I am working on WebRTC. My task is to record audio and video before call connect. I have recorded only video using VideoFileRenderer class. How can I record audio and mux with video using MediaMuxer?
This is a VideoFileRender class which I am using for recording and muxing.
package org.webrtc;
import android.media.AudioFormat;
import android.media.AudioRecord;
import android.media.MediaCodec;
import android.media.MediaCodecInfo;
import android.media.MediaFormat;
import android.media.MediaMuxer;
import android.media.MediaRecorder;
import android.os.Handler;
import android.os.HandlerThread;
import android.util.Log;
import android.view.Surface;
import org.webrtc.audio.AudioDeviceModule;
import org.webrtc.audio.JavaAudioDeviceModule;
import org.webrtc.audio.JavaAudioDeviceModule.SamplesReadyCallback;
import java.io.IOException;
import java.nio.ByteBuffer;
public class VideoFileRender implements VideoSink {
private static final String TAG = "VideoFileRender";
private final HandlerThread renderThread;
private final Handler renderThreadHandler;
private final HandlerThread audioHandlerThread;
private final Handler audioThreadHandler;
private int outputFileWidth = -1;
private int outputFileHeight = -1;
private ByteBuffer[] encoderOutputBuffers;
private ByteBuffer[] audioInputBuffers;
private ByteBuffer[] audioOutputBuffers;
private EglBase eglBase;
private EglBase.Context sharedContext;
private VideoFrameDrawer frameDrawer;
// TODO: these ought to be configurable as well
private static final String MIME_TYPE = "video/avc"; // H.264 Advanced Video Coding
private static final int FRAME_RATE = 30; // 30fps
private static final int FRAME_INTERVAL = 5; // 5 seconds between I-frames
private MediaMuxer mediaMuxer;
private MediaCodec encoder;
private MediaCodec.BufferInfo bufferInfo, audioBufferInfo;
private int trackIndex = -1;
private int audioTrackIndex;
private boolean isRunning = true;
private GlRectDrawer drawer;
private Surface surface;
private MediaCodec audioEncoder;
private AudioThread audioThread;
// private AudioThread audioThread;
private static final int SAMPLE_RATE = 44100; // 44.1[KHz] is only setting guaranteed to be available on all devices.
private static final int BIT_RATE = 64000;
public static final int SAMPLES_PER_FRAME = 1024; // AAC, bytes/frame/channel
public static final int FRAMES_PER_BUFFER = 25; // AAC, frame/buffer/sec
public VideoFileRender(String outputFile, final EglBase.Context sharedContext, boolean withAudio) throws IOException {
renderThread = new HandlerThread(TAG + "RenderThread");
renderThread.start();
renderThreadHandler = new Handler(renderThread.getLooper());
// if (withAudio) {
audioHandlerThread = new HandlerThread(TAG + "AudioThread");
audioHandlerThread.start();
audioThreadHandler = new Handler(audioHandlerThread.getLooper());
/*} else {
audioThread = null;
audioThreadHandler = null;
}*/
bufferInfo = new MediaCodec.BufferInfo();
this.sharedContext = sharedContext;
// Create a MediaMuxer. We can't add the video track and start() the muxer here,
// because our MediaFormat doesn't have the Magic Goodies. These can only be
// obtained from the encoder after it has started processing data.
mediaMuxer = new MediaMuxer(outputFile,
MediaMuxer.OutputFormat.MUXER_OUTPUT_MPEG_4);
audioTrackIndex = withAudio ? -1 : 0;
audioThread = new AudioThread();
}
private void initVideoEncoder() {
MediaFormat format = MediaFormat.createVideoFormat(MIME_TYPE, outputFileWidth, outputFileHeight);
// Set some properties. Failing to specify some of these can cause the MediaCodec
// configure() call to throw an unhelpful exception.
format.setInteger(MediaFormat.KEY_COLOR_FORMAT,
MediaCodecInfo.CodecCapabilities.COLOR_FormatSurface);
format.setInteger(MediaFormat.KEY_BIT_RATE, 6000000);
format.setInteger(MediaFormat.KEY_FRAME_RATE, FRAME_RATE);
format.setInteger(MediaFormat.KEY_I_FRAME_INTERVAL, FRAME_INTERVAL);
// Create a MediaCodec encoder and configure it with our format. Get a Surface
// we can use for input and wrap it with a class that handles the EGL work.
