Recherche avancée

Sur d’autres sites (13308)

• ADD Image overlay to ffmpeg video stream

  1er juillet 2017, par Chris

  I am new to ffmpeg and want to add an HUD to the video stream, so a few questions.

  1. What file do I need to edit.
  2. What do I need to do to achieve this.

  Thanks in advance. Also I am VERY new to all of this, I will need instructions step by step

  I saw other questions saying to add this : ffmpeg -n -i video.mp4 -i logo.png -filter_complex "[0:v]setsar=sar=1[v];[v][1]blend=all_mode='overlay':all_opacity=0.7" -movflags +faststart tmb/video.mp4

  But I dont know where to put it, i entered it in the terminal and got this :

  pi@raspberrypi:~ $ ffmpeg -n -i video.mp4 -i logo.png -filter_complex "[0:v]setsar=sar=1[v];[v][1]blend=all_mode='overlay':all_opacity=0.7" -movflags +faststart tmb/video.mp4
  
  ffmpeg version N-86215-gb5228e4 Copyright (c) 2000-2017 the FFmpeg developers
  
    built with gcc 4.9.2 (Raspbian 4.9.2-10)
  
    configuration: --arch=armel --target-os=linux --enable-gpl --enable-libx264 --enable-nonfree --extra-libs=-ldl
  
    libavutil      55. 63.100 / 55. 63.100
  
    libavcodec     57. 96.101 / 57. 96.101
  
    libavformat    57. 72.101 / 57. 72.101
  
    libavdevice    57.  7.100 / 57.  7.100
  
    libavfilter     6. 90.100 /  6. 90.100
  
    libswscale      4.  7.101 /  4.  7.101
  
    libswresample   2.  8.100 /  2.  8.100
  
    libpostproc    54.  6.100 / 54.  6.100
  
  video.mp4: No such file or directory

  I dont understand what i am supposed to do with the video.mp4 ?

  HERE IS THE SCRIPT THAT SENDS THE VIDEO.

  import subprocess
  
  import shlex
  
  import re
  
  import os
  
  import time
  
  import urllib2
  
  import platform
  
  import json
  
  import sys
  
  import base64
  
  import random
  
  
  
  
  
  import argparse
  
  
  
  parser = argparse.ArgumentParser(description='robot control')
  
  parser.add_argument('camera_id')
  
  parser.add_argument('video_device_number', default=0, type=int)
  
  parser.add_argument('--kbps', default=450, type=int)
  
  parser.add_argument('--brightness', default=75, type=int, help='camera brightness')
  
  parser.add_argument('--contrast', default=75, type=int, help='camera contrast')
  
  parser.add_argument('--saturation', default=15, type=int, help='camera saturation')
  
  parser.add_argument('--rotate180', default=False, type=bool, help='rotate image 180 degrees')
  
  parser.add_argument('--env', default="prod")
  
  
  
  
  
  
  
  args = parser.parse_args()
  
  
  
  
  
  
  
  server = "runmyrobot.com"
  
  #server = "52.52.213.92"
  
  
  
  
  
  from socketIO_client import SocketIO, LoggingNamespace
  
  
  
  # enable raspicam driver in case a raspicam is being used
  
  os.system("sudo modprobe bcm2835-v4l2")
  
  
  
  
  
  if args.env == "dev":
  
      print "using dev port 8122"
  
      port = 8122
  
  elif args.env == "prod":
  
      print "using prod port 8022"
  
      port = 8022
  
  else:
  
      print "invalid environment"
  
      sys.exit(0)
  
  
  
  
  
  print "initializing socket io"
  
  print "server:", server
  
  print "port:", port
  
  socketIO = SocketIO(server, port, LoggingNamespace)
  
  print "finished initializing socket io"
  
  
  
  #ffmpeg -f qtkit -i 0 -f mpeg1video -b 400k -r 30 -s 320x240 http://52.8.81.124:8082/hello/320/240/
  
  
  
  
  
  def onHandleCameraCommand(*args):
  
      #thread.start_new_thread(handle_command, args)
  
      print args
  
  
  
  
  
  socketIO.on('command_to_camera', onHandleCameraCommand)
  
  
  
  
  
  def onHandleTakeSnapshotCommand(*args):
  
      print "taking snapshot"
  
      inputDeviceID = streamProcessDict['device_answer']
  
      snapShot(platform.system(), inputDeviceID)
  
      with open ("snapshot.jpg", 'rb') as f:
  
          data = f.read()
  
      print "emit"
  
  
  
      socketIO.emit('snapshot', {'image':base64.b64encode(data)})
  
  
  
  socketIO.on('take_snapshot_command', onHandleTakeSnapshotCommand)
  
  
  
  
  
  def randomSleep():
  
      """A short wait is good for quick recovery, but sometimes a longer delay is needed or it will just keep trying and failing short intervals, like because the system thinks the port is still in use and every retry makes the system think it's still in use. So, this has a high likelihood of picking a short interval, but will pick a long one sometimes."""
  
