Android Speech to Text

Aug 19, 2015 By: Dr. Droid Android Basics, Intent Comment: 1

Android comes with an inbuilt feature speech to text through which you can provide speech input to your app. With this you can add some of the cool features to your app like adding voice navigation(Helpful when you are targeting disabled people), filling a form with voice input etc.,

In the background how voice input works is, the speech input will be streamed to a server, on the server voice will be converted to text and finally text will be sent back to our app.

If you want to do the other way i.e converting text to speech, follow my tutorial Android Text to Speech

Example

In this tutorial, we are going to learn how to use convert Speech/Voice to Text.

Video Demo

1. Create a new project in Eclipse by navigating to File ⇒ New Android ⇒ Application Project and fill required details. By default my activity is MainActivity.java.

2. First create a layout in xml file naming activity_main.xml that contains Button for starting voice recognition and a ListView to display the result.

<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:layout_width="fill_parent"
    android:layout_height="fill_parent"
    android:orientation="vertical" >

    <TextView
        android:layout_width="fill_parent"
        android:layout_height="wrap_content"
        android:gravity="center"
        android:padding="15dp"
        android:text="@string/click_text"
        android:textColor="#0587d9"
        android:textSize="18sp"
        android:textStyle="bold" />

    <Button
        android:id="@+id/speakButton"
        android:layout_width="fill_parent"
        android:layout_height="wrap_content"
        android:layout_margin="5dp"
        android:padding="5dp"
        android:text="@string/click" />

    <ListView
        android:id="@+id/text_listview"
        android:layout_width="fill_parent"
        android:layout_height="fill_parent"
        android:layout_margin="5dp" />

</LinearLayout>

<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"

android:layout_width="fill_parent"

android:layout_height="fill_parent"

android:orientation="vertical" >

<TextView

android:layout_width="fill_parent"

android:layout_height="wrap_content"

android:gravity="center"

android:padding="15dp"

android:text="@string/click_text"

android:textColor="#0587d9"

android:textSize="18sp"

android:textStyle="bold" />

<Button

android:id="@+id/speakButton"

android:layout_width="fill_parent"

android:layout_height="wrap_content"

android:layout_margin="5dp"

android:padding="5dp"

android:text="@string/click" />

<ListView

android:id="@+id/text_listview"

android:layout_width="fill_parent"

android:layout_height="fill_parent"

android:layout_margin="5dp" />

</LinearLayout>

3. Now open your MainActivity.java and add the following lines. There are only two steps by which we can achieve our goal :

Step 1: Starting RecognizerIntent

First we need to create a RecognizerIntent by setting necessary flags such as :

ACTION_RECOGNIZE_SPEECH – Simply takes user’s speech input and returns it to same activity.
LANGUAGE_MODEL_FREE_FORM – Considers input in free form English.
EXTRA_PROMPT – Text prompt to show to the user when asking them to speak.

Step 2: Receiving the speech response
Once the speech input is done we have to catch the response in onActivityResult and take appropriate action needed.

Note : Before doing anything we have to check if the device support Speech Reocgnizer or not.

package com.voice_to_text;

import java.util.ArrayList;
import java.util.List;

import android.content.Intent;
import android.content.pm.PackageManager;
import android.content.pm.ResolveInfo;
import android.os.Bundle;
import android.speech.RecognizerIntent;
import android.support.v7.app.AppCompatActivity;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.ArrayAdapter;
import android.widget.Button;
import android.widget.ListView;

public class MainActivity extends AppCompatActivity {
	private static final int REQUEST_CODE = 1234;
	private static ListView wordsList;
	private static Button speakButton;

	@Override
	protected void onCreate(Bundle savedInstanceState) {
		super.onCreate(savedInstanceState);
		setContentView(R.layout.activity_main);

		init();

	}

	private void init() {
		speakButton = (Button) findViewById(R.id.speakButton);
		wordsList = (ListView) findViewById(R.id.text_listview);

