polyphonic audio playback with node.js on raspberry pi

Question

I've been trying to create polyphonic WAV playback with node.js on raspberry pi 3 running latest raspbian:

• shelling out to aplay/mpg123/some other program - allows me to only play single sound at once
• I tried combination of https://github.com/sebpiq/node-web-audio-api and https://github.com/TooTallNate/node-speaker (sample code below) but audio quality is very low, with a lot of distortions

Is there anything I'm missing here? I know I could easily do it in another programming language (I was able to write C++ code with SDL, and Python with pygame), but the question is if it's possible with node.js :)

Here's my current web-audio-api + node-speaker code:

var AudioContext = require('web-audio-api').AudioContext;
var Speaker      = require('speaker');
var fs           = require('fs');

var track1       = './tracks/1.wav';
var track2       = './tracks/1.wav';

var context      = new AudioContext();

context.outStream = new Speaker({
  channels:   context.format.numberOfChannels,
  bitDepth:   context.format.bitDepth,
  sampleRate: context.format.sampleRate
});

function play(audioBuffer) {
  if (!audioBuffer) { return; }

  var bufferSource = context.createBufferSource();

  bufferSource.connect(context.destination);
  bufferSource.buffer = audioBuffer;
  bufferSource.loop   = false;
  bufferSource.start(0);
}

var audioData1 = fs.readFileSync(track1);
var audioData2 = fs.readFileSync(track2);

var audioBuffer1, audioBuffer2;

context.decodeAudioData(audioData1, function(audioBuffer) {
  audioBuffer1 = audioBuffer;
  if (audioBuffer1 && audioBuffer2) { playBoth(); }
});

context.decodeAudioData(audioData2, function(audioBuffer) {
  audioBuffer2 = audioBuffer;
  if (audioBuffer1 && audioBuffer2) { playBoth(); }
});

function playBoth() {
  console.log('playing...');

  play(audioBuffer1);
  play(audioBuffer2);
}

Answer 1

audio quality is very low, with a lot of distortions

According to the WebAudio spec (https://webaudio.github.io/web-audio-api/#SummingJunction):

No clipping is applied at the inputs or outputs of the AudioNode to allow a maximum of dynamic range within the audio graph.

Now if you're playing two audio streams, it's possible that summing them results in a value that's beyond the acceptable range, which sounds like - distortions.

Try lowering the volume of each audio stream by first piping them through a GainNode as so:

function play(audioBuffer) {
  if (!audioBuffer) { return; }

  var bufferSource = context.createBufferSource();
  var gainNode = context.createGain();
  gainNode.gain.value = 0.5 // for instance, find a good value

  bufferSource.connect(gainNode);
  gainNode.connect(context.destination);
  bufferSource.buffer = audioBuffer;
  bufferSource.loop   = false;
  bufferSource.start(0);
}

Alternatively, you could use a DynamicsCompressorNode, but manually setting the gain gives you more control over the output.