使用音频文件api为dialogflow detect intent创建16000采样率和单通道的audio.wav文件或blob

Question

我正在使用dialogflow创建聊天机器人。对于发送音频请求，我们需要创建16000Hz采样率和单声道.wav音频文件。我已经用javascript创建了.wav文件，但是由于不是16000Hz，它不能像预期的那样工作。你知道吗

我附加了javascript和python代码。您还可以建议创建16000Hz音频文件的其他方法。你知道吗

Javascript代码：

const recordAudio = () =>
  new Promise(async resolve => {
    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
    const mediaRecorder = new MediaRecorder(stream);
    const audioChunks = [];

    mediaRecorder.addEventListener("dataavailable", event => {
      audioChunks.push(event.data);
    }); 

    const start = () => mediaRecorder.start();

    const stop = () =>
      new Promise(resolve => {
        mediaRecorder.addEventListener("stop", () => {
          const audioBlob = new Blob(audioChunks, {'type': 'audio/wav;'});
          //  console.log(audioBlob)
          SendAudioQuery(audioBlob)
          const audioUrl = URL.createObjectURL(audioBlob);
          const audio = new Audio(audioUrl);
          console.log(audioUrl)
          const play = () => audio.play();
          resolve({ audioBlob, audioUrl, play });
        });

        mediaRecorder.stop();
      });

    resolve({ start, stop });
  });

const sleep = time => new Promise(resolve => setTimeout(resolve, time));

const handleAction = async () => {
  const recorder = await recordAudio();
  const actionButton = document.getElementById('action');
  actionButton.disabled = true;
  recorder.start();
  await sleep(3000);
  const audio = await recorder.stop();
  audio.play();
  await sleep(3000);
  actionButton.disabled = false;
}

Python代码：

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."""
    import dialogflow_v2 as dialogflow

    session_client = dialogflow.SessionsClient()

    # Note: hard coding audio_encoding and sample_rate_hertz for simplicity.
    audio_encoding = dialogflow.enums.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.types.InputAudioConfig(
        audio_encoding=audio_encoding, language_code=language_code,
        sample_rate_hertz=sample_rate_hertz)
    query_input = dialogflow.types.QueryInput(audio_config=audio_config)

    response = session_client.detect_intent(
        session=session, query_input=query_input,
        input_audio=input_audio)

    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))