Detectar intents con salida de audio

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.dialogflow.v2.DetectIntentRequest;
import com.google.cloud.dialogflow.v2.DetectIntentResponse;
import com.google.cloud.dialogflow.v2.OutputAudioConfig;
import com.google.cloud.dialogflow.v2.OutputAudioEncoding;
import com.google.cloud.dialogflow.v2.QueryInput;
import com.google.cloud.dialogflow.v2.QueryResult;
import com.google.cloud.dialogflow.v2.SessionName;
import com.google.cloud.dialogflow.v2.SessionsClient;
import com.google.cloud.dialogflow.v2.TextInput;
import com.google.common.collect.Maps;
import java.io.IOException;
import java.util.List;
import java.util.Map;

public class DetectIntentWithTextToSpeechResponse {

  public static Map<String, QueryResult> detectIntentWithTexttoSpeech(
      String projectId, List<String> texts, String sessionId, String languageCode)
      throws IOException, ApiException {
    Map<String, QueryResult> queryResults = Maps.newHashMap();
    // Instantiates a client
    try (SessionsClient sessionsClient = SessionsClient.create()) {
      // Set the session name using the sessionId (UUID) and projectID (my-project-id)
      SessionName session = SessionName.of(projectId, sessionId);
      System.out.println("Session Path: " + session.toString());

      // Detect intents for each text input
      for (String text : texts) {
        // Set the text (hello) and language code (en-US) for the query
        TextInput.Builder textInput =
            TextInput.newBuilder().setText(text).setLanguageCode(languageCode);

        // Build the query with the TextInput
        QueryInput queryInput = QueryInput.newBuilder().setText(textInput).build();

        //
        OutputAudioEncoding audioEncoding = OutputAudioEncoding.OUTPUT_AUDIO_ENCODING_LINEAR_16;
        int sampleRateHertz = 16000;
        OutputAudioConfig outputAudioConfig =
            OutputAudioConfig.newBuilder()
                .setAudioEncoding(audioEncoding)
                .setSampleRateHertz(sampleRateHertz)
                .build();

        DetectIntentRequest dr =
            DetectIntentRequest.newBuilder()
                .setQueryInput(queryInput)
                .setOutputAudioConfig(outputAudioConfig)
                .setSession(session.toString())
                .build();

        // Performs the detect intent request
        DetectIntentResponse response = sessionsClient.detectIntent(dr);

        // Display the query result
        QueryResult queryResult = response.getQueryResult();

        System.out.println("====================");
        System.out.format("Query Text: '%s'\n", queryResult.getQueryText());
        System.out.format(
            "Detected Intent: %s (confidence: %f)\n",
            queryResult.getIntent().getDisplayName(), queryResult.getIntentDetectionConfidence());
        System.out.format(
            "Fulfillment Text: '%s'\n",
            queryResult.getFulfillmentMessagesCount() > 0
                ? queryResult.getFulfillmentMessages(0).getText()
                : "Triggered Default Fallback Intent");

        queryResults.put(text, queryResult);
      }
    }
    return queryResults;
  }
}

// Imports the Dialogflow client library
const dialogflow = require('@google-cloud/dialogflow').v2;

// Instantiate a DialogFlow client.
const sessionClient = new dialogflow.SessionsClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const projectId = 'ID of GCP project associated with your Dialogflow agent';
// const sessionId = `user specific ID of session, e.g. 12345`;
// const query = `phrase(s) to pass to detect, e.g. I'd like to reserve a room for six people`;
// const languageCode = 'BCP-47 language code, e.g. en-US';
// const outputFile = `path for audio output file, e.g. ./resources/myOutput.wav`;

// Define session path
const sessionPath = sessionClient.projectAgentSessionPath(
  projectId,
  sessionId
);
const fs = require('fs');
const util = require('util');

async function detectIntentwithTTSResponse() {
  // The audio query request
  const request = {
    session: sessionPath,
    queryInput: {
      text: {
        text: query,
        languageCode: languageCode,
      },
    },
    outputAudioConfig: {
      audioEncoding: 'OUTPUT_AUDIO_ENCODING_LINEAR_16',
    },
  };
  sessionClient.detectIntent(request).then(responses => {
    console.log('Detected intent:');
    const audioFile = responses[0].outputAudio;
    util.promisify(fs.writeFile)(outputFile, audioFile, 'binary');
    console.log(`Audio content written to file: ${outputFile}`);
  });
}
detectIntentwithTTSResponse();

def detect_intent_with_texttospeech_response(
    project_id, session_id, texts, language_code
):
    """Returns the result of detect intent with texts as inputs and includes
    the response in an audio format.

    Using the same `session_id` between requests allows continuation
    of the conversation."""
    from google.cloud import dialogflow

    session_client = dialogflow.SessionsClient()

    session_path = session_client.session_path(project_id, session_id)
    print("Session path: {}\n".format(session_path))

    for text in texts:
        text_input = dialogflow.TextInput(text=text, language_code=language_code)

        query_input = dialogflow.QueryInput(text=text_input)

        # Set the query parameters with sentiment analysis
        output_audio_config = dialogflow.OutputAudioConfig(
            audio_encoding=dialogflow.OutputAudioEncoding.OUTPUT_AUDIO_ENCODING_LINEAR_16
        )

        request = dialogflow.DetectIntentRequest(
            session=session_path,
            query_input=query_input,
            output_audio_config=output_audio_config,
        )
        response = session_client.detect_intent(request=request)

        print("=" * 20)
        print("Query text: {}".format(response.query_result.query_text))
        print(
            "Detected intent: {} (confidence: {})\n".format(
                response.query_result.intent.display_name,
                response.query_result.intent_detection_confidence,
            )
        )
        print("Fulfillment text: {}\n".format(response.query_result.fulfillment_text))
        # The response's audio_content is binary.
        with open("output.wav", "wb") as out:
            out.write(response.output_audio)
            print('Audio content written to file "output.wav"')