use of com.google.cloud.dialogflow.cx.v3beta1.VoiceSelectionParams in project java-dialogflow-cx by googleapis.
the class DetectIntentStream method detectIntentStream.
// DialogFlow API Detect Intent sample with audio files processes as an audio stream.
public static void detectIntentStream(String projectId, String locationId, String agentId, String sessionId, String audioFilePath) throws ApiException, IOException {
SessionsSettings.Builder sessionsSettingsBuilder = SessionsSettings.newBuilder();
if (locationId.equals("global")) {
sessionsSettingsBuilder.setEndpoint("dialogflow.googleapis.com:443");
} else {
sessionsSettingsBuilder.setEndpoint(locationId + "-dialogflow.googleapis.com:443");
}
SessionsSettings sessionsSettings = sessionsSettingsBuilder.build();
// Instantiates a client
try (SessionsClient sessionsClient = SessionsClient.create(sessionsSettings)) {
// Set the session name using the projectID (my-project-id), locationID (global), agentID
// (UUID), and sessionId (UUID).
// Using the same `sessionId` between requests allows continuation of the conversation.
SessionName session = SessionName.of(projectId, locationId, agentId, sessionId);
// Instructs the speech recognizer how to process the audio content.
// Note: hard coding audioEncoding and sampleRateHertz for simplicity.
// Audio encoding of the audio content sent in the query request.
InputAudioConfig inputAudioConfig = InputAudioConfig.newBuilder().setAudioEncoding(AudioEncoding.AUDIO_ENCODING_LINEAR_16).setSampleRateHertz(// sampleRateHertz = 16000
16000).build();
// Build the AudioInput with the InputAudioConfig.
AudioInput audioInput = AudioInput.newBuilder().setConfig(inputAudioConfig).build();
// Build the query with the InputAudioConfig.
QueryInput queryInput = QueryInput.newBuilder().setAudio(audioInput).setLanguageCode(// languageCode = "en-US"
"en-US").build();
// Create the Bidirectional stream
BidiStream<StreamingDetectIntentRequest, StreamingDetectIntentResponse> bidiStream = sessionsClient.streamingDetectIntentCallable().call();
// Specify sssml name and gender
VoiceSelectionParams voiceSelection = // Voices that are available https://cloud.google.com/text-to-speech/docs/voices
VoiceSelectionParams.newBuilder().setName("en-GB-Standard-A").setSsmlGender(SsmlVoiceGender.SSML_VOICE_GENDER_FEMALE).build();
SynthesizeSpeechConfig speechConfig = SynthesizeSpeechConfig.newBuilder().setVoice(voiceSelection).build();
// Setup audio config
OutputAudioConfig audioConfig = // https://cloud.google.com/dialogflow/cx/docs/reference/rpc/google.cloud.dialogflow.cx.v3#outputaudioencoding
OutputAudioConfig.newBuilder().setAudioEncoding(OutputAudioEncoding.OUTPUT_AUDIO_ENCODING_UNSPECIFIED).setAudioEncodingValue(1).setSynthesizeSpeechConfig(speechConfig).build();
// The first request must **only** contain the audio configuration:
bidiStream.send(StreamingDetectIntentRequest.newBuilder().setSession(session.toString()).setQueryInput(queryInput).setOutputAudioConfig(audioConfig).build());
try (FileInputStream audioStream = new FileInputStream(audioFilePath)) {
// Subsequent requests must **only** contain the audio data.
// Following messages: audio chunks. We just read the file in fixed-size chunks. In reality
// you would split the user input by time.
byte[] buffer = new byte[4096];
int bytes;
while ((bytes = audioStream.read(buffer)) != -1) {
AudioInput subAudioInput = AudioInput.newBuilder().setAudio(ByteString.copyFrom(buffer, 0, bytes)).build();
QueryInput subQueryInput = QueryInput.newBuilder().setAudio(subAudioInput).setLanguageCode(// languageCode = "en-US"
"en-US").build();
bidiStream.send(StreamingDetectIntentRequest.newBuilder().setQueryInput(subQueryInput).build());
}
}
// Tell the service you are done sending data.
bidiStream.closeSend();
for (StreamingDetectIntentResponse response : bidiStream) {
QueryResult queryResult = response.getDetectIntentResponse().getQueryResult();
System.out.println("====================");
System.out.format("Query Text: '%s'\n", queryResult.getTranscript());
System.out.format("Detected Intent: %s (confidence: %f)\n", queryResult.getIntent().getDisplayName(), queryResult.getIntentDetectionConfidence());
}
}
}
use of com.google.cloud.dialogflow.cx.v3beta1.VoiceSelectionParams in project java-texttospeech by googleapis.
the class SynthesizeText method synthesizeSsml.
// [END tts_synthesize_text_audio_profile]
// [START tts_synthesize_ssml]
/**
* Demonstrates using the Text to Speech client to synthesize text or ssml.
*
* <p>Note: ssml must be well-formed according to: (https://www.w3.org/TR/speech-synthesis/
* Example: <speak>Hello there.</speak>
*
* @param ssml the ssml document to be synthesized. (e.g., "<?xml...")
