Cloud-Based TTS: A Developer's Guide to Text-to-Speech in the Cloud

1from google.cloud import texttospeech
2
3client = texttospeech.TextToSpeechClient()
4
5text = "Hello, world! This is Google Cloud Text-to-Speech."
6
7synthesis_input = texttospeech.SynthesisInput(text=text)
8
9voice = texttospeech.VoiceSelectionParams(
10    language_code="en-US",
11    name="en-US-Wavenet-D"  # Example voice
12)
13
14audio_config = texttospeech.AudioConfig(
15    audio_encoding=texttospeech.AudioEncoding.MP3
16)
17
18response = client.synthesize_speech(
19    input=synthesis_input,
20    voice=voice,
21    audio_config=audio_config
22)
23
24with open("output.mp3", "wb") as out:
25    out.write(response.audio_content)
26    print('Audio content written to file "output.mp3"')
27

1const AWS = require('aws-sdk');
2
3// Configure AWS
4AWS.config.update({
5  region: 'us-east-1', // Replace with your AWS region
6  accessKeyId: 'YOUR_ACCESS_KEY_ID',
7  secretAccessKey: 'YOUR_SECRET_ACCESS_KEY'
8});
9
10const polly = new AWS.Polly({
11  apiVersion: '2016-06-10'
12});
13
14const params = {
15  OutputFormat: 'mp3',
16  Text: 'Hello, world! This is Amazon Polly.',
17  TextType: 'text',
18  VoiceId: 'Joanna'
19};
20
21polly.synthesizeSpeech(params, (err, data) => {
22  if (err) {
23    console.log(err, err.stack);
24  } else {
25    console.log("===Data:" + data);
26    // Save the audio stream to a file (example)
27    const fs = require('fs');
28    fs.writeFile('polly.mp3', data.AudioStream, (err) => {
29      if (err) throw err;
30      console.log('The file has been saved!');
31    });
32  }
33});
34

1using Microsoft.CognitiveServices.Speech;
2
3class Program
4{
5    async static Task Main(string[] args)
6    {
7        var config = SpeechConfig.FromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_REGION");
8        config.SpeechSynthesisVoiceName = "en-US-JennyNeural";
9
10        using (var synthesizer = new SpeechSynthesizer(config))
11        {
12            var result = await synthesizer.SpeakTextAsync("Hello, world! This is Azure Text to Speech.");
13
14            if (result.Reason == ResultReason.SynthesizingAudioCompleted)
15            {
16                Console.WriteLine("Speech synthesized to speaker successfully.");
17            }
18            else if (result.Reason == ResultReason.Canceled)
19            {
20                var cancellation = SpeechSynthesisCancellationDetails.FromResult(result);
21                Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");
22
23                if (cancellation.Reason == CancellationReason.Error)
24                {
25                    Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
26                    Console.WriteLine($"CANCELED: ErrorDetails={cancellation.ErrorDetails}");
27                    Console.WriteLine("Did you set the speech resource key and region values?");
28                }
29            }
30        }
31    }
32}
33