Menu
Realtime moving Waveform
I'm currently playing with Web Audio API and made a spectrum using canvas.
function animate(){
var a=new Uint8Array(analyser.frequencyBinCount),
y=new Uint8Array(analyser.frequencyBinCount),b,c,d;
analyser.getByteTimeDomainData(y);
analyser.getByteFrequencyData(a);
b=c=a.length;
d=w/c;
ctx.clearRect(0,0,w,h);
while(b--){
var bh=a[b]+1;
ctx.fillStyle='hsla('+(b/c*240)+','+(y[b]/255*100|0)+'%,50%,1)';
ctx.fillRect(1*b,h-bh,1,bh);
ctx.fillRect(1*b,y[b],1,1);
}
animation=webkitRequestAnimationFrame(animate);
}
Mini question: is there a way to not write 2 times new Uint8Array(analyser.frequencyBinCount)?
DEMO
add a MP3/MP4 file and wait. (tested in Chrome)
http://jsfiddle.net/pc76H/2/
But there are many problems. I can't find a proper documentation of the various audio filters.
Also, if you look at the spectrum you will notice that after 70% or the range there is no data. What does that mean? that maybe from 16k hz to 20k hz is no sound? I would apply a text to the canvas to show the various HZ. but where??
I found out that the returned data is a power of 32 in length with a max of 2048 and the height is always 256.
BUT the real question is ... I want to create a moving waveform like in traktor.
I already did that some time ago with PHP it converts the file to low bitrate than extracts the data and coverts that to a image. i found the script somewhere...but I don't remember where... note: needs LAME
<?php
$a=$_GET["f"];
if(file_exists($a)){
if(file_exists($a.".png")){
header("Content-Type: image/png");
echo file_get_contents($a.".png");
}else{
$b=3000;$c=300;define("d",3);
ini_set("max_execution_time","30000");
function n($g,$h){
$g=hexdec(bin2hex($g));
$h=hexdec(bin2hex($h));
return($g+($h*256));
};
$k=substr(md5(time()),0,10);
copy(realpath($a),"/var/www/".$k."_o.mp3");
exec("lame /var/www/{$k}_o.mp3 -f -m m -b 16 --resample 8 /var/www/{$k}.mp3 && lame --decode /var/www/{$k}.mp3 /var/www/{$k}.wav");
//system("lame {$k}_o.mp3 -f -m m -b 16 --resample 8 {$k}.mp3 && lame --decode {$k}.mp3 {$k}.wav");
@unlink("/var/www/{$k}_o.mp3");
@unlink("/var/www/{$k}.mp3");
$l="/var/www/{$k}.wav";
$m=fopen($l,"r");
$n[]=fread($m,4);
$n[]=bin2hex(fread($m,4));
$n[]=fread($m,4);
$n[]=fread($m,4);
$n[]=bin2hex(fread($m,4));
$n[]=bin2hex(fread($m,2));
$n[]=bin2hex(fread($m,2));
$n[]=bin2hex(fread($m,4));
$n[]=bin2hex(fread($m,4));
$n[]=bin2hex(fread($m,2));
$n[]=bin2hex(fread($m,2));
$n[]=fread($m,4);
$n[]=bin2hex(fread($m,4));
$o=hexdec(substr($n[10],0,2));
$p=$o/8;
$q=hexdec(substr($n[6],0,2));
if($q==2){$r=40;}else{$r=80;};
while(!feof($m)){
$t=array();
for($i=0;$i<$p;$i++){
$t[$i]=fgetc($m);
};
switch($p){
case 1:$s[]=n($t[0],$t[1]);break;
case 2:if(ord($t[1])&128){$u=0;}else{$u=128;};$u=chr((ord($t[1])&127)+$u);$s[]= floor(n($t[0],$u)/256);break;
};
fread($m,$r);
};
fclose($m);
unlink("/var/www/{$k}.wav");
$x=imagecreatetruecolor(sizeof($s)/d,$c);
imagealphablending($x,false);
imagesavealpha($x,true);
$y=imagecolorallocatealpha($x,255,255,255,127);
imagefilledrectangle($x,0,0,sizeof($s)/d,$c,$y);
for($d=0;$d<sizeof($s);$d+=d){
$v=(int)($s[$d]/255*$c);
imageline($x,$d/d,0+($c-$v),$d/d,$c-($c-$v),imagecolorallocate($x,255,0,255));
};
$z=imagecreatetruecolor($b,$c);
imagealphablending($z,false);
imagesavealpha($z,true);
imagefilledrectangle($z,0,0,$b,$c,$y);
imagecopyresampled($z,$x,0,0,0,0,$b,$c,sizeof($s)/d,$c);
imagepng($z,realpath($a).".png");
header("Content-Type: image/png");
imagepng($z);
imagedestroy($z);
};
}else{
echo $a;
};
?>
The script works... but you are limited to a max image size of 4k pixels.
so you have not a nice waveform if it should rappresent only some milliseconds.
