn about:
- AWS Configuration
- Cognito Identity Pool ID
- Speech Component
- State Machine
This is the scene we will build in this tutorial. For best results, be sure you are using the latest version of your browser.
Before you begin, be sure you complete the following tasks and tutorials:
- Sign in to Amazon Sumerian with your AWS account
- Download a WebGL-compatible browser. We recommend the latest version of Google Chrome or Firefox Quantum
- All Amazon Sumerian Beginner tutorials
- Speech Component tutorial
- Amazon Cognito Setup Using AWS Cloudformation tutorial
Watch the video tutorial from the Hosts Video Course.
Step 1: Create a New Scene
From the Dashboard, open or create a new scene.
Click Import Assets above the canvas to open the asset library. Choose a Host and add them to your scene. This tutorial uses Preston. Note: We are always adding to the cast of available Hosts. You will have access to more Hosts than what’s shown in the image below.
Find the entity in the Assets panel and drag the entity (hexagon icon) onto the canvas.