从文本字符串合成

演示如何从文本字符串合成。

包含此代码示例的文档页面

如需查看上下文中使用的代码示例，请参阅以下文档：

代码示例

C#


using System;
using System.IO;
using Google.Cloud.TextToSpeech.V1;

public class QuickStart
{
    public static void Main(string[] args)
    {
        // Instantiate a client
        TextToSpeechClient client = TextToSpeechClient.Create();

        // Set the text input to be synthesized.
        SynthesisInput input = new SynthesisInput
        {
            Text = "Hello, World!"
        };

        // Build the voice request, select the language code ("en-US"),
        // and the SSML voice gender ("neutral").
        VoiceSelectionParams voice = new VoiceSelectionParams
        {
            LanguageCode = "en-US",
            SsmlGender = SsmlVoiceGender.Neutral
        };

        // Select the type of audio file you want returned.
        AudioConfig config = new AudioConfig
        {
            AudioEncoding = AudioEncoding.Mp3
        };

        // Perform the Text-to-Speech request, passing the text input
        // with the selected voice parameters and audio file type
        var response = client.SynthesizeSpeech(new SynthesizeSpeechRequest
        {
            Input = input,
            Voice = voice,
            AudioConfig = config
        });

        // Write the binary AudioContent of the response to an MP3 file.
        using (Stream output = File.Create("sample.mp3"))
        {
            response.AudioContent.WriteTo(output);
            Console.WriteLine($"Audio content written to file 'sample.mp3'");
        }
    }
}

Go


// Command quickstart generates an audio file with the content "Hello, World!".
package main

import (
	"context"
	"fmt"
	"io/ioutil"
	"log"

	texttospeech "cloud.google.com/go/texttospeech/apiv1"
	texttospeechpb "google.golang.org/genproto/googleapis/cloud/texttospeech/v1"
)

func main() {
	// Instantiates a client.
	ctx := context.Background()

	client, err := texttospeech.NewClient(ctx)
	if err != nil {
		log.Fatal(err)
	}

	// Perform the text-to-speech request on the text input with the selected
	// voice parameters and audio file type.
	req := texttospeechpb.SynthesizeSpeechRequest{
		// Set the text input to be synthesized.
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Text{Text: "Hello, World!"},
		},
		// Build the voice request, select the language code ("en-US") and the SSML
		// voice gender ("neutral").
		Voice: &texttospeechpb.VoiceSelectionParams{
			LanguageCode: "en-US",
			SsmlGender:   texttospeechpb.SsmlVoiceGender_NEUTRAL,
		},
		// Select the type of audio file you want returned.
		AudioConfig: &texttospeechpb.AudioConfig{
			AudioEncoding: texttospeechpb.AudioEncoding_MP3,
		},
	}

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

	// The resp's AudioContent is binary.
	filename := "output.mp3"
	err = ioutil.WriteFile(filename, resp.AudioContent, 0644)
	if err != nil {
		log.Fatal(err)
	}
	fmt.Printf("Audio content written to file: %v\n", filename)
}

Java

// 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.protobuf.ByteString;
import java.io.FileOutputStream;
import java.io.OutputStream;

/**
 * Google Cloud TextToSpeech API sample application. Example usage: mvn package exec:java
 * -Dexec.mainClass='com.example.texttospeech.QuickstartSample'
 */
public class QuickstartSample {

  /** Demonstrates using the Text-to-Speech API. */
  public static void main(String... args) throws Exception {
    // Instantiates a client
    try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
      // Set the text input to be synthesized
      SynthesisInput input = SynthesisInput.newBuilder().setText("Hello, World!").build();

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

      // Select the type of audio file you want returned
      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("output.mp3")) {
        out.write(audioContents.toByteArray());
        System.out.println("Audio content written to file \"output.mp3\"");
      }
    }
  }
}

Node.js

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

// Import other required libraries
const fs = require('fs');
const util = require('util');
// Creates a client
const client = new textToSpeech.TextToSpeechClient();
async function quickStart() {
  // The text to synthesize
  const text = 'hello, world!';

  // Construct the request
  const request = {
    input: {text: text},
    // Select the language and SSML voice gender (optional)
    voice: {languageCode: 'en-US', ssmlGender: 'NEUTRAL'},
    // 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('output.mp3', response.audioContent, 'binary');
  console.log('Audio content written to file: output.mp3');
}
quickStart();

PHP

// includes the autoloader for libraries installed with composer
require __DIR__ . '/vendor/autoload.php';

// Imports the Cloud Client Library
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;

// instantiates a client
$client = new TextToSpeechClient();

// sets text to be synthesised
$synthesisInputText = (new SynthesisInput())
    ->setText('Hello, world!');

// build the voice request, select the language code ("en-US") and the ssml
// voice gender
$voice = (new VoiceSelectionParams())
    ->setLanguageCode('en-US')
    ->setSsmlGender(SsmlVoiceGender::FEMALE);

// Effects profile
$effectsProfileId = "telephony-class-application";

// select the type of audio file you want returned
$audioConfig = (new AudioConfig())
    ->setAudioEncoding(AudioEncoding::MP3)
    ->setEffectsProfileId(array($effectsProfileId));

// perform text-to-speech request on the text input with selected voice
// parameters and audio file type
$response = $client->synthesizeSpeech($synthesisInputText, $voice, $audioConfig);
$audioContent = $response->getAudioContent();

// the response's audioContent is binary
file_put_contents('output.mp3', $audioContent);
echo 'Audio content written to "output.mp3"' . PHP_EOL;

Python

"""Synthesizes speech from the input string of text or ssml.

Note: ssml must be well-formed according to:
    https://www.w3.org/TR/speech-synthesis/
"""
from google.cloud import texttospeech

# Instantiates a client
client = texttospeech.TextToSpeechClient()

# Set the text input to be synthesized
synthesis_input = texttospeech.SynthesisInput(text="Hello, World!")

# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = texttospeech.VoiceSelectionParams(
    language_code="en-US", ssml_gender=texttospeech.SsmlVoiceGender.NEUTRAL
)

# Select the type of audio file you want returned
audio_config = texttospeech.AudioConfig(
    audio_encoding=texttospeech.AudioEncoding.MP3
)

# Perform 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
)

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

Ruby

# Synthesizes speech from the input string of text or ssml.
# Note: ssml must be well-formed according to:
# https://www.w3.org/TR/speech-synthesis/

require "google/cloud/text_to_speech"

# Instantiates a client
client = Google::Cloud::TextToSpeech.text_to_speech

# Set the text input to be synthesized
synthesis_input = { text: "Hello, World!" }

# Build the voice request, select the language code ("en-US") and the ssml
# voice gender ("neutral")
voice = {
  language_code: "en-US",
  ssml_gender:   "NEUTRAL"
}

# Select the type of audio file you want returned
audio_config = { audio_encoding: "MP3" }

# Perform 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
)

# The response's audio_content is binary.
File.open "output.mp3", "wb" do |file|
  # Write the response to the output file.
  file.write response.audio_content
end

puts "Audio content written to file 'output.mp3'"