* @throws Exception on TextToSpeechClient Errors.
*/
public static ByteString synthesizeSsml(String ssml) throws Exception {
// Instantiates a client
try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
// Set the ssml input to be synthesized
SynthesisInput input = SynthesisInput.newBuilder().setSsml(ssml).build();
// Build the voice request
VoiceSelectionParams voice = VoiceSelectionParams.newBuilder().setLanguageCode(// languageCode = "en_us"
"en-US").setSsmlGender(// ssmlVoiceGender = SsmlVoiceGender.FEMALE
SsmlVoiceGender.FEMALE).build();
// Select the type of audio file you want returned
AudioConfig audioConfig = AudioConfig.newBuilder().setAudioEncoding(// MP3 audio.
AudioEncoding.MP3).build();
// Perform the text-to-speech request
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\"");
return audioContents;
}
}
}
use of com.google.cloud.dialogflow.cx.v3beta1.VoiceSelectionParams in project java-texttospeech by googleapis.
the class SynthesizeText method synthesizeText.
// [START tts_synthesize_text]
/**
* Demonstrates using the Text to Speech client to synthesize text or ssml.
*
* @param text the raw text to be synthesized. (e.g., "Hello there!")
* @throws Exception on TextToSpeechClient Errors.
*/
public static ByteString synthesizeText(String text) throws Exception {
// Instantiates a client
try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
// Set the text input to be synthesized
SynthesisInput input = SynthesisInput.newBuilder().setText(text).build();
// Build the voice request
VoiceSelectionParams voice = VoiceSelectionParams.newBuilder().setLanguageCode(// languageCode = "en_us"
"en-US").setSsmlGender(// ssmlVoiceGender = SsmlVoiceGender.FEMALE
SsmlVoiceGender.FEMALE).build();
// Select the type of audio file you want returned
AudioConfig audioConfig = AudioConfig.newBuilder().setAudioEncoding(// MP3 audio.
AudioEncoding.MP3).build();
// Perform the text-to-speech request
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\"");
return audioContents;
}
}
}
use of com.google.cloud.dialogflow.cx.v3beta1.VoiceSelectionParams in project java-texttospeech by googleapis.
the class SynthesizeText method synthesizeTextWithAudioProfile.
// [END tts_synthesize_text]
// [START tts_synthesize_text_audio_profile]
/**
* Demonstrates using the Text to Speech client with audio profiles to synthesize text or ssml
*
* @param text the raw text to be synthesized. (e.g., "Hello there!")
* @param effectsProfile audio profile to be used for synthesis. (e.g.,
* "telephony-class-application")
* @throws Exception on TextToSpeechClient Errors.
*/
public static ByteString synthesizeTextWithAudioProfile(String text, String effectsProfile) throws Exception {
// Instantiates a client
try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
// Set the text input to be synthesized
SynthesisInput input = SynthesisInput.newBuilder().setText(text).build();
// Build the voice request
VoiceSelectionParams voice = VoiceSelectionParams.newBuilder().setLanguageCode(// languageCode = "en_us"
"en-US").setSsmlGender(// ssmlVoiceGender = SsmlVoiceGender.FEMALE
SsmlVoiceGender.FEMALE).build();
// Select the type of audio file you want returned and the audio profile
AudioConfig audioConfig = AudioConfig.newBuilder().setAudioEncoding(// MP3 audio.
AudioEncoding.MP3).addEffectsProfileId(// audio profile
effectsProfile).build();
// Perform the text-to-speech request
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\"");
return audioContents;
}
}
}
use of com.google.cloud.dialogflow.cx.v3beta1.VoiceSelectionParams in project java-texttospeech by googleapis.
the class SynthesizeTextBeta method synthesizeSsml.
// [END tts_synthesize_text_audio_profile_beta]
// [START tts_synthesize_ssml]
/**
* Demonstrates using the Text to Speech client to synthesize text or ssml.
*
* <p>Note: ssml must be well-formed according to: (https://www.w3.org/TR/speech-synthesis/
* Example: <speak>Hello there.</speak>
*
* @param ssml the ssml document to be synthesized. (e.g., "<?xml...")
* @throws Exception on TextToSpeechClient Errors.
*/
public static void synthesizeSsml(String ssml) throws Exception {
// Instantiates a client
try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
// Set the ssml input to be synthesized
SynthesisInput input = SynthesisInput.newBuilder().setSsml(ssml).build();
// Build the voice request
VoiceSelectionParams voice = VoiceSelectionParams.newBuilder().setLanguageCode(// languageCode = "en_us"
"en-US").setSsmlGender(// ssmlVoiceGender = SsmlVoiceGender.FEMALE
SsmlVoiceGender.FEMALE).build();
// Select the type of audio file you want returned
AudioConfig audioConfig = AudioConfig.newBuilder().setAudioEncoding(// MP3 audio.
AudioEncoding.MP3).build();
// Perform the text-to-speech request
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\"");
}
}
}
Aggregations