  
  
      timeToWait = random.choice((0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 5))
  
      print "sleeping", timeToWait
  
      time.sleep(timeToWait)
  
  
  
  
  
  
  
  def getVideoPort():
  
  
  
  
  
      url = 'http://%s/get_video_port/%s' % (server, cameraIDAnswer)
  
  
  
  
  
      for retryNumber in range(2000):
  
          try:
  
              print "GET", url
  
              response = urllib2.urlopen(url).read()
  
              break
  
          except:
  
              print "could not open url ", url
  
              time.sleep(2)
  
  
  
      return json.loads(response)['mpeg_stream_port']
  
  
  
  def getAudioPort():
  
  
  
  
  
      url = 'http://%s/get_audio_port/%s' % (server, cameraIDAnswer)
  
  
  
  
  
      for retryNumber in range(2000):
  
          try:
  
              print "GET", url
  
              response = urllib2.urlopen(url).read()
  
              break
  
          except:
  
              print "could not open url ", url
  
              time.sleep(2)
  
  
  
      return json.loads(response)['audio_stream_port']
  
  
  
  
  
  
  
  def runFfmpeg(commandLine):
  
  
  
      print commandLine
  
      ffmpegProcess = subprocess.Popen(shlex.split(commandLine))
  
      print "command started"
  
  
  
      return ffmpegProcess
  
  
  
  
  
  
  
  def handleDarwin(deviceNumber, videoPort, audioPort):
  
  
  
  
  
      p = subprocess.Popen(["ffmpeg", "-list_devices", "true", "-f", "qtkit", "-i", "dummy"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  
  
  
      out, err = p.communicate()
  
  
  
      print err
  
  
  
      deviceAnswer = raw_input("Enter the number of the camera device for your robot from the list above: ")
  
      commandLine = 'ffmpeg -f qtkit -i %s -f mpeg1video -b 400k -r 30 -s 320x240 http://%s:%s/hello/320/240/' % (deviceAnswer, server, videoPort)
  
  
  
      process = runFfmpeg(commandLine)
  
  
  
      return {'process': process, 'device_answer': deviceAnswer}
  
  
  
  
  
  def handleLinux(deviceNumber, videoPort, audioPort):
  
  
  
      print "sleeping to give the camera time to start working"
  
      randomSleep()
  
      print "finished sleeping"
  
  
  
  
  
      #p = subprocess.Popen(["ffmpeg", "-list_devices", "true", "-f", "qtkit", "-i", "dummy"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  
      #out, err = p.communicate()
  
      #print err
  
  
  
  
  
      os.system("v4l2-ctl -c brightness={brightness} -c contrast={contrast} -c saturation={saturation}".format(brightness=args.brightness,
  
                                                                                                               contrast=args.contrast,
  
                                                                                                               saturation=args.saturation))
  
  
  
  
  
      if deviceNumber is None:
  
          deviceAnswer = raw_input("Enter the number of the camera device for your robot: ")
  
      else:
  
          deviceAnswer = str(deviceNumber)
  
  
  
  
  
      #commandLine = '/usr/local/bin/ffmpeg -s 320x240 -f video4linux2 -i /dev/video%s -f mpeg1video -b 1k -r 20 http://runmyrobot.com:%s/hello/320/240/' % (deviceAnswer, videoPort)
  
      #commandLine = '/usr/local/bin/ffmpeg -s 640x480 -f video4linux2 -i /dev/video%s -f mpeg1video -b 150k -r 20 http://%s:%s/hello/640/480/' % (deviceAnswer, server, videoPort)
  
      # For new JSMpeg
  
      #commandLine = '/usr/local/bin/ffmpeg -f v4l2 -framerate 25 -video_size 640x480 -i /dev/video%s -f mpegts -codec:v mpeg1video -s 640x480 -b:v 250k -bf 0 http://%s:%s/hello/640/480/' % (deviceAnswer, server, videoPort) # ClawDaddy
  
