Synthesize plain text

Demonstrates how to pass text to the Text-to-Speech API to synthesize audio.

Code sample

Go


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

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

	text, err := ioutil.ReadFile(textFile)
	if err != nil {
		return err
	}

	req := texttospeechpb.SynthesizeSpeechRequest{
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Text{Text: string(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 a text file or ssml file.
 *
 * @param textFile the text file to be synthesized. (e.g., hello.txt)
 * @throws Exception on TextToSpeechClient Errors.
 */
public static ByteString synthesizeTextFile(String textFile) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Read the file's contents
    String contents = new String(Files.readAllBytes(Paths.get(textFile)));
    // Set the text input to be synthesized
    SynthesisInput input = SynthesisInput.newBuilder().setText(contents).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 textFile = 'Local path to text file, eg. input.txt';
// const outputFile = 'Local path to save audio file to, e.g. output.mp3';

const request = {
  input: {text: fs.readFileSync(textFile)},
  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

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

/** Uncomment and populate these variables in your code */
// $path = 'The text file to be synthesized. (e.g., hello.txt)';

// create client object
$client = new TextToSpeechClient();

// get text from file
$text = file_get_contents($path);
$input_text = (new SynthesisInput())
    ->setText($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);

$response = $client->synthesizeSpeech($input_text, $voice, $audioConfig);
$audioContent = $response->getAudioContent();

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

$client->close();

Python

def synthesize_text_file(text_file):
    """Synthesizes speech from the input file of text."""
    from google.cloud import texttospeech

    client = texttospeech.TextToSpeechClient()

    with open(text_file, "r") as f:
        text = f.read()
        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", 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"')

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser