use of com.google.cloud.texttospeech.v1beta1.AudioConfig in project webapp by elimu-ai.
the class GoogleCloudTextToSpeechHelper method synthesizeText.
public static byte[] synthesizeText(String text, Language language) throws NotSupportedException, IOException {
logger.info("synthesizeText");
byte[] byteArray = null;
logger.info("text: \"" + text + "\"");
if ((language != Language.BEN) && (language != Language.ENG) && (language != Language.FIL) && (language != Language.HIN)) {
throw new NotSupportedException("This language (" + language + ") is not yet supported: https://cloud.google.com/text-to-speech/docs/voices");
}
String languageCode = null;
if (language == Language.BEN) {
languageCode = "bn";
} else if (language == Language.ENG) {
languageCode = "en";
} else if (language == Language.FIL) {
languageCode = "fil";
} else if (language == Language.HIN) {
languageCode = "hi";
}
logger.info("languageCode: " + languageCode);
// For the Google Cloud TextToSpeechClient to work, an environment variable GOOGLE_APPLICATION_CREDENTIALS needs to exist.
// To enable this during development, download the JSON file from https://console.cloud.google.com/iam-admin/serviceaccounts
// and run the following command:
// export GOOGLE_APPLICATION_CREDENTIALS=/path/to/google-cloud-service-account-key.json
logger.info("System.getenv(\"GOOGLE_APPLICATION_CREDENTIALS\"): \"" + System.getenv("GOOGLE_APPLICATION_CREDENTIALS") + "\"");
TextToSpeechClient textToSpeechClient = TextToSpeechClient.create();
logger.info("textToSpeechClient: " + textToSpeechClient);
// Set the text input to be synthesized
SynthesisInput synthesisInput = SynthesisInput.newBuilder().setText(text).build();
logger.info("synthesisInput: " + synthesisInput);
// Build the voice request
VoiceSelectionParams voiceSelectionParams = VoiceSelectionParams.newBuilder().setLanguageCode(// TODO: fetch from Language enum
languageCode).setSsmlGender(SsmlVoiceGender.FEMALE).build();
logger.info("voiceSelectionParams: " + voiceSelectionParams);
// Select the type of audio file to be returned
AudioConfig audioConfig = AudioConfig.newBuilder().setAudioEncoding(AudioEncoding.MP3).build();
logger.info("audioConfig: " + audioConfig);
// Perform Text-to-Speech request
SynthesizeSpeechResponse synthesizeSpeechResponse = textToSpeechClient.synthesizeSpeech(synthesisInput, voiceSelectionParams, audioConfig);
logger.info("synthesizeSpeechResponse: " + synthesizeSpeechResponse);
// Get the audio contents from the response
ByteString audioContentsByteString = synthesizeSpeechResponse.getAudioContent();
// Convert to byte array
byteArray = audioContentsByteString.toByteArray();
return byteArray;
}
Aggregations