网络音频 API 播放时通过 http 流式传输音频标签输出

Web Audio API stream audio tags output via http as they are played

我正在开发一个 Electron 应用程序,它通过 Telegram Bot Api 接口接收 song/voice 请求,并以 jukebox/radio 方式在音频对象中播放它们。

我想要实现的是通过 http 将我的应用程序的音频输出实时流式传输到连接到本地 (nodejs) 服务器的客户端。

所以基本上我需要在播放时处理所有音频标签 PCM,然后将它们混合(也许将结果转换为 mp3 格式?)并将结果通过管道传输给客户端。至少这是我目前的想法。

不幸的是,我一直停留在捕获音频对象输出上。 我了解了 RecordJs 以及它如何从 AudioNode 对象录制音频,但我还没有找到混合多个音频标签传出流的示例。

你能帮我解决这个问题吗?

当网络音频 API 呈现时,音频是原始 PCM(未压缩),它在内存缓冲区中可用,根据缓冲区分配的大小获得 emptied/reloaded - 您可以拦截并复制此缓冲区进入下游发布给客户的流程

将以下代码保存为 html 文件,然后在同一目录中使用

提供它
python -m SimpleHTTPServer

将浏览器指向 http://localhost:8000/ 并选择你的新 html 文件......浏览器必须提示确认使用麦克风......然后查看你的 javascript 控制台(ctrl-shift-i)......在这里你看到第一个三个FFT 和时域音频数组缓冲区的元素...在

上的代码搜索中

array_time_domain

这是您的原始 PCM 音频(将被复制并发送给订阅的客户端(留作 reader 的练习 ;-))...如果不需要降低 FFT 相关代码,请注释掉CPU/battery 流失

注意 - onaudioprocess 回调会随着音频的传输而重复调用,因此请确保您上面提到的复制过程非常高效,因此它比音频缓冲区刷新之间的循环周期更快地完成(提示 Web Worker)

这里我使用来自麦克风的输入源音频。无论源音频如何,此内部回调渲染事件循环都是相同的

<html><head><meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1">
<title>capture microphone then show time & frequency domain output</title>

<script type="text/javascript">

var webaudio_tooling_obj = function () {

    var audioContext = new AudioContext();

    console.log("audio is starting up ...");

    var BUFF_SIZE_RENDERER = 16384;
    var SIZE_SHOW = 3; // number of array elements to show in console output

    var audioInput = null,
    microphone_stream = null,
    gain_node = null,
    script_processor_node = null,
    script_processor_analysis_node = null,
    analyser_node = 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;

        console.log("__________ " + label);

        if (label === "time") {

            for (; index < num_row_to_display && index < size_buffer; index += 1) {

                var curr_value_time = (given_typed_array[index] / 128) - 1.0;

                console.log(curr_value_time);
            }

        } else if (label === "frequency") {

            for (; index < num_row_to_display && index < size_buffer; index += 1) {

                console.log(given_typed_array[index]);
            }

        } else {

            throw new Error("ERROR - must pass time or frequency");
        }
    }

    function process_microphone_buffer(event) {

        var i, N, inp, microphone_output_buffer;

        microphone_output_buffer = event.inputBuffer.getChannelData(0); // just mono - 1 channel for now
    }

    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_RENDERER, 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_analysis_node = audioContext.createScriptProcessor(2048, 1, 1);
        script_processor_analysis_node.connect(gain_node);

        analyser_node = audioContext.createAnalyser();
        analyser_node.smoothingTimeConstant = 0;
        analyser_node.fftSize = 2048;

        microphone_stream.connect(analyser_node);

        analyser_node.connect(script_processor_analysis_node);

        var buffer_length = analyser_node.frequencyBinCount;

        var array_freq_domain = new Uint8Array(buffer_length);
        var array_time_domain = new Uint8Array(buffer_length);

        console.log("buffer_length " + buffer_length);

        script_processor_analysis_node.onaudioprocess = function() {

            // get the average for the first channel
            analyser_node.getByteFrequencyData(array_freq_domain);
            analyser_node.getByteTimeDomainData(array_time_domain);

            // draw the spectrogram
            if (microphone_stream.playbackState == microphone_stream.PLAYING_STATE) {

                show_some_data(array_freq_domain, SIZE_SHOW, "frequency");
                show_some_data(array_time_domain, SIZE_SHOW, "time"); // store this to record to aggregate buffer/file
            }
        };
    }

}(); //  webaudio_tooling_obj = function()

</script>

</head>
<body>

    <p>Volume</p>
    <input id="volume" type="range" min="0" max="1" step="0.1" value="0.0"/>

</body>
</html>