What do i need to store/create a realtime waveform like the traktors app or this php script? btw the traktor has also a colored waveform(the php script not).
EDIT
I rewrote your script that it fits my idea... it's relatively fast.
As you can see inside the function createArray i push the various lines into an object with the key as x coordinate.
I'm simply taking the the highest number.
here is where we could play with the colors.
var ajaxB,AC,B,LC,op,x,y,ARRAY={},W=1024,H=256;
var aMax=Math.max.apply.bind(Math.max, Math);
function error(a){
console.log(a);
};
function createDrawing(){
console.log('drawingArray');
var C=document.createElement('canvas');
C.width=W;
C.height=H;
document.body.appendChild(C);
var context=C.getContext('2d');
context.save();
context.strokeStyle='#121';
context.globalCompositeOperation='lighter';
L2=W*1;
while(L2--){
context.beginPath();
context.moveTo(L2,0);
context.lineTo(L2+1,ARRAY[L2]);
context.stroke();
}
context.restore();
};
function createArray(a){
console.log('creatingArray');
B=a;
LC=B.getChannelData(0);// Float32Array describing left channel
L=LC.length;
op=W/L;
for(var i=0;i<L;i++){
x=W*i/L|0;
y=LC[i]*H/2;
if(ARRAY[x]){
ARRAY[x].push(y)
}else{
!ARRAY[x-1]||(ARRAY[x-1]=aMax(ARRAY[x-1]));
// the above line contains an array of values
// which could be converted to a color
// or just simply create a gradient
// based on avg max min (frequency???) whatever
ARRAY[x]=[y]
}
};
createDrawing();
};
function decode(){
console.log('decodingMusic');
AC=new webkitAudioContext
AC.decodeAudioData(this.response,createArray,error);
};
function loadMusic(url){
console.log('loadingMusic');
ajaxB=new XMLHttpRequest;
ajaxB.open('GET',url);
ajaxB.responseType='arraybuffer';
ajaxB.onload=decode;
ajaxB.send();
}
loadMusic('AudioOrVideo.mp4');
857
Ok, so what i would do is to load the sound with an XMLHttpRequest, then decode it using webaudio, then display it 'carefully' to have the colors you are searching for.
I just made a quick version, copy-pasting from various of my projects, it is quite working, as you might see with this picture :
The issue is that it is slow as hell. To have (more) decent speed, you'll have to do some computation to reduce the number of lines to draw on the canvas, because at 441000 Hz, you very quickly get too many lines to draw.
// AUDIO CONTEXT
window.AudioContext = window.AudioContext || window.webkitAudioContext ;
if (!AudioContext) alert('This site cannot be run in your Browser. Try a recent Chrome or Firefox. ');
var audioContext = new AudioContext();
var currentBuffer = null;
// CANVAS
var canvasWidth = 512, canvasHeight = 120 ;
var newCanvas = createCanvas (canvasWidth, canvasHeight);
var context = null;
window.onload = appendCanvas;
function appendCanvas() { document.body.appendChild(newCanvas);
context = newCanvas.getContext('2d'); }
// MUSIC LOADER + DECODE
function loadMusic(url) {
var req = new XMLHttpRequest();
req.open( "GET", url, true );
req.responseType = "arraybuffer";
req.onreadystatechange = function (e) {
if (req.readyState == 4) {
if(req.status == 200)
audioContext.decodeAudioData(req.response,
function(buffer) {
currentBuffer = buffer;
displayBuffer(buffer);
}, onDecodeError);
else
alert('error during the load.Wrong url or cross origin issue');
}
} ;
req.send();
}
function onDecodeError() { alert('error while decoding your file.'); }
// MUSIC DISPLAY
function displayBuffer(buff /* is an AudioBuffer */) {
var leftChannel = buff.getChannelData(0); // Float32Array describing left channel
var lineOpacity = canvasWidth / leftChannel.length ;
context.save();
context.fillStyle = '#222' ;
context.fillRect(0,0,canvasWidth,canvasHeight );
context.strokeStyle = '#121';
context.globalCompositeOperation = 'lighter';
context.translate(0,canvasHeight / 2);
context.globalAlpha = 0.06 ; // lineOpacity ;
for (var i=0; i< leftChannel.length; i++) {
// on which line do we get ?
