Here we capture microphone audio as a Web Audio API event loop buffer using getUserMedia() … time domain and frequency domain snippets of each audio event loop buffer are printed (viewable in browser console just hit key F12 or ctrl+shift+i )
<html><head><meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>capture microphone audio into buffer</title>
<script type="text/javascript">
var webaudio_tooling_obj = function () {
var audioContext = new AudioContext();
console.log("audio is starting up ...");
var BUFF_SIZE = 16384;
var audioInput = null,
microphone_stream = null,
gain_node = null,
script_processor_node = null,
script_processor_fft_node = null,
analyserNode = null;
if (!navigator.getUserMedia)
navigator.getUserMedia = navigator.getUserMedia || navigator.webkitGetUserMedia ||
navigator.mozGetUserMedia || navigator.msGetUserMedia;
if (navigator.getUserMedia){
navigator.getUserMedia({audio:true},
function(stream) {
start_microphone(stream);
},
function(e) {
alert('Error capturing audio.');
}
);
} else { alert('getUserMedia not supported in this browser.'); }
// ---
function show_some_data(given_typed_array, num_row_to_display, label) {
var size_buffer = given_typed_array.length;
var index = 0;
var max_index = num_row_to_display;
console.log("__________ " + label);
for (; index < max_index && index < size_buffer; index += 1) {
console.log(given_typed_array[index]);
}
}
function process_microphone_buffer(event) { // invoked by event loop
var i, N, inp, microphone_output_buffer;
microphone_output_buffer = event.inputBuffer.getChannelData(0); // just mono - 1 channel for now
// microphone_output_buffer <-- this buffer contains current gulp of data size BUFF_SIZE
show_some_data(microphone_output_buffer, 5, "from getChannelData");
}
function start_microphone(stream){
gain_node = audioContext.createGain();
gain_node.connect( audioContext.destination );
microphone_stream = audioContext.createMediaStreamSource(stream);
microphone_stream.connect(gain_node);
script_processor_node = audioContext.createScriptProcessor(BUFF_SIZE, 1, 1);
script_processor_node.onaudioprocess = process_microphone_buffer;
microphone_stream.connect(script_processor_node);
// --- enable volume control for output speakers
document.getElementById('volume').addEventListener('change', function() {
var curr_volume = this.value;
gain_node.gain.value = curr_volume;
console.log("curr_volume ", curr_volume);
});
// --- setup FFT
script_processor_fft_node = audioContext.createScriptProcessor(2048, 1, 1);
script_processor_fft_node.connect(gain_node);
analyserNode = audioContext.createAnalyser();
analyserNode.smoothingTimeConstant = 0;
analyserNode.fftSize = 2048;
microphone_stream.connect(analyserNode);
analyserNode.connect(script_processor_fft_node);
script_processor_fft_node.onaudioprocess = function() {
// get the average for the first channel
var array = new Uint8Array(analyserNode.frequencyBinCount);
analyserNode.getByteFrequencyData(array);
// draw the spectrogram
if (microphone_stream.playbackState == microphone_stream.PLAYING_STATE) {
show_some_data(array, 5, "from fft");
}
};
}
}(); // webaudio_tooling_obj = function()
</script>
</head>
<body>
<p>Volume</p>
<input id="volume" type="range" min="0" max="1" step="0.1" value="0.5"/>
</body>
</html>
Since this code exposes microphone data as a buffer you could add ability to stream using websockets or simply aggregate each event loop buffer into a monster buffer then download the monster to a file
Notice the call to
var audioContext = new AudioContext();
which indicates its using the Web Audio API which is baked into all modern browsers (including mobile browsers) to provide an extremely powerful audio platform of which tapping into the mic is but a tiny fragment … NOTE the CPU usage jumps up due to this demo writing each event loop buffer into browser console log which is for testing only so actual use is far less resource intensive even when you mod this to stream audio to elsewhere
Links to some Web Audio API documentation