SSML で住所を読み上げる

<!--  Using libraries-bom to manage versions.
See https://github.com/GoogleCloudPlatform/cloud-opensource-java/wiki/The-Google-Cloud-Platform-Libraries-BOM -->
<dependencyManagement>
  <dependencies>
    <dependency>
      <groupId>com.google.cloud</groupId>
      <artifactId>libraries-bom</artifactId>
      <version>26.32.0</version>
      <type>pom</type>
      <scope>import</scope>
    </dependency>
  </dependencies>
</dependencyManagement>

<dependencies>
  <dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-texttospeech</artifactId>
  </dependency>
</dependencies>

// Imports the Google Cloud client library
import com.google.cloud.texttospeech.v1.AudioConfig;
import com.google.cloud.texttospeech.v1.AudioEncoding;
import com.google.cloud.texttospeech.v1.SsmlVoiceGender;
import com.google.cloud.texttospeech.v1.SynthesisInput;
import com.google.cloud.texttospeech.v1.SynthesizeSpeechResponse;
import com.google.cloud.texttospeech.v1.TextToSpeechClient;
import com.google.cloud.texttospeech.v1.VoiceSelectionParams;
import com.google.common.html.HtmlEscapers;
import com.google.protobuf.ByteString;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.nio.file.Files;
import java.nio.file.Paths;

// Imports the Google Cloud client library
const textToSpeech = require('@google-cloud/text-to-speech');

// Import other required libraries
const fs = require('fs');
//const escape = require('escape-html');
const util = require('util');

import html

from google.cloud import texttospeech

/**
 * Generates synthetic audio from a String of SSML text.
 *
 * <p>Given a string of SSML text and an output file name, this function calls the Text-to-Speech
 * API. The API returns a synthetic audio version of the text, formatted according to the SSML
 * commands. This function saves the synthetic audio to the designated output file.
 *
 * @param ssmlText String of tagged SSML text
 * @param outFile String name of file under which to save audio output
 * @throws Exception on errors while closing the client
 */
public static void ssmlToAudio(String ssmlText, String outFile) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Set the ssml text input to synthesize
    SynthesisInput input = SynthesisInput.newBuilder().setSsml(ssmlText).build();

    // Build the voice request, select the language code ("en-US") and
    // the ssml voice gender ("male")
    VoiceSelectionParams voice =
        VoiceSelectionParams.newBuilder()
            .setLanguageCode("en-US")
            .setSsmlGender(SsmlVoiceGender.MALE)
            .build();

    // Select the audio file type
    AudioConfig audioConfig =
        AudioConfig.newBuilder().setAudioEncoding(AudioEncoding.MP3).build();

    // Perform the text-to-speech request on the text input with the selected voice parameters and
    // audio file type
    SynthesizeSpeechResponse response =
        textToSpeechClient.synthesizeSpeech(input, voice, audioConfig);

    // Get the audio contents from the response
    ByteString audioContents = response.getAudioContent();

    // Write the response to the output file
    try (OutputStream out = new FileOutputStream(outFile)) {
      out.write(audioContents.toByteArray());
      System.out.println("Audio content written to file " + outFile);
    }
  }
}

/**
 * Generates synthetic audio from a String of SSML text.
 *
 * Given a string of SSML text and an output file name, this function
 * calls the Text-to-Speech API. The API returns a synthetic audio
 * version of the text, formatted according to the SSML commands. This
 * function saves the synthetic audio to the designated output file.
 *
 * ARGS
 * ssmlText: String of tagged SSML text
 * outfile: String name of file under which to save audio output
 * RETURNS
 * nothing
 *
 */
async function ssmlToAudio(ssmlText, outFile) {
  // Creates a client
  const client = new textToSpeech.TextToSpeechClient();

  // Constructs the request
  const request = {
    // Select the text to synthesize
    input: {ssml: ssmlText},
    // Select the language and SSML Voice Gender (optional)
    voice: {languageCode: 'en-US', ssmlGender: 'MALE'},
    // Select the type of audio encoding
    audioConfig: {audioEncoding: 'MP3'},
  };

  // Performs the Text-to-Speech request
  const [response] = await client.synthesizeSpeech(request);
  // Write the binary audio content to a local file
  const writeFile = util.promisify(fs.writeFile);
  await writeFile(outFile, response.audioContent, 'binary');
  console.log('Audio content written to file ' + outFile);
}

def ssml_to_audio(ssml_text: str) -> None:
    """
    Generates SSML text from plaintext.
    Given a string of SSML text and an output file name, this function
    calls the Text-to-Speech API. The API returns a synthetic audio
    version of the text, formatted according to the SSML commands. This
    function saves the synthetic audio to the designated output file.

    Args:
        ssml_text: string of SSML text
    """

    # Instantiates a client
    client = texttospeech.TextToSpeechClient()

    # Sets the text input to be synthesized
    synthesis_input = texttospeech.SynthesisInput(ssml=ssml_text)

    # Builds the voice request, selects the language code ("en-US") and
    # the SSML voice gender ("MALE")
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.MALE
    )

    # Selects the type of audio file to return
    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    # Performs the text-to-speech request on the text input with the selected
    # voice parameters and audio file type
    response = client.synthesize_speech(
        input=synthesis_input, voice=voice, audio_config=audio_config
    )

    # Writes the synthetic audio to the output file.
    with open("test_example.mp3", "wb") as out:
        out.write(response.audio_content)
        print("Audio content written to file " + "test_example.mp3")

/**
 * Generates SSML text from plaintext.
 *
 * <p>Given an input filename, this function converts the contents of the input text file into a
 * String of tagged SSML text. This function formats the SSML String so that, when synthesized,
 * the synthetic audio will pause for two seconds between each line of the text file. This
 * function also handles special text characters which might interfere with SSML commands.
 *
 * @param inputFile String name of plaintext file
 * @return a String of SSML text based on plaintext input.
 * @throws IOException on files that don't exist
 */
public static String textToSsml(String inputFile) throws Exception {

  // Read lines of input file
  String rawLines = new String(Files.readAllBytes(Paths.get(inputFile)));

  // Replace special characters with HTML Ampersand Character Codes
  // These codes prevent the API from confusing text with SSML tags
  // For example, '<' --> '&lt;' and '&' --> '&amp;'
  String escapedLines = HtmlEscapers.htmlEscaper().escape(rawLines);

  // Convert plaintext to SSML
  // Tag SSML so that there is a 2 second pause between each address
  String expandedNewline = escapedLines.replaceAll("\\n", "\n<break time='2s'/>");
  String ssml = "<speak>" + expandedNewline + "</speak>";

  // Return the concatenated String of SSML
  return ssml;
}

/**
 * Generates SSML text from plaintext.
 *
 * Given an input filename, this function converts the contents of the input text file
 * into a String of tagged SSML text. This function formats the SSML String so that,
 * when synthesized, the synthetic audio will pause for two seconds between each line
 * of the text file. This function also handles special text characters which might
 * interfere with SSML commands.
 *
 * ARGS
 * inputfile: String name of plaintext file
 * RETURNS
 * a String of SSML text based on plaintext input
 *
 */
function textToSsml(inputFile) {
  let rawLines = '';
  // Read input file
  try {
    rawLines = fs.readFileSync(inputFile, 'utf8');
  } catch (e) {
    console.log('Error:', e.stack);
    return;
  }

  // Replace special characters with HTML Ampersand Character Codes
  // These codes prevent the API from confusing text with SSML tags
  // For example, '<' --> '&lt;' and '&' --> '&amp;'
  let escapedLines = rawLines;
  escapedLines = escapedLines.replace(/&/g, '&amp;');
  escapedLines = escapedLines.replace(/"/g, '&quot;');
  escapedLines = escapedLines.replace(/</g, '&lt;');
  escapedLines = escapedLines.replace(/>/g, '&gt;');

  // Convert plaintext to SSML
  // Tag SSML so that there is a 2 second pause between each address
  const expandedNewline = escapedLines.replace(/\n/g, '\n<break time="2s"/>');
  const ssml = '<speak>' + expandedNewline + '</speak>';

  // Return the concatenated String of SSML
  return ssml;
}

def text_to_ssml(inputfile: str) -> str:
    """
    Generates SSML text from plaintext.
    Given an input filename, this function converts the contents of the text
    file into a string of formatted SSML text. This function formats the SSML
    string so that, when synthesized, the synthetic audio will pause for two
    seconds between each line of the text file. This function also handles
    special text characters which might interfere with SSML commands.

    Args:
        inputfile: name of plaintext file
    Returns: SSML text based on plaintext input
    """

    # Parses lines of input file
    with open(inputfile) as f:
        raw_lines = f.read()

    # Replace special characters with HTML Ampersand Character Codes
    # These Codes prevent the API from confusing text with
    # SSML commands
    # For example, '<' --> '&lt;' and '&' --> '&amp;'

    escaped_lines = html.escape(raw_lines)

    # Convert plaintext to SSML
    # Wait two seconds between each address
    ssml = "<speak>{}</speak>".format(
        escaped_lines.replace("\n", '\n<break time="2s"/>')
    )

    # Return the concatenated string of ssml script
    return ssml