Pasa texto a la API de Text-to-Speech

Se muestra cómo pasar texto a la API de Text-to-Speech para sintetizar audio.

Explora más

Para obtener documentación en la que se incluye esta muestra de código, consulta lo siguiente:

Crea archivos de audio de voz

Muestra de código

Go

Para obtener información sobre cómo instalar y usar la biblioteca cliente de Text-to-Speech, consulta las bibliotecas cliente de Text-to-Speech. Para obtener más información, consulta la documentación de referencia de la API de Text-to-Speech Go.

Para autenticarte en Text-to-Speech, configura las credenciales predeterminadas de la aplicación. Si deseas obtener más información, consulta Configura la autenticación para un entorno de desarrollo local.


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

Java

/**
 * 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;
    }
  }
}

Node.js

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}`);

PHP

Para obtener información sobre cómo instalar y usar la biblioteca cliente de Text-to-Speech, consulta las bibliotecas cliente de Text-to-Speech.

use Google\Cloud\TextToSpeech\V1\AudioConfig;
use Google\Cloud\TextToSpeech\V1\AudioEncoding;
use Google\Cloud\TextToSpeech\V1\Client\TextToSpeechClient;
use Google\Cloud\TextToSpeech\V1\SsmlVoiceGender;
use Google\Cloud\TextToSpeech\V1\SynthesisInput;
use Google\Cloud\TextToSpeech\V1\SynthesizeSpeechRequest;
use Google\Cloud\TextToSpeech\V1\VoiceSelectionParams;

/**
 * @param string $text Text to synthesize
 */
function synthesize_text(string $text): void
{
    // create client object
    $client = new TextToSpeechClient();

    $input_text = (new SynthesisInput())
        ->setText($text);

    // note: the voice can also be specified by name
    // names of voices can be retrieved with $client->listVoices()
    $voice = (new VoiceSelectionParams())
        ->setLanguageCode('en-US')
        ->setSsmlGender(SsmlVoiceGender::FEMALE);

    $audioConfig = (new AudioConfig())
        ->setAudioEncoding(AudioEncoding::MP3);
    $request = (new SynthesizeSpeechRequest())
        ->setInput($input_text)
        ->setVoice($voice)
        ->setAudioConfig($audioConfig);

    $response = $client->synthesizeSpeech($request);
    $audioContent = $response->getAudioContent();

    file_put_contents('output.mp3', $audioContent);
    print('Audio content written to "output.mp3"' . PHP_EOL);

    $client->close();
}

Python

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

    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"')

¿Qué sigue?

Para buscar y filtrar muestras de código para otros productos de Google Cloud, consulta el navegador de muestra de Google Cloud.