音声入力ファイルでインテントを検出

func DetectIntentAudio(projectID, sessionID, audioFile, languageCode string) (string, error) {
	ctx := context.Background()

	sessionClient, err := dialogflow.NewSessionsClient(ctx)
	if err != nil {
		return "", err
	}
	defer sessionClient.Close()

	if projectID == "" || sessionID == "" {
		return "", fmt.Errorf("detect.DetectIntentAudio empty project (%s) or session (%s)", projectID, sessionID)
	}

	sessionPath := fmt.Sprintf("projects/%s/agent/sessions/%s", projectID, sessionID)

	// In this example, we hard code the encoding and sample rate for simplicity.
	audioConfig := dialogflowpb.InputAudioConfig{AudioEncoding: dialogflowpb.AudioEncoding_AUDIO_ENCODING_LINEAR_16, SampleRateHertz: 16000, LanguageCode: languageCode}

	queryAudioInput := dialogflowpb.QueryInput_AudioConfig{AudioConfig: &audioConfig}

	audioBytes, err := os.ReadFile(audioFile)
	if err != nil {
		return "", err
	}

	queryInput := dialogflowpb.QueryInput{Input: &queryAudioInput}
	request := dialogflowpb.DetectIntentRequest{Session: sessionPath, QueryInput: &queryInput, InputAudio: audioBytes}

	response, err := sessionClient.DetectIntent(ctx, &request)
	if err != nil {
		return "", err
	}

	queryResult := response.GetQueryResult()
	fulfillmentText := queryResult.GetFulfillmentText()
	return fulfillmentText, nil
}

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.dialogflow.v2.AudioEncoding;
import com.google.cloud.dialogflow.v2.DetectIntentRequest;
import com.google.cloud.dialogflow.v2.DetectIntentResponse;
import com.google.cloud.dialogflow.v2.InputAudioConfig;
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.protobuf.ByteString;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

public class DetectIntentAudio {

  // DialogFlow API Detect Intent sample with audio files.
  public static QueryResult detectIntentAudio(
      String projectId, String audioFilePath, String sessionId, String languageCode)
      throws IOException, ApiException {
    // 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());

      // Note: hard coding audioEncoding and sampleRateHertz for simplicity.
      // Audio encoding of the audio content sent in the query request.
      AudioEncoding audioEncoding = AudioEncoding.AUDIO_ENCODING_LINEAR_16;
      int sampleRateHertz = 16000;

      // Instructs the speech recognizer how to process the audio content.
      InputAudioConfig inputAudioConfig =
          InputAudioConfig.newBuilder()
              .setAudioEncoding(
                  audioEncoding) // audioEncoding = AudioEncoding.AUDIO_ENCODING_LINEAR_16
              .setLanguageCode(languageCode) // languageCode = "en-US"
              .setSampleRateHertz(sampleRateHertz) // sampleRateHertz = 16000
              .build();

      // Build the query with the InputAudioConfig
      QueryInput queryInput = QueryInput.newBuilder().setAudioConfig(inputAudioConfig).build();

      // Read the bytes from the audio file
      byte[] inputAudio = Files.readAllBytes(Paths.get(audioFilePath));

      // Build the DetectIntentRequest
      DetectIntentRequest request =
          DetectIntentRequest.newBuilder()
              .setSession(session.toString())
              .setQueryInput(queryInput)
              .setInputAudio(ByteString.copyFrom(inputAudio))
              .build();

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

      // 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");

      return queryResult;
    }
  }
}

const fs = require('fs');
const util = require('util');
const {struct} = require('pb-util');
// Imports the Dialogflow library
const dialogflow = require('@google-cloud/dialogflow');

// Instantiates a session client
const sessionClient = new dialogflow.SessionsClient();

// The path to identify the agent that owns the created intent.
const sessionPath = sessionClient.projectAgentSessionPath(
  projectId,
  sessionId
);

// Read the content of the audio file and send it as part of the request.
const readFile = util.promisify(fs.readFile);
const inputAudio = await readFile(filename);
const request = {
  session: sessionPath,
  queryInput: {
    audioConfig: {
      audioEncoding: encoding,
      sampleRateHertz: sampleRateHertz,
      languageCode: languageCode,
    },
  },
  inputAudio: inputAudio,
};

// Recognizes the speech in the audio and detects its intent.
const [response] = await sessionClient.detectIntent(request);

console.log('Detected intent:');
const result = response.queryResult;
// Instantiates a context client
const contextClient = new dialogflow.ContextsClient();

console.log(`  Query: ${result.queryText}`);
console.log(`  Response: ${result.fulfillmentText}`);
if (result.intent) {
  console.log(`  Intent: ${result.intent.displayName}`);
} else {
  console.log('  No intent matched.');
}
const parameters = JSON.stringify(struct.decode(result.parameters));
console.log(`  Parameters: ${parameters}`);
if (result.outputContexts && result.outputContexts.length) {
  console.log('  Output contexts:');
  result.outputContexts.forEach(context => {
    const contextId =
      contextClient.matchContextFromProjectAgentSessionContextName(
        context.name
      );
    const contextParameters = JSON.stringify(
      struct.decode(context.parameters)
    );
    console.log(`    ${contextId}`);
    console.log(`      lifespan: ${context.lifespanCount}`);
    console.log(`      parameters: ${contextParameters}`);
  });
}

def detect_intent_audio(project_id, session_id, audio_file_path, language_code):
    """Returns the result of detect intent with an audio file as input.

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

    session_client = dialogflow.SessionsClient()

    # Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
    audio_encoding = dialogflow.AudioEncoding.AUDIO_ENCODING_LINEAR_16
    sample_rate_hertz = 16000

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

    with open(audio_file_path, "rb") as audio_file:
        input_audio = audio_file.read()

    audio_config = dialogflow.InputAudioConfig(
        audio_encoding=audio_encoding,
        language_code=language_code,
        sample_rate_hertz=sample_rate_hertz,
    )
    query_input = dialogflow.QueryInput(audio_config=audio_config)

    request = dialogflow.DetectIntentRequest(
        session=session,
        query_input=query_input,
        input_audio=input_audio,
    )
    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))