Spring Boot API for Google Text-To-Speech

				
					package io.techwings.media.texttospeech.app.services;

import com.google.cloud.texttospeech.v1.*;
import com.google.protobuf.ByteString;
import io.techwings.media.texttospeech.app.model.TextToSpeechRequestModel;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Service;
import org.springframework.util.StringUtils;

import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;

@Service
public class TextToSpeechService {

    @Value("${user.home}")
    private String userHome;

    /**
     * Demonstrates using the Text to Speech client to synthesize text or ssml.
     *
     * @param model The Model for the Request to GCP Text-To-Speech. (e.g., "Hello there!")
     * @throws Exception on TextToSpeechClient Errors.
     */
    public ByteString synthesizeText(TextToSpeechRequestModel model) throws Exception {

        this.validateAndNormaliseModel(model);

        // Instantiates a client
        try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
            SynthesisInput input = prepareSynthesisInput(model);

            // Build the voice request
            VoiceSelectionParams voice = setVoiceSelectionParams();

            // Select the type of audio file you want returned
            AudioConfig audioConfig = setAudioConfig();

            // Perform the text-to-speech request
            SynthesizeSpeechResponse response =
                    textToSpeechClient.synthesizeSpeech(input, voice, audioConfig);

            return response.getAudioContent();

        }
    }



    public void writeOutputAudioFile(ByteString audioContents,
                                     String outputFilePath) throws IOException {
        Path path = Paths.get(outputFilePath);
        Path directoryExtract = path.getParent();
        if (!Files.exists(directoryExtract))
            Files.createDirectories(directoryExtract);
        if (Files.exists(path))
            Files.delete(path);
        try (OutputStream out = new FileOutputStream(outputFilePath)) {
            out.write(audioContents.toByteArray());
        }

    }

    private SynthesisInput prepareSynthesisInput(TextToSpeechRequestModel model) {
        // Set the text input to be synthesized
        String inputText = model.getInputText();
        return SynthesisInput.newBuilder()
                .setText(inputText).build();
    }

    private AudioConfig setAudioConfig() {
        return AudioConfig.newBuilder()
                .setAudioEncoding(AudioEncoding.MP3) // MP3 audio.
                .build();
    }

    private static VoiceSelectionParams setVoiceSelectionParams() {
        return VoiceSelectionParams.newBuilder()
                .setLanguageCode("en-GB") // languageCode = "en_us"
                .setName("en-GB-Neural2-A")
                .build();
    }

    private void validateAndNormaliseModel(TextToSpeechRequestModel model) {
        prepareOutputPath(model);
        normaliseInputTextAndEnsureDefaultIsNotNull(model);
    }

    private void prepareOutputPath(TextToSpeechRequestModel model) {
        String outputPath = StringUtils.hasText(model.getOutputPath()) ? model.getOutputPath() :
                this.defaultPath();
        model.setOutputPath(outputPath);
    }

    private String defaultPath() {
        return Paths.get(userHome, "tmp", "output.mp3").toString();
    }

    private static void normaliseInputTextAndEnsureDefaultIsNotNull(TextToSpeechRequestModel model) {
        if (!StringUtils.hasText(model.getInputText()))
            model.setInputText("");
    }

}