オーディオ用 Media Source Extensions

var audio = document.createElement('audio');
var mediaSource = new MediaSource();
var SEGMENTS = 5;

mediaSource.addEventListener('sourceopen', function() {
    var sourceBuffer = mediaSource.addSourceBuffer('audio/mpeg');

    function onAudioLoaded(data, index) {
    // Append the ArrayBuffer data into our new SourceBuffer.
    sourceBuffer.appendBuffer(data);
    }

    // Retrieve an audio segment via XHR.  For simplicity, we're retrieving the
    // entire segment at once, but we could also retrieve it in chunks and append
    // each chunk separately.  MSE will take care of assembling the pieces.
    GET('sintel/sintel_0.mp3', function(data) { onAudioLoaded(data, 0); } );
});

audio.src = URL.createObjectURL(mediaSource);

function onAudioLoaded(data, index) {
    // Parsing gapless metadata is unfortunately non trivial and a bit messy, so
    // we'll glaze over it here; see the appendix for details.
    // ParseGaplessData() will return a dictionary with two elements:
    //
    //    audioDuration: Duration in seconds of all non-padding audio.
    //    frontPaddingDuration: Duration in seconds of the front padding.
    //
    var gaplessMetadata = ParseGaplessData(data);

    // Each appended segment must be appended relative to the next.  To avoid any
    // overlaps, we'll use the end timestamp of the last append as the starting
    // point for our next append or zero if we haven't appended anything yet.
    var appendTime = index > 0 ? sourceBuffer.buffered.end(0) : 0;

    // Simply put, an append window allows you to trim off audio (or video) frames
    // which fall outside of a specified time range.  Here, we'll use the end of
    // our last append as the start of our append window and the end of the real
    // audio data for this segment as the end of our append window.
    sourceBuffer.appendWindowStart = appendTime;
    sourceBuffer.appendWindowEnd = appendTime + gaplessMetadata.audioDuration;

    // The timestampOffset field essentially tells MediaSource where in the media
    // timeline the data given to appendBuffer() should be placed.  I.e., if the
    // timestampOffset is 1 second, the appended data will start 1 second into
    // playback.
    //
    // MediaSource requires that the media timeline starts from time zero, so we
    // need to ensure that the data left after filtering by the append window
    // starts at time zero.  We'll do this by shifting all of the padding we want
    // to discard before our append time (and thus, before our append window).
    sourceBuffer.timestampOffset =
        appendTime - gaplessMetadata.frontPaddingDuration;

    // When appendBuffer() completes, it will fire an updateend event signaling
    // that it's okay to append another segment of media.  Here, we'll chain the
    // append for the next segment to the completion of our current append.
    if (index == 0) {
    sourceBuffer.addEventListener('updateend', function() {
        if (++index < SEGMENTS) {
        GET('sintel/sintel_' + index + '.mp3',
            function(data) { onAudioLoaded(data, index); });
        } else {
        // We've loaded all available segments, so tell MediaSource there are no
        // more buffers which will be appended.
        mediaSource.endOfStream();
        URL.revokeObjectURL(audio.src);
        }
    });
    }

    // appendBuffer() will now use the timestamp offset and append window settings
    // to filter and timestamp the data we're appending.
    //
    // Note: While this demo uses very little memory, more complex use cases need
    // to be careful about memory usage or garbage collection may remove ranges of
    // media in unexpected places.
    sourceBuffer.appendBuffer(data);
}

unzip Jan_Morgenstern-Sintel-FLAC.zip
sha1sum 1-Snow_Fight.flac
# 0535ca207ccba70d538f7324916a3f1a3d550194  1-Snow_Fight.flac

ffmpeg -i 1-Snow_Fight.flac -t 31.5 -af "afade=t=out:st=28:d=2.5" sintel.flac

ffmpeg -i sintel.flac -acodec pcm_f32le -map 0 -f segment \
        -segment_list out.list -segment_time 6.5 sintel_%d.wav

lame -V=2 sintel_0.wav sintel_0.mp3
lame -V=2 sintel_1.wav sintel_1.mp3
lame -V=2 sintel_2.wav sintel_2.mp3
lame -V=2 sintel_3.wav sintel_3.mp3
lame -V=2 sintel_4.wav sintel_4.mp3

afconvert sintel_0.wav sintel_0_intermediate.caf -d 0 -f caff \
            --soundcheck-generate
afconvert sintel_1.wav sintel_1_intermediate.caf -d 0 -f caff \
            --soundcheck-generate
afconvert sintel_2.wav sintel_2_intermediate.caf -d 0 -f caff \
            --soundcheck-generate
afconvert sintel_3.wav sintel_3_intermediate.caf -d 0 -f caff \
            --soundcheck-generate
afconvert sintel_4.wav sintel_4_intermediate.caf -d 0 -f caff \
            --soundcheck-generate
afconvert sintel_0_intermediate.caf -d aac -f m4af -u pgcm 2 --soundcheck-read \
            -b 256000 -q 127 -s 2 sintel_0.m4a
afconvert sintel_1_intermediate.caf -d aac -f m4af -u pgcm 2 --soundcheck-read \
            -b 256000 -q 127 -s 2 sintel_1.m4a
afconvert sintel_2_intermediate.caf -d aac -f m4af -u pgcm 2 --soundcheck-read \
            -b 256000 -q 127 -s 2 sintel_2.m4a
afconvert sintel_3_intermediate.caf -d aac -f m4af -u pgcm 2 --soundcheck-read \
            -b 256000 -q 127 -s 2 sintel_3.m4a
afconvert sintel_4_intermediate.caf -d aac -f m4af -u pgcm 2 --soundcheck-read \
            -b 256000 -q 127 -s 2 sintel_4.m4a