var x = Math.floor ( canvasWidth * i / leftChannel.length ) ;
var y = leftChannel[i] * canvasHeight / 2 ;
context.beginPath();
context.moveTo( x , 0 );
context.lineTo( x+1, y );
context.stroke();
}
context.restore();
console.log('done');
}
function createCanvas ( w, h ) {
var newCanvas = document.createElement('canvas');
newCanvas.width = w; newCanvas.height = h;
return newCanvas;
};
loadMusic('could_be_better.mp3');
Edit : The issue here is that we have too much data to draw. Take a 3 minutes mp3, you'll have 3*60*44100 = about 8.000.000 line to draw. On a display that has, say, 1024 px resolution, that makes 8.000 lines per pixel...
In the code above, the canvas is doing the 'resampling', by drawing lines with low-opacity and in 'ligther' composition mode (e.g. pixel's r,g,b will add-up).
To speed-up things, you have to re-sample by yourself, but to get some colors, it's not just a down-sampling, you'll have to handle a set (within a performance array most probably) of 'buckets', one for each horizontal pixel (so, say 1024), and in every bucket you compute the cumulated sound pressure, the variance, min, max and then, at display time, you decide how you will render that with colors.
For instance :
values between 0 positiveMin are very clear. (any sample is below that point).
values between positiveMin and positiveAverage - variance are darker,
values between positiveAverage - variance and positiveAverage + variance are darker,
and values between positiveAverage+variance and positiveMax lighter .
(same for negative values)
That makes 5 colors for each bucket, and it's still quite some work, for you to code and for the browser to compute.
I don't know if the performance could get decent with this, but i fear the statistics accuracy and the color coding of the software you mention can't be reached on a browser (obviously not in real-time), and that you'll have to make some compromises.
Edit 2 :
I tried to get some colors out of stats but it quite failed. My guess, now, is that the guys at tracktor also change color depending on frequency.... quite some work here....
Anyway, just for the record, the code for an average / mean variation follows.
(variance was too low, i had to use mean variation).
// MUSIC DISPLAY
function displayBuffer2(buff /* is an AudioBuffer */) {
var leftChannel = buff.getChannelData(0); // Float32Array describing left channel
// we 'resample' with cumul, count, variance
// Offset 0 : PositiveCumul 1: PositiveCount 2: PositiveVariance
// 3 : NegativeCumul 4: NegativeCount 5: NegativeVariance
// that makes 6 data per bucket
var resampled = new Float64Array(canvasWidth * 6 );
var i=0, j=0, buckIndex = 0;
var min=1e3, max=-1e3;
var thisValue=0, res=0;
var sampleCount = leftChannel.length;
// first pass for mean
for (i=0; i<sampleCount; i++) {
// in which bucket do we fall ?
buckIndex = 0 | ( canvasWidth * i / sampleCount );
buckIndex *= 6;
// positive or negative ?
thisValue = leftChannel[i];
if (thisValue>0) {
resampled[buckIndex ] += thisValue;
resampled[buckIndex + 1] +=1;
} else if (thisValue<0) {
resampled[buckIndex + 3] += thisValue;
resampled[buckIndex + 4] +=1;
}
if (thisValue<min) min=thisValue;
if (thisValue>max) max = thisValue;
}
// compute mean now
for (i=0, j=0; i<canvasWidth; i++, j+=6) {
if (resampled[j+1] != 0) {
resampled[j] /= resampled[j+1]; ;
}
if (resampled[j+4]!= 0) {
resampled[j+3] /= resampled[j+4];
}
}
// second pass for mean variation ( variance is too low)
for (i=0; i<leftChannel.length; i++) {
// in which bucket do we fall ?
buckIndex = 0 | (canvasWidth * i / leftChannel.length );
buckIndex *= 6;
// positive or negative ?
