protected override void Execute(CodeActivityContext context)
{
var text = Text.Get(context);
var languageCode = LanguageCode.Get(context);
var serviceAcc = ServiceAccountFile.Get(context);
SsmlVoiceGender gender = (SsmlVoiceGender)Enum.Parse(typeof(SsmlVoiceGender), Gender.ToString());
Recognize.TextToSpeech(text, languageCode, gender, serviceAcc);
}
public static void TextToSpeech(string text, string languageCode, SsmlVoiceGender gender, string serviceAcc)
{
GoogleCredential credentials = GoogleCredential.FromFile(serviceAcc);
TextToSpeechClient client = TextToSpeechClient.Create(credentials);
SynthesizeSpeechResponse response = client.SynthesizeSpeech(
new SynthesisInput()
{
Text = text
},
new VoiceSelectionParams()
{
LanguageCode = languageCode,
SsmlGender = gender
},
new AudioConfig()
{
AudioEncoding = AudioEncoding.Linear16
}
);
string speechFile = Path.Combine(Directory.GetCurrentDirectory(), "sample.wav");
File.WriteAllBytes(speechFile, response.AudioContent);
System.Media.SoundPlayer player = new System.Media.SoundPlayer();
player.SoundLocation = speechFile;
player.PlaySync();
try
{
File.Delete(speechFile);
}
catch
{
Console.WriteLine("Cannot delete the file");
}
}
public async Task <Stream> TextToAudioStreamAsync(string text, string language = "fr-FR", SsmlVoiceGender voiceGender = SsmlVoiceGender.Male, CancellationToken token = default)
{
var request = new SynthesizeSpeechRequest
{
AudioConfig = new AudioConfig
{
AudioEncoding = AudioEncoding.OggOpus,
},
Input = new SynthesisInput
{
Text = text
},
Voice = new VoiceSelectionParams
{
LanguageCode = language,
SsmlGender = voiceGender,
},
};
var response = await ttsClient.SynthesizeSpeechAsync(request, token);
using var opusStream = new MemoryStream();
response.AudioContent.WriteTo(opusStream);
opusStream.Position = 0;
var opusDecoder = new OpusDecoder(48000, 2);
var oggIn = new OpusOggReadStream(opusDecoder, opusStream);
var pcmStream = new MemoryStream();
while (oggIn.HasNextPacket)
{
short[] packet = oggIn.DecodeNextPacket();
if (packet != null)
{
for (int i = 0; i < packet.Length; i++)
{
byte[] bytes = BitConverter.GetBytes(packet[i]);
pcmStream.Write(bytes, 0, bytes.Length);
}
}
}
pcmStream.Position = 0;
return(pcmStream);
}
public void CheckForSpeechInDisk(Speech speech, string word, string languageCode, SsmlVoiceGender gender)
{
if (!File.Exists("wwwroot/assets/speeches/" + speech.Code + ".mp3"))
{
var response = new ResultModel <SynthesizeSpeechResponse>();
if (notFoundLanguageCodes.Any(x => x.Code == languageCode))
{
response = new ResultModel <SynthesizeSpeechResponse>
{
Success = false,
ErrorMessage = notFoundLanguageCodes.Find(x => x.Code == languageCode).ErrorMessage
};
}
else
{
response = DownloadWord(new SpeechModel {
Text = word, LanguageCode = languageCode, Gender = gender
});
}
if (!response.Success)
{
speech.ErrorMessage = response.ErrorMessage;
speech.Status = SpeechStatus.Error;
db.Query <int>(@"
update [dbo].[speech] SET
Code = @Code,
AddedDate = @AddedDate,
Status = @Status,
ErrorMessage = @ErrorMessage
Where Id = @Id
", speech).SingleOrDefault();
}
else
{
// Write the response to the output file.
using FileStream output = File.Create("wwwroot/assets/speeches/" + speech.Code + ".mp3");
response.Data.AudioContent.WriteTo(output);
// To change status of speech to success
speech.Status = SpeechStatus.Success;
db.Query <Speech>("update dbo.Speech SET Status = @Status where Id = @Id", speech).SingleOrDefault();
}
}
else
{
// To change status of speech to success
speech.Status = SpeechStatus.Success;
db.Query <Speech>("update dbo.Speech SET Status = @Status where Id = @Id", speech).SingleOrDefault();
}
}
// Generate
private void button2_Click(object sender, EventArgs e)
{
try
{
if (!AuthenticateWithGoogle())
{
return;
}
// Set the text input to be synthesized.
SynthesisInput input = new SynthesisInput();
if (checkBox_SSML.Checked)
{
input.Ssml = richTextBox_Text.Text;
}
else
{
input.Text = richTextBox_Text.Text;
}
// Build the voice request, select the language code ("en-US"),
// and the SSML voice gender ("neutral").
SsmlVoiceGender selected = (SsmlVoiceGender)Enum.Parse(typeof(SsmlVoiceGender), comboBox_Gender.Text);
VoiceSelectionParams voice = new VoiceSelectionParams
{
LanguageCode = LanguageCode,
SsmlGender = selected
};
// Select the type of audio file you want returned.
AudioConfig config = new AudioConfig
{
AudioEncoding = AudioEncoding.Mp3,
Pitch = (double)numericUpDown_Pitch.Value,
SpeakingRate = (double)numericUpDown_Speed.Value
};
// 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(outputFile))
{
response.AudioContent.WriteTo(output);
Log("Audio content written to " + outputFile + "");
}
}
catch (Exception e2)
{
Log("Error: " + e2.Message);
}
}