MP4Box -dash 1000 sintel_0.m4a && mv sintel_0_dashinit.mp4 sintel_0.mp4
MP4Box -dash 1000 sintel_1.m4a && mv sintel_1_dashinit.mp4 sintel_1.mp4
MP4Box -dash 1000 sintel_2.m4a && mv sintel_2_dashinit.mp4 sintel_2.mp4
MP4Box -dash 1000 sintel_3.m4a && mv sintel_3_dashinit.mp4 sintel_3.mp4
MP4Box -dash 1000 sintel_4.m4a && mv sintel_4_dashinit.mp4 sintel_4.mp4
rm sintel_{0,1,2,3,4}_dash.mpd

// Since most MP3 encoders store the gapless metadata in binary, we'll need a
// method for turning bytes into integers.  Note: This doesn't work for values
// larger than 2^30 since we'll overflow the signed integer type when shifting.
function ReadInt(buffer) {
    var result = buffer.charCodeAt(0);
    for (var i = 1; i < buffer.length; ++i) {
    result <<../= 8;
    result += buffer.charCodeAt(i);
    }
    return result;
}

function ParseGaplessData(arrayBuffer) {
    // Gapless data is generally within the first 512 bytes, so limit parsing.
    var byteStr = new TextDecoder().decode(arrayBuffer.slice(0, 512));

    var frontPadding = 0, endPadding = 0, realSamples = 0;

    // ... we'll fill this in as we go below.

iTunSMPB[ 26 bytes ]0000000 00000840 000001C0 0000000000046E00

// iTunes encodes the gapless data as hex strings like so:
//
//    'iTunSMPB[ 26 bytes ]0000000 00000840 000001C0 0000000000046E00'
//    'iTunSMPB[ 26 bytes ]####### frontpad  endpad    real samples'
//
// The approach here elides the complexity of actually parsing MP4 atoms. It
// may not work for all files without some tweaks.
var iTunesDataIndex = byteStr.indexOf('iTunSMPB');
if (iTunesDataIndex != -1) {
    var frontPaddingIndex = iTunesDataIndex + 34;
    frontPadding = parseInt(byteStr.substr(frontPaddingIndex, 8), 16);

    var endPaddingIndex = frontPaddingIndex + 9;
    endPadding = parseInt(byteStr.substr(endPaddingIndex, 8), 16);

    var sampleCountIndex = endPaddingIndex + 9;
    realSamples = parseInt(byteStr.substr(sampleCountIndex, 16), 16);
}

// Xing padding is encoded as 24bits within the header.  Note: This code will
// only work for Layer3 Version 1 and Layer2 MP3 files with XING frame counts
// and gapless information.  See the following document for more details:
// http://www.codeproject.com/Articles/8295/MPEG-Audio-Frame-Header
var xingDataIndex = byteStr.indexOf('Xing');
if (xingDataIndex == -1) xingDataIndex = byteStr.indexOf('Info');
if (xingDataIndex != -1) {
    // See section 2.3.1 in the link above for the specifics on parsing the Xing
    // frame count.
    var frameCountIndex = xingDataIndex + 8;
    var frameCount = ReadInt(byteStr.substr(frameCountIndex, 4));

    // For Layer3 Version 1 and Layer2 there are 1152 samples per frame.  See
    // section 2.1.5 in the link above for more details.
    var paddedSamples = frameCount * 1152;

    // ... we'll cover this below.

xingDataIndex = byteStr.indexOf('LAME');
if (xingDataIndex == -1) xingDataIndex = byteStr.indexOf('Lavf');
if (xingDataIndex != -1) {
    // See http://gabriel.mp3-tech.org/mp3infotag.html#delays for details of
    // how this information is encoded and parsed.
    var gaplessDataIndex = xingDataIndex + 21;
    var gaplessBits = ReadInt(byteStr.substr(gaplessDataIndex, 3));

    // Upper 12 bits are the front padding, lower are the end padding.
    frontPadding = gaplessBits >> 12;
    endPadding = gaplessBits & 0xFFF;
}

realSamples = paddedSamples - (frontPadding + endPadding);
}

return {
audioDuration: realSamples * SECONDS_PER_SAMPLE,
frontPaddingDuration: frontPadding * SECONDS_PER_SAMPLE
};
}