Navigating in an Android app with voice (Kotlin)

While interacting with the voice Agentic Interface built with the Alan AI Platform, users can perform actions in the app with voice. For example, they can give commands to navigate to another screen, select an item in the list, enable or disable options. To achieve this, you need to send commands from the dialog script to the app and handle them in the app.

In this tutorial, we will add voice commands that will allow us to navigate between tabs in the app.

YouTube

If you are a visual learner, watch this tutorial on Alan AI YouTube Channel.

What you will learn

• How to complete tasks in the Android app with voice

• How to navigate in the Android app with voice

• How to send commands from the dialog script and handle them in the Android app

What you will need

For this tutorial, we will use the app created in the Building a voice Agentic Interface for an Android Java or Kotlin app tutorial.

Step 1: Add voice commands to navigate between tabs

First, we need to add new voice commands to navigate between tabs with voice. In Alan AI Studio, open the project and in the code editor, add the following intents:

Dialog script

intent('Open the second tab', p => {
    p.play({command: "openTab", tab: 1});
    p.play('Opening the second tab');
});

intent('Go back', p => {
    p.play({command: "openTab", tab: 0});
    p.play('Going back to the first tab');
});

When we say one of these phrases, two things will happen:

• Alan AI will send the command provided in the intent to the Android app. To send the command, we need to specify a JSON object in the p.play function. Here the object contains the command name — openTab, and the index of the tab to be opened in the app.

• The Agentic Interface will play back the action confirmation to us.

Step 2: Handle commands on the app side

When we say Open the second tab or Go back, Alan AI now sends a command to the Android app. We need to handle this command in the app and make sure an appropriate action is performed. To do this, we will use the onCommand handler.

In the IDE, open the MainActivity.kt file and update the code for handling commands in the Alan AI agentic interface block to the following:

MainActivity.kt

class MainActivity : AppCompatActivity() {
  override fun onCreate(savedInstanceState: Bundle?) {
    val alanCallback: AlanCallback = object : AlanCallback() {
      /// Handling commands from Alan AI Studio
      override fun onCommand(eventCommand: EventCommand) {
        try {
          val command = eventCommand.data
          val commandName = command.getJSONObject("data").getString("command")
          when (commandName) {
            /// Navigating between tabs when the openTab command is received
            "openTab" -> {
              val tab = eventCommand.data.getJSONObject("data").getString("tab").toInt()
              tabs.getTabAt(tab)?.select()
            }
          }
        } catch (e: JSONException) {
          e.message?.let { Log.e("AlanButton", it) }
        }
      }
    };

    /// Register callbacks
    alanButton?.registerCallback(alanCallback);
  }
}

Here is how it works: when the Android app receives the openTab command from the dialog script, the tab index is saved to the tab variable and used to open the necessary tab.

You can test it: run the app, tap the Alan AI agentic interface and say: Open the second tab. The second tab in the app will be open. Then say Go back, and you will get back to the first tab.

What’s next?

Have a look at the next tutorial: Passing the app state to the dialog script.