Building a voice agent for an Ionic React app

With Alan AI SDK for Ionic, you can create a voice agent or chatbot and embed it to your Ionic React app. The Alan AI Platform provides you with all the tools and leverages the industry’s best Automatic Speech Recognition (ASR), Spoken Language Understanding (SLU) and Speech Synthesis technologies to quickly build an AI agent from scratch.

In this tutorial, we will create a simple Ionic app with three tabs. The app users will be able to click the voice agent button and give custom voice commands on each tab, and Alan AI will reply to them.

What you will learn

  • How to add a voice interface to an Ionic React app

  • How to write simple voice commands for an Ionic app

What you will need

To go through this tutorial, make sure the following prerequisites are met:

  • You have signed up to Alan AI Studio.

  • You have created a project in Alan AI Studio.

  • The environment for using the Ionic framework is properly set up. For details, see Ionic documentation.

Step 1: Install the Ionic CLI

Run the following command to install the Ionic CLI:

Terminal
npm install -g ionic

Note

For this tutorial, we do not need the free Ionic Appflow SDK. If the Ionic CLI asks you during the installation process: Install the free Ionic Appflow SDK and connect your app? (y/n), choose no.

Step 2: Create a template Ionic app and run it

We will be using a React app template with tabs.

  1. Navigate to the folder in which the app will reside and run the following command:

    Terminal
    ionic start alan-react-ionic tabs --type=react
    
  2. Switch to the folder with the app:

    Terminal
    cd alan-react-ionic
    
  3. Run the app:

    Terminal
    ionic serve
    
  4. In the browser, a new window with the app will be opened. Make sure you see the right UI:

    ../../../_images/ionic-ang-template.png

Step 3: Install Alan AI SDK for Cordova and Alan AI Web components

We need to add the Alan AI SDK for Cordova component and the Alan AI Web component to the app.

  1. In the app folder, install the Alan AI SDK for Cordova component:

    Terminal
    npm install @alan-ai/cordova-plugin-alan-voice --save
    
  2. Install the Alan AI Web Component package:

    Terminal
    npm install @alan-ai/alan-button --save
    

Step 4: Add the Alan AI button to the app

Now we need to update our app to add the Alan AI button to it.

  1. Create a wrapper component for the Alan AI button. To do this, in the src/components folder, create the AlanBtn.tsx file with the following content:

    AlanBtn.tsx
    import React, {
      useEffect,
      useRef,
    } from 'react';
    import { withRouter } from 'react-router';
    
    const AlanBtn: React.FC = (props: any) => {
      const alanBtnComponent = useRef<any>(null);
    
      useEffect(() => {
        alanBtnComponent.current.addEventListener('command', (data: CustomEvent) => {
          const commandData = data.detail;
    
          if (commandData.command === 'command') {
            /* Call client code that will react to the received command */
          }
        });
       }, []);
    
      return <alan-button ref={alanBtnComponent} alan-key="YOUR_KEY_FROM_ALAN_STUDIO_HERE" />;
    };
    
    export default withRouter(AlanBtn);
    
  2. In the alan-button tag above, we need to replace YOUR_KEY_FROM_ALAN_STUDIO_HERE with the Alan AI SDK key for our Alan AI Studio project. In Alan AI Studio, at the top of the code editor, click Integrations, copy the code provided in the Alan SDK Key field and paste this code to alan-key.

    ../../../_images/alan-sdk-key-react.png
  3. In the src folder, open the App.tsx file and update it to add the Alan AI button.

    1. At the top of the file, add the import statement for the Alan AI button component:

      App.tsx
      import AlanBtn from './components/AlanBtn';
      
    2. Inside the IonReactRouter component, add <AlanBtn />:

      App.tsx
      const App: React.FC = () => (
        <IonApp>
          <IonReactRouter>
            <AlanBtn />
          </IonReactRouter>
        </IonApp>
      );
      

      see full source

  4. In the src folder, create the typescript declaration file named alan-btn.d.ts with the following content:

    alan-btn.d.ts
    declare namespace JSX {
      interface IntrinsicElements {
        [tagName:string]: any
      }
    }
    
  5. The final step is to add the Alan AI button loader to the entry point of our app. In the src folder, open the index.tsx file and add the following:

    index.tsx
    import {
      applyPolyfills,
      defineCustomElements,
    } from '@alan-ai/alan-button/dist/loader';
    
    applyPolyfills().then(_ => {
      defineCustomElements();
    });
    

    see full source

Run the app. On all app tabs, we can see the Alan AI button. Click it and say: Hello.

Step 5. Add voice commands

Let’s add some voice commands so that we can interact with Alan AI. In Alan AI Studio, open the project and in the code editor, add the following intents:

Dialog script
intent('What is your name?', p => {
    p.play('It is Alan, and yours?');
});

intent('How are you doing?', p => {
    p.play('Good, thank you. What about you?');
});

Now in the app click the Alan AI button and ask: What is your name? and How are you doing? The AI agent will give responses provided in the intents.

What’s next?

You can now proceed to building a voice interface with Alan AI. Use the following resources: