음성 오디오 파일 만들기

// SynthesizeText synthesizes plain text and saves the output to outputFile.
func SynthesizeText(w io.Writer, text, outputFile string) error {
	ctx := context.Background()

	client, err := texttospeech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	req := texttospeechpb.SynthesizeSpeechRequest{
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Text{Text: text},
		},
		// Note: the voice can also be specified by name.
		// Names of voices can be retrieved with client.ListVoices().
		Voice: &texttospeechpb.VoiceSelectionParams{
			LanguageCode: "en-US",
			SsmlGender:   texttospeechpb.SsmlVoiceGender_FEMALE,
		},
		AudioConfig: &texttospeechpb.AudioConfig{
			AudioEncoding: texttospeechpb.AudioEncoding_MP3,
		},
	}

	resp, err := client.SynthesizeSpeech(ctx, &req)
	if err != nil {
		return err
	}

	err = os.WriteFile(outputFile, resp.AudioContent, 0644)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Audio content written to file: %v\n", outputFile)
	return nil
}

/**
 * Demonstrates using the Text to Speech client to synthesize text or ssml.
 *
 * @param text the raw text to be synthesized. (e.g., "Hello there!")
 * @throws Exception on TextToSpeechClient Errors.
 */
public static ByteString synthesizeText(String text) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Set the text input to be synthesized
    SynthesisInput input = SynthesisInput.newBuilder().setText(text).build();

    // Build the voice request
    VoiceSelectionParams voice =
        VoiceSelectionParams.newBuilder()
            .setLanguageCode("en-US") // languageCode = "en_us"
            .setSsmlGender(SsmlVoiceGender.FEMALE) // ssmlVoiceGender = SsmlVoiceGender.FEMALE
            .build();

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

    // Perform the text-to-speech request
    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("output.mp3")) {
      out.write(audioContents.toByteArray());
      System.out.println("Audio content written to file \"output.mp3\"");
      return audioContents;
    }
  }
}

const textToSpeech = require('@google-cloud/text-to-speech');
const fs = require('fs');
const util = require('util');

const client = new textToSpeech.TextToSpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const text = 'Text to synthesize, eg. hello';
// const outputFile = 'Local path to save audio file to, e.g. output.mp3';

const request = {
  input: {text: text},
  voice: {languageCode: 'en-US', ssmlGender: 'FEMALE'},
  audioConfig: {audioEncoding: 'MP3'},
};
const [response] = await client.synthesizeSpeech(request);
const writeFile = util.promisify(fs.writeFile);
await writeFile(outputFile, response.audioContent, 'binary');
console.log(`Audio content written to file: ${outputFile}`);

def synthesize_text():
    """Synthesizes speech from the input string of text."""
    from google.cloud import texttospeech

    text = "Hello there."
    client = texttospeech.TextToSpeechClient()

    input_text = texttospeech.SynthesisInput(text=text)

    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices().
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US",
        name="en-US-Standard-C",
        ssml_gender=texttospeech.SsmlVoiceGender.FEMALE,
    )

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    response = client.synthesize_speech(
        request={"input": input_text, "voice": voice, "audio_config": audio_config}
    )

    # The response's audio_content is binary.
    with open("output.mp3", "wb") as out:
        out.write(response.audio_content)
        print('Audio content written to file "output.mp3"')

// SynthesizeSSML synthesizes ssml and saves the output to outputFile.
//
// ssml must be well-formed according to:
//
//	https://www.w3.org/TR/speech-synthesis/
//
// Example: <speak>Hello there.</speak>
func SynthesizeSSML(w io.Writer, ssml, outputFile string) error {
	ctx := context.Background()

	client, err := texttospeech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	req := texttospeechpb.SynthesizeSpeechRequest{
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Ssml{Ssml: ssml},
		},
		// Note: the voice can also be specified by name.
		// Names of voices can be retrieved with client.ListVoices().
		Voice: &texttospeechpb.VoiceSelectionParams{
			LanguageCode: "en-US",
			SsmlGender:   texttospeechpb.SsmlVoiceGender_FEMALE,
		},
		AudioConfig: &texttospeechpb.AudioConfig{
			AudioEncoding: texttospeechpb.AudioEncoding_MP3,
		},
	}

	resp, err := client.SynthesizeSpeech(ctx, &req)
	if err != nil {
		return err
	}

	err = os.WriteFile(outputFile, resp.AudioContent, 0644)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Audio content written to file: %v\n", outputFile)
	return nil
}

/**
 * Demonstrates using the Text to Speech client to synthesize text or ssml.
 *
 * <p>Note: ssml must be well-formed according to: (https://www.w3.org/TR/speech-synthesis/
 * Example: <speak>Hello there.</speak>
 *
 * @param ssml the ssml document to be synthesized. (e.g., "<?xml...")
 * @throws Exception on TextToSpeechClient Errors.
 */
public static ByteString synthesizeSsml(String ssml) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Set the ssml input to be synthesized
    SynthesisInput input = SynthesisInput.newBuilder().setSsml(ssml).build();

    // Build the voice request
    VoiceSelectionParams voice =
        VoiceSelectionParams.newBuilder()
            .setLanguageCode("en-US") // languageCode = "en_us"
            .setSsmlGender(SsmlVoiceGender.FEMALE) // ssmlVoiceGender = SsmlVoiceGender.FEMALE
            .build();

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

    // Perform the text-to-speech request
    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("output.mp3")) {
      out.write(audioContents.toByteArray());
      System.out.println("Audio content written to file \"output.mp3\"");
      return audioContents;
    }
  }
}

const textToSpeech = require('@google-cloud/text-to-speech');
const fs = require('fs');
const util = require('util');

const client = new textToSpeech.TextToSpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const ssml = '<speak>Hello there.</speak>';
// const outputFile = 'Local path to save audio file to, e.g. output.mp3';

const request = {
  input: {ssml: ssml},
  voice: {languageCode: 'en-US', ssmlGender: 'FEMALE'},
  audioConfig: {audioEncoding: 'MP3'},
};

const [response] = await client.synthesizeSpeech(request);
const writeFile = util.promisify(fs.writeFile);
await writeFile(outputFile, response.audioContent, 'binary');
console.log(`Audio content written to file: ${outputFile}`);

def synthesize_ssml():
    """Synthesizes speech from the input string of ssml.

    Note: ssml must be well-formed according to:
        https://www.w3.org/TR/speech-synthesis/

    """
    from google.cloud import texttospeech

    ssml = "<speak>Hello there.</speak>"
    client = texttospeech.TextToSpeechClient()

    input_text = texttospeech.SynthesisInput(ssml=ssml)

    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices().
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US",
        name="en-US-Standard-C",
        ssml_gender=texttospeech.SsmlVoiceGender.FEMALE,
    )

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    response = client.synthesize_speech(
        input=input_text, voice=voice, audio_config=audio_config
    )

    # The response's audio_content is binary.
    with open("output.mp3", "wb") as out:
        out.write(response.audio_content)
        print('Audio content written to file "output.mp3"')