thisValue = leftChannel[i];
if (thisValue>0) {
resampled[buckIndex + 2] += Math.abs( resampled[buckIndex] - thisValue );
} else if (thisValue<0) {
resampled[buckIndex + 5] += Math.abs( resampled[buckIndex + 3] - thisValue );
}
}
// compute mean variation/variance now
for (i=0, j=0; i<canvasWidth; i++, j+=6) {
if (resampled[j+1]) resampled[j+2] /= resampled[j+1];
if (resampled[j+4]) resampled[j+5] /= resampled[j+4];
}
context.save();
context.fillStyle = '#000' ;
context.fillRect(0,0,canvasWidth,canvasHeight );
context.translate(0.5,canvasHeight / 2);
context.scale(1, 200);
for (var i=0; i< canvasWidth; i++) {
j=i*6;
// draw from positiveAvg - variance to negativeAvg - variance
context.strokeStyle = '#F00';
context.beginPath();
context.moveTo( i , (resampled[j] - resampled[j+2] ));
context.lineTo( i , (resampled[j +3] + resampled[j+5] ) );
context.stroke();
// draw from positiveAvg - variance to positiveAvg + variance
context.strokeStyle = '#FFF';
context.beginPath();
context.moveTo( i , (resampled[j] - resampled[j+2] ));
context.lineTo( i , (resampled[j] + resampled[j+2] ) );
context.stroke();
// draw from negativeAvg + variance to negativeAvg - variance
// context.strokeStyle = '#FFF';
context.beginPath();
context.moveTo( i , (resampled[j+3] + resampled[j+5] ));
context.lineTo( i , (resampled[j+3] - resampled[j+5] ) );
context.stroke();
}
context.restore();
console.log('done 231 iyi');
}
// AUDIO CONTEXT window.AudioContext = (window.AudioContext || window.webkitAudioContext || window.mozAudioContext || window.oAudioContext || window.msAudioContext); if (!AudioContext) alert('This site cannot be run in your Browser. Try a recent Chrome or Firefox. '); var audioContext = new AudioContext(); var currentBuffer = null; // CANVAS var canvasWidth = window.innerWidth, canvasHeight = 120 ; var newCanvas = createCanvas (canvasWidth, canvasHeight); var context = null; window.onload = appendCanvas; function appendCanvas() { document.body.appendChild(newCanvas); context = newCanvas.getContext('2d'); } // MUSIC LOADER + DECODE function loadMusic(url) { var req = new XMLHttpRequest(); req.open( "GET", url, true ); req.responseType = "arraybuffer"; req.onreadystatechange = function (e) { if (req.readyState == 4) { if(req.status == 200) audioContext.decodeAudioData(req.response, function(buffer) { currentBuffer = buffer; displayBuffer(buffer); }, onDecodeError); else alert('error during the load.Wrong url or cross origin issue'); } } ; req.send(); } function onDecodeError() { alert('error while decoding your file.'); } // MUSIC DISPLAY function displayBuffer(buff /* is an AudioBuffer */) { var drawLines = 500; var leftChannel = buff.getChannelData(0); // Float32Array describing left channel var lineOpacity = canvasWidth / leftChannel.length ; context.save(); context.fillStyle = '#080808' ; context.fillRect(0,0,canvasWidth,canvasHeight ); context.strokeStyle = '#46a0ba'; context.globalCompositeOperation = 'lighter'; context.translate(0,canvasHeight / 2); //context.globalAlpha = 0.6 ; // lineOpacity ; context.lineWidth=1; var totallength = leftChannel.length; var eachBlock = Math.floor(totallength / drawLines); var lineGap = (canvasWidth/drawLines); context.beginPath(); for(var i=0;i<=drawLines;i++){ var audioBuffKey = Math.floor(eachBlock * i); var x = i*lineGap; var y = leftChannel[audioBuffKey] * canvasHeight / 2; context.moveTo( x, y ); context.lineTo( x, (y*-1) ); } context.stroke(); context.restore(); } function createCanvas ( w, h ) { var newCanvas = document.createElement('canvas'); newCanvas.width = w; newCanvas.height = h; return newCanvas; }; loadMusic('https://raw.githubusercontent.com/katspaugh/wavesurfer.js/master/example/media/demo.wav');Based on the top answer, I have controlled that by reducing number of lines want to draw and little canvas function call placement. see following code for your reference.