try {
encoder = MediaCodec.createEncoderByType(MIME_TYPE);
encoder.configure(format, null, null, MediaCodec.CONFIGURE_FLAG_ENCODE);
renderThreadHandler.post(() -> {
eglBase = EglBase.create(sharedContext, EglBase.CONFIG_RECORDABLE);
surface = encoder.createInputSurface();
eglBase.createSurface(surface);
eglBase.makeCurrent();
drawer = new GlRectDrawer();
});
} catch (Exception e) {
Log.wtf(TAG, e);
}
audioThread.start();
}
@Override
public void onFrame(VideoFrame frame) {
frame.retain();
if (outputFileWidth == -1) {
outputFileWidth = frame.getRotatedWidth();
outputFileHeight = frame.getRotatedHeight();
Log.d(TAG, "onFrame: " + outputFileWidth + " " + outputFileHeight);
initVideoEncoder();
}
renderThreadHandler.post(() -> renderFrameOnRenderThread(frame));
}
private void renderFrameOnRenderThread(VideoFrame frame) {
if (frameDrawer == null) {
frameDrawer = new VideoFrameDrawer();
}
frameDrawer.drawFrame(frame, drawer, null, 0, 0, outputFileWidth, outputFileHeight);
frame.release();
drainEncoder();
eglBase.swapBuffers();
}
/**
* Release all resources. All already posted frames will be rendered first.
*/
public void release() {
isRunning = false;
if (audioThreadHandler != null)
audioThreadHandler.post(() -> {
if (audioEncoder != null) {
audioEncoder.stop();
audioEncoder.release();
}
audioHandlerThread.quit();
audioThread = null;
});
renderThreadHandler.post(() -> {
muxerStarted = false;
if (encoder != null) {
encoder.stop();
encoder.release();
}
eglBase.release();
mediaMuxer.stop();
mediaMuxer.release();
renderThread.quit();
});
}
private boolean encoderStarted = false;
private volatile boolean muxerStarted = false;
private long videoFrameStart = 0;
private void drainEncoder() {
if (!encoderStarted) {
encoder.start();
encoderOutputBuffers = encoder.getOutputBuffers();
encoderStarted = true;
return;
}
while (true) {
int encoderStatus = encoder.dequeueOutputBuffer(bufferInfo, 10000);
if (encoderStatus == MediaCodec.INFO_TRY_AGAIN_LATER) {
break;
} else if (encoderStatus == MediaCodec.INFO_OUTPUT_BUFFERS_CHANGED) {
// not expected for an encoder
encoderOutputBuffers = encoder.getOutputBuffers();
Log.e(TAG, "encoder output buffers changed");
} else if (encoderStatus == MediaCodec.INFO_OUTPUT_FORMAT_CHANGED) {
// not expected for an encoder
MediaFormat newFormat = encoder.getOutputFormat();
Log.e(TAG, "encoder output format changed: " + newFormat);
trackIndex = mediaMuxer.addTrack(newFormat);
if (trackIndex != -1 && !muxerStarted) {
mediaMuxer.start();
muxerStarted = true;
}
if (!muxerStarted)
break;
} else if (encoderStatus < 0) {
Log.e(TAG, "unexpected result from encoder.dequeueOutputBuffer: " + encoderStatus);
} else { // encoderStatus >= 0
try {
ByteBuffer encodedData = encoderOutputBuffers[encoderStatus];
if (encodedData == null) {
Log.e(TAG, "encoderOutputBuffer " + encoderStatus + " was null");
break;
}
// It's usually necessary to adjust the ByteBuffer values to match BufferInfo.