		// Disable button if no recognition service is present
		PackageManager pm = getPackageManager();
		List<ResolveInfo> activities = pm.queryIntentActivities(new Intent(
				RecognizerIntent.ACTION_RECOGNIZE_SPEECH), 0);
		if (activities.size() == 0) {
			speakButton.setEnabled(false);
			speakButton.setText(R.string.recognizer);
		}
		speakButton.setOnClickListener(new OnClickListener() {

			@Override
			public void onClick(View arg0) {
				startVoiceRecognitionActivity();

			}
		});

	}

	/**
	 * Fire an intent to start the voice recognition activity.
	 */
	private void startVoiceRecognitionActivity() {
		Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
		intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
				RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
		intent.putExtra(RecognizerIntent.EXTRA_PROMPT,
				"Voice Recognition Demo...");
		startActivityForResult(intent, REQUEST_CODE);
	}

	/**
	 * Handle the results from the voice recognition activity.
	 */
	@Override
	protected void onActivityResult(int requestCode, int resultCode, Intent data) {
		if (requestCode == REQUEST_CODE && resultCode == RESULT_OK) {
			// Populate the wordsList with the String values the recognition
			// engine thought it heard
			ArrayList<String> matches = data
					.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);
			wordsList.setAdapter(new ArrayAdapter<String>(this,
					android.R.layout.simple_list_item_1, matches));
		}
		super.onActivityResult(requestCode, resultCode, data);

	}

}

package com.voice_to_text;

import java.util.ArrayList;

import java.util.List;

import android.content.Intent;

import android.content.pm.PackageManager;

import android.content.pm.ResolveInfo;

import android.os.Bundle;

import android.speech.RecognizerIntent;

import android.support.v7.app.AppCompatActivity;

import android.view.View;

import android.view.View.OnClickListener;

import android.widget.ArrayAdapter;

import android.widget.Button;

import android.widget.ListView;

public class MainActivity extends AppCompatActivity {

private static final int REQUEST_CODE = 1234;

private static ListView wordsList;

private static Button speakButton;

@Override

protected void onCreate(Bundle savedInstanceState) {

super.onCreate(savedInstanceState);

setContentView(R.layout.activity_main);

init();

}

private void init() {

speakButton = (Button) findViewById(R.id.speakButton);

wordsList = (ListView) findViewById(R.id.text_listview);

// Disable button if no recognition service is present

PackageManager pm = getPackageManager();

List<ResolveInfo> activities = pm.queryIntentActivities(new Intent(

RecognizerIntent.ACTION_RECOGNIZE_SPEECH), 0);

if (activities.size() == 0) {

speakButton.setEnabled(false);

speakButton.setText(R.string.recognizer);

}

speakButton.setOnClickListener(new OnClickListener() {

@Override

public void onClick(View arg0) {

startVoiceRecognitionActivity();

}

});

}

/**

* Fire an intent to start the voice recognition activity.

private void startVoiceRecognitionActivity() {

Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);

intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,

RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);

intent.putExtra(RecognizerIntent.EXTRA_PROMPT,

"Voice Recognition Demo...");

startActivityForResult(intent, REQUEST_CODE);

}

/**

* Handle the results from the voice recognition activity.

@Override

protected void onActivityResult(int requestCode, int resultCode, Intent data) {

if (requestCode == REQUEST_CODE && resultCode == RESULT_OK) {

// Populate the wordsList with the String values the recognition

// engine thought it heard

ArrayList<String> matches = data

.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);

wordsList.setAdapter(new ArrayAdapter<String>(this,

android.R.layout.simple_list_item_1, matches));

}

super.onActivityResult(requestCode, resultCode, data);

}

4. Now, you are all done, run your app and you will get the output as shown in video.

Thanks.

1 Comment

cabot

Sunday, August 26th, 2018

Thanks for this helpful tutorial it was very detailed and to the point.
Here is a related video you can take a look at it to see how you can turn text to video: https://youtu.be/L94717pI14M