Call from a C # (.NET Core) program

Start Visual Studio and select [** File ]-[ New ]-[ Project ], then select " Visual C # "-" Console App (.NET Core) * *"Choose.

Select [** Tools ]-[ NuGet Package Manager ]-[ Package Manager Console **] from the menu. Enter ʻInstall-Package Google.Cloud.TextToSpeech.V1 -Pre` in the console to run it.

PM> Install-Package Google.Cloud.TextToSpeech.V1 -Pre

Rewrite the contents of Program.cs as follows.

Program.cs

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

public class QuickStart {
  public static void Main(string[] args) {

    var credentialsFilePath = @"C:\Users\xxx\Desktop\credentials.json";

    var textToSpeechClientBuilder = new TextToSpeechClientBuilder() {
      CredentialsPath = credentialsFilePath
    };
    var client = textToSpeechClientBuilder.Build();

    //Read-aloud text settings
    SynthesisInput input = new SynthesisInput {
      Text = "The destination is Nihonbashi."
    };

    //Voice type setting
    VoiceSelectionParams voice = new VoiceSelectionParams {
      Name = "ja-JP-Wavenet-D",
      LanguageCode = "ja-JP",
      SsmlGender = SsmlVoiceGender.Neutral
    };

    //Audio output settings
    AudioConfig config = new AudioConfig {
      AudioEncoding = AudioEncoding.Mp3,
      Pitch = -2.0
    };

    // Text-to-Generate Speech request
    var response = client.SynthesizeSpeech(new SynthesizeSpeechRequest {
      Input = input,
      Voice = voice,
      AudioConfig = config
    });

    // Text-to-Saving Speech response (voice file)
    var fileName = DateTime.Now.ToString("yyyy-MM-dd_HHmmss") + ".mp3";
    using (Stream output = File.Create(fileName)) {
      response.AudioContent.WriteTo(output);
      Console.WriteLine($"Audio content'{fileName}'Saved as.");
    }

    Console.WriteLine("Do you want to open the folder where you output the file?[Y]/n");
    var k = Console.ReadKey();
    if (k.Key != ConsoleKey.N && k.Key != ConsoleKey.Escape) {
      Process.Start("explorer.exe", Directory.GetCurrentDirectory());
    }
  }
}

When executed, an MP3 file "Mokukichi is Nihonbashi" will be generated.

In addition, ** Speech Synthesis Markup Language ** (SSML) is also supported, and if you change it as follows It reads out, "Mokukichi is not ** Nipponbashi **, but ** Nipponbashi **." You can also insert ** intervals **, such as by <break time =" 200ms "/>.

SSML format

SynthesisInput input = new SynthesisInput {
  Ssml = "<speak>The destination is not Nihonbashi,<sub alias='Nipponbashi'>Nihonbashi</sub>is.</speak>".Replace("'", "\"")
};

Call from a Python program

pip install --upgrade google-cloud-texttospeech

python

from datetime import datetime
from pytz import timezone
from google.cloud import texttospeech
from google.oauth2 import service_account

credentials = service_account.Credentials.from_service_account_file('credentials.json')
client = texttospeech.TextToSpeechClient(credentials=credentials)

synthesis_input = texttospeech.types.SynthesisInput(
  text='The destination is Akihabara.')

voice = texttospeech.types.VoiceSelectionParams(
  language_code='ja-JP',
  name='ja-JP-Wavenet-D',
  ssml_gender=texttospeech.enums.SsmlVoiceGender.NEUTRAL)

audio_config = texttospeech.types.AudioConfig(
  audio_encoding=texttospeech.enums.AudioEncoding.MP3,
  pitch = -2.0
  )

response = client.synthesize_speech(synthesis_input, voice, audio_config)

now = datetime.now(timezone('Asia/Tokyo'))
filename = now.strftime('%Y-%m-%d_%H%M%S.mp3')
with open(filename, 'wb') as out:
  out.write(response.audio_content)
  print(f'Audio content written to file {filename}')