// AUDIO CONTEXT
window.AudioContext = (window.AudioContext ||
window.webkitAudioContext ||
window.mozAudioContext ||
window.oAudioContext ||
window.msAudioContext);
if (!AudioContext) alert('This site cannot be run in your Browser. Try a recent Chrome or Firefox. ');
var audioContext = new AudioContext();
var currentBuffer = null;
// CANVAS
var canvasWidth = window.innerWidth, canvasHeight = 120 ;
var newCanvas = createCanvas (canvasWidth, canvasHeight);
var context = null;
window.onload = appendCanvas;
function appendCanvas() { document.body.appendChild(newCanvas);
context = newCanvas.getContext('2d'); }
// MUSIC LOADER + DECODE
function loadMusic(url) {
var req = new XMLHttpRequest();
req.open( "GET", url, true );
req.responseType = "arraybuffer";
req.onreadystatechange = function (e) {
if (req.readyState == 4) {
if(req.status == 200)
audioContext.decodeAudioData(req.response,
function(buffer) {
currentBuffer = buffer;
displayBuffer(buffer);
}, onDecodeError);
else
alert('error during the load.Wrong url or cross origin issue');
}
} ;
req.send();
}
function onDecodeError() { alert('error while decoding your file.'); }
// MUSIC DISPLAY
function displayBuffer(buff /* is an AudioBuffer */) {
var drawLines = 500;
var leftChannel = buff.getChannelData(0); // Float32Array describing left channel
var lineOpacity = canvasWidth / leftChannel.length ;
context.save();
context.fillStyle = '#080808' ;
context.fillRect(0,0,canvasWidth,canvasHeight );
context.strokeStyle = '#46a0ba';
context.globalCompositeOperation = 'lighter';
context.translate(0,canvasHeight / 2);
//context.globalAlpha = 0.6 ; // lineOpacity ;
context.lineWidth=1;
var totallength = leftChannel.length;
var eachBlock = Math.floor(totallength / drawLines);
var lineGap = (canvasWidth/drawLines);
context.beginPath();
for(var i=0;i<=drawLines;i++){
var audioBuffKey = Math.floor(eachBlock * i);
var x = i*lineGap;
var y = leftChannel[audioBuffKey] * canvasHeight / 2;
context.moveTo( x, y );
context.lineTo( x, (y*-1) );
}
context.stroke();
context.restore();
}
function createCanvas ( w, h ) {
var newCanvas = document.createElement('canvas');
newCanvas.width = w; newCanvas.height = h;
return newCanvas;
};
loadMusic('could_be_better.mp3');this is a bit old, sorry to bump, but it's the only post about displaying a full waveform with the Web Audio Api and I'd like to share what method i used.
This method is not perfect but it only goes through the displayed audio and it only goes over it once. it also succeeds in displaying an actual waveform for short files or big zoom :
and a convincing loudness chart for bigger files dezoomed :
here is what it's like at middle zoom, kind of pleasant too:
notice that both zooms use the same algorythm. I still struggle about scales (the zoomed waveform is bigger than the dezoomed one (though not so bigger than displayed on the images)
this algorythm i find is quite efficient (i can change zoom on 4mn music and it redraws flawlessly every 0.1s)
function drawWaveform (audioBuffer, canvas, pos = 0.5, zoom = 1) {
const canvasCtx = canvas.getContext("2d")
const width = canvas.clientWidth
const height = canvas.clientHeight
canvasCtx.clearRect(0, 0, width, height)
canvasCtx.fillStyle = "rgb(255, 0, 0)"
// calculate displayed part of audio
// and slice audio buffer to only process that part
const bufferLength = audioBuffer.length
const zoomLength = bufferLength / zoom
const start = Math.max(0, bufferLength * pos - zoomLength / 2)
const end = Math.min(bufferLength, start + zoomLength)
const rawAudioData = audioBuffer.getChannelData(0).slice(start, end)
// process chunks corresponding to 1 pixel width
const chunkSize = Math.max(1, Math.floor(rawAudioData.length / width))
const values = []
for (let x = 0; x < width; x++) {
const start = x*chunkSize
const end = start + chunkSize
const chunk = rawAudioData.slice(start, end)
// calculate the total positive and negative area
let positive = 0
let negative = 0
chunk.forEach(val =>
val > 0 && (positive += val) || val < 0 && (negative += val)
)
// make it mean (this part makes dezommed audio smaller, needs improvement)
negative /= chunk.length
positive /= chunk.length
// calculate amplitude of the wave
chunkAmp = -(negative - positive)
// draw the bar corresponding to this pixel
canvasCtx.fillRect(
x,
height / 2 - positive * height,
1,
Math.max(1, chunkAmp * height)
)
}
}
To use it :
async function decodeAndDisplayAudio (audioData) {
const source = audioCtx.createBufferSource()
source.buffer = await audioCtx.decodeAudioData(audioData)
drawWaveform(source.buffer, canvas, 0.5, 1)
// change position (0//start -> 0.5//middle -> 1//end)
// and zoom (0.5//full -> 400//zoomed) as you wish
}
// audioData comes raw from the file (server send it in my case)
decodeAndDisplayAudio(audioData)
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
