Node.js中的Google Cloud语音到文本api编码问题

Question

I'm trying to capture audio from a user's microphone and send it to a server where it will get sent to Google's Speech-to-Text-API for translation. I'm accessing the audio using navigator.mediaDevices.GetuserMedia() which I capture using a MediaRecorder object. When I run the following code I get an error from Google that says "INVALID_ARGUMENT: RecognitionAudio not set." I'm not sure how to set it as the relavant page ( https://cloud.google.com/speech-to-text/docs/reference/rest/v1/RecognitionAudio ) doesn't say much about it. Relevant client side code that runs after user presses stop:

mediaRecorder.onstop = function(e) {
     var blob = new Blob(chunks, { type : 'audio/flac' });
     var reader = new FileReader();
     reader.readAsBinaryString(blob); 
     reader.onloadend = function() {
       base64data = reader.result;
       writeBinaryFile(base64data)
     }

     chunks = []; //array to store recording
}

//asynchronous binary file write
function writeBinaryFile(content) {
 $.ajax({
   type: "POST",
   url: "/voice_api",
   data: { content: content }
 }).done(function(data) {
   // TODO: display success status somewhere
 });

Server side code running node.js:

app.post("/voice_api", (req, res) => {
    const audioBytes = req.body;
    // The audio file's encoding, sample rate in hertz, and BCP-47 language code
    const audio = {
      content: audioBytes,
    };
    const config = {
      languageCode: 'en-US'
    };
    const request = {
      audio: audio,
      config: config
    };

    // Detects speech in the audio file
    client
      .recognize(request)
      .then(data => {
        const response = data[0];
        const transcription = response.results
          .map(result => result.alternatives[0].transcript)
          .join('\n');
        console.log(`Transcription: ${transcription}`);
        res.send(transcription);
      })
      .catch(err => {
        console.error('ERROR:', err);
      });
});

If I run the server code with the line "const audioBytes = req.body;" changed to "const audioBytes = req.body.content;" I get an error message that there is bad encoding. I'm not sure if I'm encoding it properly on the client side or if I'm accessing it properly on the server side. Any help would be appreciated. Thanks!

Answer 1

const config = {
    // "enableAutomaticPunctuation": true,
    "encoding": "LINEAR16",
    "languageCode": "en-US",
    "model": "default",
    "sampleRateHertz": 44100,
    audioChannelCount: 2,
    enableSeparateRecognitionPerChannel: true,
};