How to enable Neural Text-to-Speech (NTTS) in Java using Amazon Polly

I am trying to use Amazon Polly to convert text to speech using Java API. As described by Amazon there are several US english voices which support Neural. <https://docs.aws.amazon.com/polly/latest/dg/voicelist.html>

The code I am following to run in Java application is as following:

package com.amazonaws.demos.polly;
import java.io.IOException;
import java.io.InputStream;
import com.amazonaws.ClientConfiguration;
import com.amazonaws.auth.DefaultAWSCredentialsProviderChain;
import com.amazonaws.regions.Region;
import com.amazonaws.regions.Regions;
import com.amazonaws.services.polly.AmazonPollyClient;
import com.amazonaws.services.polly.model.DescribeVoicesRequest;
import com.amazonaws.services.polly.model.DescribeVoicesResult;
import com.amazonaws.services.polly.model.OutputFormat;
import com.amazonaws.services.polly.model.SynthesizeSpeechRequest;
import com.amazonaws.services.polly.model.SynthesizeSpeechResult;
import com.amazonaws.services.polly.model.Voice;
import javazoom.jl.player.advanced.AdvancedPlayer;
import javazoom.jl.player.advanced.PlaybackEvent;
import javazoom.jl.player.advanced.PlaybackListener;
public class PollyDemo {
private final AmazonPollyClient polly;
private final Voice voice;
private static final String JOANNA="Joanna"; 
private static final String KENDRA="Kendra"; 
private static final String MATTHEW="Matthew"; 
private static final String SAMPLE = "Congratulations. You have successfully built this working demo of Amazon Polly in Java. Have fun building voice enabled apps with Amazon Polly (that's me!), and always look at the AWS website for tips and tricks on using Amazon Polly and other great services from AWS";
public PollyDemo(Region region) {
// create an Amazon Polly client in a specific region
polly = new AmazonPollyClient(new DefaultAWSCredentialsProviderChain(), 
new ClientConfiguration());
polly.setRegion(region);
// Create describe voices request.
DescribeVoicesRequest describeVoicesRequest = new DescribeVoicesRequest();
// Synchronously ask Amazon Polly to describe available TTS voices.
DescribeVoicesResult describeVoicesResult = polly.describeVoices(describeVoicesRequest);
//voice = describeVoicesResult.getVoices().get(0);
voice = describeVoicesResult.getVoices().stream().filter(p -> p.getName().equals(MATTHEW)).findFirst().get();
}
public InputStream synthesize(String text, OutputFormat format) throws IOException {
SynthesizeSpeechRequest synthReq = 
new SynthesizeSpeechRequest().withText(text).withVoiceId(voice.getId())
.withOutputFormat(format);
SynthesizeSpeechResult synthRes = polly.synthesizeSpeech(synthReq);
return synthRes.getAudioStream();
}
public static void main(String args[]) throws Exception {
//create the test class
PollyDemo helloWorld = new PollyDemo(Region.getRegion(Regions.US_WEST_1));
//get the audio stream
InputStream speechStream = helloWorld.synthesize(SAMPLE, OutputFormat.Mp3);
//create an MP3 player
AdvancedPlayer player = new AdvancedPlayer(speechStream,
javazoom.jl.player.FactoryRegistry.systemRegistry().createAudioDevice());
player.setPlayBackListener(new PlaybackListener() {
@Override
public void playbackStarted(PlaybackEvent evt) {
System.out.println("Playback started");
System.out.println(SAMPLE);
}
@Override
public void playbackFinished(PlaybackEvent evt) {
System.out.println("Playback finished");
}
});
// play it!
player.play();
}
} 

By default its taking the Standard of the voice of Matthew. Please suggest what needs to be changed to make the speech Neural for the voice of Matthew.

Thanks

Thanks @ASR for your feedback.

I was able to find the engine parameter as you suggested.

The way I had to solve this is:

1. Update the aws-java-sdk-polly version from 1.11.77 (as they have in their documentation) to the latest 1.11.762 in the pom.xml and build the Maven project. This brings the latest class definition for SynthesizeSpeechRequest Class. With 1.11.77 I was unable to see withEngine function in its definition.

<dependency>
<groupId>com.amazonaws</groupId>
<artifactId>aws-java-sdk-polly</artifactId>
<version>1.11.762</version>
</dependency>

2. Updated the withEngine("neural") as below:

SynthesizeSpeechRequest synthReq = 
new SynthesizeSpeechRequest().withText(text).withVoiceId(voice.getId())
.withOutputFormat(format).withEngine("neural");

3. As defined in https://docs.aws.amazon.com/polly/latest/dg/NTTS-main.html Neural voice is only available in specific regions. So I had to chose as following:

PollyDemo helloWorld = new PollyDemo(Region.getRegion(Regions.US_WEST_2));

After this Neural voice worked perfectly.

I am assuming you are using AWS Java SDK 1.11

AWS documentation here states that you need to set the engine parameter in the speech sysnthesis request to neural. AWS Java SDK documentation here describes the withEngine method to set it to neural.

PS: the documentation page doesn't seem to provide the method URLs, so you will have to search for it.