Text-to-Speech 클라이언트 라이브러리

#include "google/cloud/texttospeech/v1/text_to_speech_client.h"
#include <iostream>

auto constexpr kText = R"""(
Four score and seven years ago our fathers brought forth on this
continent, a new nation, conceived in Liberty, and dedicated to
the proposition that all men are created equal.)""";

int main(int argc, char* argv[]) try {
  if (argc != 1) {
    std::cerr << "Usage: " << argv[0] << "\n";
    return 1;
  }

  namespace texttospeech = ::google::cloud::texttospeech_v1;
  auto client = texttospeech::TextToSpeechClient(
      texttospeech::MakeTextToSpeechConnection());

  google::cloud::texttospeech::v1::SynthesisInput input;
  input.set_text(kText);
  google::cloud::texttospeech::v1::VoiceSelectionParams voice;
  voice.set_language_code("en-US");
  google::cloud::texttospeech::v1::AudioConfig audio;
  audio.set_audio_encoding(google::cloud::texttospeech::v1::LINEAR16);

  auto response = client.SynthesizeSpeech(input, voice, audio);
  if (!response) throw std::move(response).status();
  // Normally one would play the results (response->audio_content()) over some
  // audio device. For this quickstart, we just print some information.
  auto constexpr kWavHeaderSize = 48;
  auto constexpr kBytesPerSample = 2;  // we asked for LINEAR16
  auto const sample_count =
      (response->audio_content().size() - kWavHeaderSize) / kBytesPerSample;
  std::cout << "The audio has " << sample_count << " samples\n";

  return 0;
} catch (google::cloud::Status const& status) {
  std::cerr << "google::cloud::Status thrown: " << status << "\n";
  return 1;
}

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

import (
	"context"
	"fmt"
	"log"
	"os"

	texttospeech "cloud.google.com/go/texttospeech/apiv1"
	"cloud.google.com/go/texttospeech/apiv1/texttospeechpb"
)

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

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

	// 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 = os.WriteFile(filename, resp.AudioContent, 0644)
	if err != nil {
		log.Fatal(err)
	}
	fmt.Printf("Audio content written to file: %v\n", filename)
}

// 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\"");
      }
    }
  }
}

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

// Import other required libraries
const {writeFile} = require('node:fs/promises');

// 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);

  // Save the generated binary audio content to a local file
  await writeFile('output.mp3', response.audioContent, 'binary');
  console.log('Audio content written to file: output.mp3');
}

await quickStart();

"""Synthesizes speech from the input string of text or ssml.
Make sure to be working in a virtual environment.

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"')