将实时音频流式传输到 Node.js 服务器

Question

I'm working on a project and I require to send an audio stream to a Node.js server. I'm able to capture microphone sound with this function:

function micCapture(){
    'use strict';

    navigator.getUserMedia = navigator.getUserMedia || navigator.webkitGetUserMedia || navigator.mozGetUserMedia;

    var constraints = {
        audio: true,
        video: false
    };

    var video = document.querySelector('video');

    function successCallback(stream) {
        window.stream = stream; // stream available to console
        if (window.URL) {
            video.src = window.webkitURL.createObjectURL(stream);
        } else {
            video.src = stream;
        }
        //Send audio stream
        //server.send(stream);
    }

    function errorCallback(error) {
        console.log('navigator.getUserMedia error: ', error);
    }

    navigator.getUserMedia(constraints, successCallback, errorCallback);
}

As you can see, I'm able to capture audio and play it on the website.

Now I want to send that audio stream to a Node.js server, and send it back to other clients. Like a voicechat, but I don't want to use WebRTC as I need the stream in the server. How can I achieve this? Can I use socket.io-stream to do this? In the examples I saw, they recorded the audio, and sent a file, but I need "live" audio.

Answer 1

I have recently done live audio upload using socket.io from browser to server. I am going to answer here in case someone else needs it.

    var stream;
    var socket = io();
    var bufferSize = 1024 * 16;
    var audioContext = new AudioContext();
    // createScriptProcessor is deprecated. Let me know if anyone find alternative
    var processor = audioContext.createScriptProcessor(bufferSize, 1, 1);
    processor.connect(audioContext.destination);

    navigator.mediaDevices.getUserMedia({ video: false, audio: true }).then(handleMicStream).catch(err => {
      console.log('error from getUserMedia', err);
    });

handleMicStream will run when user accepts the permission to use microphone.

  function handleMicStream(streamObj) {
    // keep the context in a global variable
    stream = streamObj;

    input = audioContext.createMediaStreamSource(stream);

    input.connect(processor);

    processor.onaudioprocess = e => {
      microphoneProcess(e); // receives data from microphone
    };
  }


  function microphoneProcess(e) {
    const left = e.inputBuffer.getChannelData(0); // get only one audio channel
    const left16 = convertFloat32ToInt16(left); // skip if you don't need this
    socket.emit('micBinaryStream', left16); // send to server via web socket
  }

// Converts data to BINARY16
function convertFloat32ToInt16(buffer) {
    let l = buffer.length;
    const buf = new Int16Array(l / 3);

    while (l--) {
      if (l % 3 === 0) {
        buf[l / 3] = buffer[l] * 0xFFFF;
      }
    }
    return buf.buffer;
  }

Have your socket.io server listen to micBinaryStream and you should get the data. I needed the data as a BINARY16 format for google api if you do not need this you can skip the function call to convertFloat32ToInt16() .

Important

When you need to stop listening you MUST disconnect the the processor and end the stream. Run the function closeAll() below.

function closeAll() {
    const tracks = stream ? stream.getTracks() : null;
    const track = tracks ? tracks[0] : null;

    if (track) {
      track.stop();
    }

    if (processor) {
      if (input) {
        try {
          input.disconnect(processor);
        } catch (error) {
          console.warn('Attempt to disconnect input failed.');
        }
      }
      processor.disconnect(audioContext.destination);
    }

    if (audioContext) {
      audioContext.close().then(() => {
        input = null;
        processor = null;
        audioContext = null;
      });
    }
  }

Answer 2

it's an old time question, i see. I'm doing the same thing (except my server doesn't run node.js and is written in C#) and stumbled upon this.

Don't know if someone is still interested but i've elaborated a bit. The current alternative to the deprecated createScriptProcessor is the AudioWorklet interface.

From: https://webaudio.github.io/web-audio-api/#audioworklet

1.32.1. Concepts

The AudioWorklet object allows developers to supply scripts (such as JavaScript or >WebAssembly code) to process audio on the rendering thread, supporting custom >AudioNodes. This processing mechanism ensures synchronous execution of the script >code with other built-in AudioNodes in the audio graph.

You cannot implement interfaces in Javascript as far as i know but you can extend a class derived from it.

And the one we need is: https://developer.mozilla.org/en-US/docs/Web/API/AudioWorkletProcessor

So i did write a processor that just mirrors the output with the input values and displays them.

class CustomAudioProcessor extends AudioWorkletProcessor {
    process (inputs, outputs, parameters) {
        const input = inputs[0];
        const output = output[0];
        for (let channel = 0; channel < input.length; ++channel) {   
            for (let i = 0; i < input[channel].length; ++i) {
            // Just copying all the data from input to output
            output[channel][i] = input[channel][i];
            // The next one will make the app crash but yeah, the values are there
            // console.log(output[channel][i]);
            }
        }
    }
}

The processor must then be placed into the audio pipeline, after the microphone and before the speakers.

function record() {

constraints = { audio: true };
navigator.mediaDevices.getUserMedia(constraints)
.then(function(stream) {
   audioCtx = new AudioContext();
    var source = audioCtx.createMediaStreamSource(stream);
    audioCtx.audioWorklet.addModule("custom-audio-processor.js").then(() => {
        customAudioProcessor = new AudioWorkletNode(audioCtx, "custom-audio-processor");
        source.connect(customAudioProcessor);
        customAudioProcessor.connect(audioCtx.destination);
    }) 

    audioCtx.destination.play();

Works! Good luck! :)