Beginner Tutorial

Using a Host and Speech Components

25 minutes

Posted on: January 26, 2018

Learn Sumerian
Using a Host and Speech Components


lip sync

In this tutorial you will learn about:

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
  • Hosts
  • Physics
  • 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:


Watch the video tutorial from the Hosts Video Course.

Step 1: Create a New Scene

  1. From the Dashboard, open or create a new scene.

  2. 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.

  3. Find the entity in the Assets panel and drag the entity (hexagon icon) onto the canvas.