Google 會運用 AI 技術將內容翻譯成你偏好的語言，但可能會出錯。

串流輸入音訊來偵測意圖

本頁面說明如何使用 API，將音訊輸入串流至偵測意圖要求。Dialogflow 會先處理音訊並轉換成文字，再嘗試比對意圖。這個程序稱為「音訊輸入」、「語音辨識」、「語音轉文字」或「STT」。

事前準備

這項功能僅適用於使用 API 進行使用者互動的情況。如果您使用整合，可以略過本指南。

閱讀本指南前，請先完成下列工作：

詳閱 Dialogflow 基本概念。
執行設定步驟。

建立虛擬服務專員

前往 Dialogflow ES 控制台。
如果出現提示，請登入控制台。詳情請參閱「Dialogflow 控制台總覽」。
在側欄選單中，展開「Loading agents」(載入代理程式)。
按一下「Create new agent」。
輸入代理名稱、預設語言和預設時區。
輸入現有專案。如要讓 Dialogflow 控制台建立專案，請選取「Create a new Google project」(建立新的 Google 專案)。
按一下「Create」(建立)。

串流基本概念

Session 類型的 streamingDetectIntent 方法會傳回雙向 gRPC 串流物件。這個物件可用的方法因語言而異，詳情請參閱用戶端程式庫的參考文件。

串流物件用於同時傳送及接收資料。用戶端會使用這個物件，將音訊內容串流至 Dialogflow，同時監聽 StreamingDetectIntentResponse。

streamingDetectIntent 方法有 query_input.audio_config.single_utterance 參數，會影響語音辨識：

如果設為 false (預設)，語音辨識功能會持續運作，直到用戶端關閉串流為止。
如果設為 true，Dialogflow 會偵測輸入音訊中的單一語音語句。當 Dialogflow 偵測到音訊的語音已停止或暫停時，就會停止語音辨識，並將 StreamingDetectIntentResponse 傳送至用戶端，其中包含 END_OF_SINGLE_UTTERANCE 的辨識結果。收到 END_OF_SINGLE_UTTERANCE 後，Dialogflow 會忽略串流中傳送至 Dialogflow 的任何音訊。

在雙向串流中，用戶端可以「半關閉」串流物件，向伺服器表示不會再傳送資料。例如，在 Java 和 Go 中，這個方法稱為 closeSend。

在下列情況下，請務必半關閉 (而非取消) 串流：

您的用戶端已完成資料傳送作業。
用戶端的 single_utterance 設為 true，並收到辨識結果為 END_OF_SINGLE_UTTERANCE 的 StreamingDetectIntentResponse。

關閉串流後，用戶端應視需要使用新串流啟動新要求。

串流偵測意圖

以下範例使用 Session 類型的 streamingDetectIntent 方法來串流音訊內容。

Go

如要向 Dialogflow CX 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

func DetectIntentStream(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.DetectIntentStream 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}

	queryInput := dialogflowpb.QueryInput{Input: &queryAudioInput}

	streamer, err := sessionClient.StreamingDetectIntent(ctx)
	if err != nil {
		return "", err
	}

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

	defer f.Close()

	go func() {
		audioBytes := make([]byte, 1024)

		request := dialogflowpb.StreamingDetectIntentRequest{Session: sessionPath, QueryInput: &queryInput}
		err = streamer.Send(&request)
		if err != nil {
			log.Fatal(err)
		}

		for {
			_, err := f.Read(audioBytes)
			if err == io.EOF {
				streamer.CloseSend()
				break
			}
			if err != nil {
				log.Fatal(err)
			}

			request = dialogflowpb.StreamingDetectIntentRequest{InputAudio: audioBytes}
			err = streamer.Send(&request)
			if err != nil {
				log.Fatal(err)
			}
		}
	}()

	var queryResult *dialogflowpb.QueryResult

	for {
		response, err := streamer.Recv()
		if err == io.EOF {
			break
		}
		if err != nil {
			log.Fatal(err)
		}

		recognitionResult := response.GetRecognitionResult()
		transcript := recognitionResult.GetTranscript()
		log.Printf("Recognition transcript: %s\n", transcript)

		queryResult = response.GetQueryResult()
	}

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

Java

如要向 Dialogflow CX 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


import com.google.api.gax.rpc.ApiException;
import com.google.api.gax.rpc.BidiStream;
import com.google.cloud.dialogflow.v2.AudioEncoding;
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.cloud.dialogflow.v2.StreamingDetectIntentRequest;
import com.google.cloud.dialogflow.v2.StreamingDetectIntentResponse;
import com.google.protobuf.ByteString;
import java.io.FileInputStream;
import java.io.IOException;

class DetectIntentStream {

  // DialogFlow API Detect Intent sample with audio files processes as an audio stream.
  static void detectIntentStream(String projectId, String audioFilePath, String sessionId)
      throws IOException, ApiException {
    // String projectId = "YOUR_PROJECT_ID";
    // String audioFilePath = "path_to_your_audio_file";
    // Using the same `sessionId` between requests allows continuation of the conversation.
    // String sessionId = "Identifier of the DetectIntent session";

    // 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);

      // 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)
              .setLanguageCode("en-US") // languageCode = "en-US"
              .setSampleRateHertz(16000) // sampleRateHertz = 16000
              .build();

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

      // Create the Bidirectional stream
      BidiStream<StreamingDetectIntentRequest, StreamingDetectIntentResponse> bidiStream =
          sessionsClient.streamingDetectIntentCallable().call();