encodedData.position(bufferInfo.offset);
encodedData.limit(bufferInfo.offset + bufferInfo.size);
if (videoFrameStart == 0 && bufferInfo.presentationTimeUs != 0) {
videoFrameStart = bufferInfo.presentationTimeUs;
}
bufferInfo.presentationTimeUs -= videoFrameStart;
if (muxerStarted)
mediaMuxer.writeSampleData(trackIndex, encodedData, bufferInfo);
isRunning = isRunning && (bufferInfo.flags & MediaCodec.BUFFER_FLAG_END_OF_STREAM) == 0;
encoder.releaseOutputBuffer(encoderStatus, false);
if ((bufferInfo.flags & MediaCodec.BUFFER_FLAG_END_OF_STREAM) != 0) {
break;
}
} catch (Exception e) {
Log.wtf(TAG, e);
break;
}
}
}
}
private long presTime = 0L;
private class AudioThread extends Thread {
@Override
public void run() {
if (audioEncoder == null) {
try {
final MediaFormat audioFormat = MediaFormat.createAudioFormat(MIME_TYPE, SAMPLE_RATE, 1);
audioFormat.setInteger(MediaFormat.KEY_AAC_PROFILE, MediaCodecInfo.CodecProfileLevel.AACObjectLC);
audioFormat.setInteger(MediaFormat.KEY_CHANNEL_MASK, AudioFormat.CHANNEL_IN_MONO);
audioFormat.setInteger(MediaFormat.KEY_BIT_RATE, BIT_RATE);
audioFormat.setInteger(MediaFormat.KEY_CHANNEL_COUNT, 1);
audioEncoder = MediaCodec.createEncoderByType(MIME_TYPE);
audioEncoder.configure(audioFormat, null, null, MediaCodec.CONFIGURE_FLAG_ENCODE);
audioEncoder.start();
audioInputBuffers = audioEncoder.getInputBuffers();
audioOutputBuffers = audioEncoder.getOutputBuffers();
} catch (Exception e) {
e.printStackTrace();
}
}
android.os.Process.setThreadPriority(android.os.Process.THREAD_PRIORITY_URGENT_AUDIO);
try {
final int min_buffer_size = AudioRecord.getMinBufferSize(
SAMPLE_RATE, AudioFormat.CHANNEL_IN_MONO,
AudioFormat.ENCODING_PCM_16BIT);
int buffer_size = SAMPLES_PER_FRAME * FRAMES_PER_BUFFER;
if (buffer_size < min_buffer_size)
buffer_size = ((min_buffer_size / SAMPLES_PER_FRAME) + 1) * SAMPLES_PER_FRAME * 2;
AudioRecord audioRecord = new AudioRecord(
MediaRecorder.AudioSource.MIC, SAMPLE_RATE,
AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT, buffer_size);
if (audioRecord.getState() != AudioRecord.STATE_INITIALIZED)
audioRecord = null;
if (audioRecord != null) {
final ByteBuffer buf = ByteBuffer.allocateDirect(SAMPLES_PER_FRAME);
int readBytes;
audioRecord.startRecording();
for (; isRunning; ) {
// read audio data from internal mic
buf.clear();
readBytes = audioRecord.read(buf, SAMPLES_PER_FRAME);
if (readBytes > 0) {
// set audio data to encoder
buf.position(readBytes);
buf.flip();
encode(buf, readBytes, getPTSUs());
}
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
}
private void encode(ByteBuffer buffer, int length, long presentationTimeUs) {
final ByteBuffer[] inputBuffers = audioEncoder.getInputBuffers();
final int inputBufferIndex = audioEncoder.dequeueInputBuffer(10000);
if (inputBufferIndex >= 0) {
final ByteBuffer inputBuffer = inputBuffers[inputBufferIndex];
inputBuffer.clear();
if (buffer != null) {
inputBuffer.put(buffer);
}
// if (DEBUG) Log.v(TAG, "encode:queueInputBuffer");
if (length <= 0) {
audioEncoder.queueInputBuffer(inputBufferIndex, 0, 0,
presentationTimeUs, MediaCodec.BUFFER_FLAG_END_OF_STREAM);
} else {
audioEncoder.queueInputBuffer(inputBufferIndex, 0, length,
presentationTimeUs, 0);
}
} else if (inputBufferIndex == MediaCodec.INFO_TRY_AGAIN_LATER) {
// wait for MediaCodec encoder is ready to encode
// nothing to do here because MediaCodec#dequeueInputBuffer(TIMEOUT_USEC)
// will wait for maximum TIMEOUT_USEC(10msec) on each call
}
}
private long prevOutputPTSUs = 0;
protected long getPTSUs() {
long result = System.nanoTime() / 1000L;
if (result < prevOutputPTSUs)
result = (prevOutputPTSUs - result) + result;
return result;
}
}
I expect using scenario mp4 file will be created with audio and video, but it creates an mp4 file with only video.