Android Speech to Text Tutorial

Android comes with a built in feature for Speech to Text.
This is really helpful when you want to provide navigation in your app through voice commands.

When you say something in the app, your voice will be streamed to the server and the server will convert it to text and send back.

You can also have offline speech recognition.

Enable the Offline mode

Right now all the devices are not supporting offline speech input. However you can follow this discussion to enable offline speech input for supported devices.

You have to download offline speech packages.

1. On your device go to Settings -> Language and Input. Click on icon on Google voice input.
2. Under ALL tab select the language you want to download.
3. Once the language package downloaded, you can see it under INSTALLED tab.

Code

1. 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

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

Layout

<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:background="@drawable/bg_gradient"
    android:orientation="vertical" >
 
    <TextView
        android:id="@+id/txtSpeechInput"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:layout_alignParentTop="true"
        android:layout_centerHorizontal="true"
        android:layout_marginTop="100dp"
        android:textColor="@color/white"
        android:textSize="26dp"
        android:textStyle="normal" />
 
    <LinearLayout
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:layout_alignParentBottom="true"
        android:layout_centerHorizontal="true"
        android:layout_marginBottom="60dp"
        android:gravity="center"
        android:orientation="vertical" >
 
        <ImageButton
            android:id="@+id/btnSpeak"
            android:layout_width="wrap_content"
            android:layout_height="wrap_content"
            android:background="@android:color/transparent"
            android:src="@drawable/ico_mic" />
 
        <TextView
            android:layout_width="wrap_content"
            android:layout_height="wrap_content"
            android:layout_marginTop="10dp"
            android:text="@string/tap_on_mic"
            android:textColor="@color/white"
            android:textSize="20sp"
            android:textStyle="normal" />
    </LinearLayout>
 
</RelativeLayout>

MainActivity

 
import java.util.ArrayList;
import java.util.Locale;
 
import android.app.Activity;
import android.content.ActivityNotFoundException;
import android.content.Intent;
import android.os.Bundle;
import android.speech.RecognizerIntent;
import android.view.Menu;
import android.view.View;
import android.widget.ImageButton;
import android.widget.TextView;
import android.widget.Toast;
 
public class MainActivity extends Activity {
 
    private TextView txtSpeechInput;
    private ImageButton btnSpeak;
    private final int REQ_CODE_SPEECH_INPUT = 100;
 
    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);
 
        txtSpeechInput = (TextView) findViewById(R.id.txtSpeechInput);
        btnSpeak = (ImageButton) findViewById(R.id.btnSpeak);
 
        // hide the action bar
        getActionBar().hide();
 
        btnSpeak.setOnClickListener(new View.OnClickListener() {
 
            @Override
            public void onClick(View v) {
                promptSpeechInput();
            }
        });
 
    }
 
    /**
     * Showing google speech input dialog
     * */
    private void promptSpeechInput() {
        Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
        intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
                RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
        intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, Locale.getDefault());
        intent.putExtra(RecognizerIntent.EXTRA_PROMPT,
                getString(R.string.speech_prompt));
        try {
            startActivityForResult(intent, REQ_CODE_SPEECH_INPUT);
        } catch (ActivityNotFoundException a) {
            Toast.makeText(getApplicationContext(),
                    getString(R.string.speech_not_supported),
                    Toast.LENGTH_SHORT).show();
        }
    }
 
    /**
     * Receiving speech input
     * */
    @Override
    protected void onActivityResult(int requestCode, int resultCode, Intent data) {
        super.onActivityResult(requestCode, resultCode, data);
 
        switch (requestCode) {
        case REQ_CODE_SPEECH_INPUT: {
            if (resultCode == RESULT_OK && null != data) {
 
                ArrayList<String> result = data
                        .getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);
                txtSpeechInput.setText(result.get(0));
            }
            break;
        }
 
        }
    }
 
    @Override
    public boolean onCreateOptionsMenu(Menu menu) {
        // Inflate the menu; this adds items to the action bar if it is present.
        getMenuInflater().inflate(R.menu.main, menu);
        return true;
    }
 
}