      // The first request must **only** contain the audio configuration:
      bidiStream.send(
          StreamingDetectIntentRequest.newBuilder()
              .setSession(session.toString())
              .setQueryInput(queryInput)
              .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) {
          bidiStream.send(
              StreamingDetectIntentRequest.newBuilder()
                  .setInputAudio(ByteString.copyFrom(buffer, 0, bytes))
                  .build());
        }
      }

      // Tell the service you are done sending data
      bidiStream.closeSend();

      for (StreamingDetectIntentResponse response : bidiStream) {
        QueryResult queryResult = response.getQueryResult();
        System.out.println("====================");
        System.out.format("Intent Display Name: %s\n", queryResult.getIntent().getDisplayName());
        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");
      }
    }
  }
}

Node.js

如要向 Dialogflow CX 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

const fs = require('fs');
const util = require('util');
const {Transform, pipeline} = require('stream');
const {struct} = require('pb-util');

const pump = util.promisify(pipeline);
// Imports the Dialogflow library
const dialogflow = require('@google-cloud/dialogflow');

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

// The path to the local file on which to perform speech recognition, e.g.
// /path/to/audio.raw const filename = '/path/to/audio.raw';

// The encoding of the audio file, e.g. 'AUDIO_ENCODING_LINEAR_16'
// const encoding = 'AUDIO_ENCODING_LINEAR_16';

// The sample rate of the audio file in hertz, e.g. 16000
// const sampleRateHertz = 16000;

// The BCP-47 language code to use, e.g. 'en-US'
// const languageCode = 'en-US';
const sessionPath = sessionClient.projectAgentSessionPath(
  projectId,
  sessionId
);

const initialStreamRequest = {
  session: sessionPath,
  queryInput: {
    audioConfig: {
      audioEncoding: encoding,
      sampleRateHertz: sampleRateHertz,
      languageCode: languageCode,
    },
  },
};

// Create a stream for the streaming request.
const detectStream = sessionClient
  .streamingDetectIntent()
  .on('error', console.error)
  .on('data', data => {
    if (data.recognitionResult) {
      console.log(
        `Intermediate transcript: ${data.recognitionResult.transcript}`
      );
    } else {
      console.log('Detected intent:');

      const result = data.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}`);
        });
      }
    }
  });

// Write the initial stream request to config for audio input.
detectStream.write(initialStreamRequest);

// Stream an audio file from disk to the Conversation API, e.g.
// "./resources/audio.raw"
await pump(
  fs.createReadStream(filename),
  // Format the audio stream into the request format.
  new Transform({
    objectMode: true,
    transform: (obj, _, next) => {
      next(null, {inputAudio: obj});
    },
  }),
  detectStream
);

Python

如要向 Dialogflow CX 進行驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

def detect_intent_stream(project_id, session_id, audio_file_path, language_code):
    """Returns the result of detect intent with streaming audio 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_path = session_client.session_path(project_id, session_id)
    print("Session path: {}\n".format(session_path))

    def request_generator(audio_config, audio_file_path):
        query_input = dialogflow.QueryInput(audio_config=audio_config)

        # The first request contains the configuration.
        yield dialogflow.StreamingDetectIntentRequest(
            session=session_path, query_input=query_input
        )

        # Here we are reading small chunks of audio data from a local
        # audio file.  In practice these chunks should come from
        # an audio input device.
        with open(audio_file_path, "rb") as audio_file:
            while True:
                chunk = audio_file.read(4096)
                if not chunk:
                    break
                # The later requests contains audio data.
                yield dialogflow.StreamingDetectIntentRequest(input_audio=chunk)

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

    requests = request_generator(audio_config, audio_file_path)
    responses = session_client.streaming_detect_intent(requests=requests)

    print("=" * 20)
    for response in responses:
        print(
            'Intermediate transcript: "{}".'.format(
                response.recognition_result.transcript
            )
        )
        # Note: Since Python gRPC doesn't have closeSend method, to stop processing the audio after result is recognized,
        # you may close the channel manually to prevent further iteration.
        # Keep in mind that if there is a silence chunk in the audio, part after it might be missed because of early teardown.
        # https://cloud.google.com/dialogflow/es/docs/how/detect-intent-stream#streaming_basics
        if response.recognition_result.is_final:
            session_client.transport.close()
            break

    # Note: The result from the last response is the final transcript along
    # with the detected content.
    query_result = response.query_result

    print("=" * 20)
    print("Query text: {}".format(query_result.query_text))
    print(
        "Detected intent: {} (confidence: {})\n".format(
            query_result.intent.display_name, query_result.intent_detection_confidence
        )
    )
    print("Fulfillment text: {}\n".format(query_result.fulfillment_text))

其他語言

C#：請按照用戶端程式庫頁面上的 C# 設定操作說明完成相關步驟，然後參閱 .NET 適用的 Dialogflow CX 參考文件。

PHP：請按照用戶端程式庫頁面上的 PHP 設定操作說明完成相關步驟，然後參閱 PHP 適用的 Dialogflow CX 參考文件。

Ruby：請按照用戶端程式庫頁面上的 Ruby 設定操作說明完成相關步驟，然後參閱 Ruby 適用的 Dialogflow CX 參考文件。

範例

如要進一步瞭解從瀏覽器麥克風串流至 Dialogflow 的最佳做法，請參閱範例頁面。

利用音訊輸入檔案偵測意圖

利用音訊輸出偵測意圖

串流輸入音訊來偵測意圖 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

事前準備

建立虛擬服務專員

串流基本概念

串流偵測意圖

Go

Java

Node.js

Python

其他語言

範例

串流輸入音訊來偵測意圖