      #commandLine = '/usr/local/bin/ffmpeg -s 1280x720 -f video4linux2 -i /dev/video%s -f mpeg1video -b 1k -r 20 http://runmyrobot.com:%s/hello/1280/720/' % (deviceAnswer, videoPort)
  
  
  
  
  
      if args.rotate180:
  
          rotationOption = "-vf transpose=2,transpose=2"
  
      else:
  
          rotationOption = ""
  
  
  
      # video with audio
  
      videoCommandLine = '/usr/local/bin/ffmpeg -f v4l2 -framerate 25 -video_size 640x480 -i /dev/video%s %s -f mpegts -codec:v mpeg1video -s 640x480 -b:v %dk -bf 0 -muxdelay 0.001 http://%s:%s/hello/640/480/' % (deviceAnswer, rotationOption, args.kbps, server, videoPort)
  
      audioCommandLine = '/usr/local/bin/ffmpeg -f alsa -ar 44100 -ac 1 -i hw:1 -f mpegts -codec:a mp2 -b:a 32k -muxdelay 0.001 http://%s:%s/hello/640/480/' % (server, audioPort)
  
  
  
  
  
      print videoCommandLine
  
      print audioCommandLine
  
  
  
      videoProcess = runFfmpeg(videoCommandLine)
  
      audioProcess = runFfmpeg(audioCommandLine)
  
  
  
      return {'video_process': videoProcess, 'audioProcess': audioProcess, 'device_answer': deviceAnswer}
  
  
  
  
  
  
  
  def handleWindows(deviceNumber, videoPort):
  
  
  
      p = subprocess.Popen(["ffmpeg", "-list_devices", "true", "-f", "dshow", "-i", "dummy"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  
  
  
  
  
      out, err = p.communicate() 
  
      lines = err.split('\n')
  
  
  
      count = 0
  
  
  
      devices = []
  
  
  
      for line in lines:
  
  
  
          #if "]  \"" in line:
  
          #    print "line:", line
  
  
  
          m = re.search('.*\\"(.*)\\"', line)
  
          if m != None:
  
              #print line
  
              if m.group(1)[0:1] != '@':
  
                  print count, m.group(1)
  
                  devices.append(m.group(1))
  
                  count += 1
  
  
  
  
  
      if deviceNumber is None:
  
          deviceAnswer = raw_input("Enter the number of the camera device for your robot from the list above: ")
  
      else:
  
          deviceAnswer = str(deviceNumber)
  
  
  
      device = devices[int(deviceAnswer)]
  
      commandLine = 'ffmpeg -s 640x480 -f dshow -i video="%s" -f mpegts -codec:v mpeg1video -b 200k -r 20 http://%s:%s/hello/640/480/' % (device, server, videoPort)
  
  
  
  
  
      process = runFfmpeg(commandLine)
  
  
  
      return {'process': process, 'device_answer': device}
  
  
  
  
  
  
  
  def handleWindowsScreenCapture(deviceNumber, videoPort):
  
  
  
      p = subprocess.Popen(["ffmpeg", "-list_devices", "true", "-f", "dshow", "-i", "dummy"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  
  
  
  
  
      out, err = p.communicate()
  
  
  
      lines = err.split('\n')
  
  
  
      count = 0
  
  
  
      devices = []
  
  
  
      for line in lines:
  
  
  
          #if "]  \"" in line:
  
          #    print "line:", line
  
  
  
          m = re.search('.*\\"(.*)\\"', line)
  
          if m != None:
  
              #print line
  
              if m.group(1)[0:1] != '@':
  
                  print count, m.group(1)
  
                  devices.append(m.group(1))
  
                  count += 1
  
  
  
  
  
      if deviceNumber is None:
  
          deviceAnswer = raw_input("Enter the number of the camera device for your robot from the list above: ")
  
      else:
  
          deviceAnswer = str(deviceNumber)
  
  
  
  
  
  
  
      device = devices[int(deviceAnswer)]
  
      commandLine = 'ffmpeg -f dshow -i video="screen-capture-recorder" -vf "scale=640:480" -f mpeg1video -b 50k -r 20 http://%s:%s/hello/640/480/' % (server, videoPort)
  
  
  
      print "command line:", commandLine
  
  
  
      process = runFfmpeg(commandLine)
  
  
  
      return {'process': process, 'device_answer': device}
  
  
  
  
  
  
  
  
  
  def snapShot(operatingSystem, inputDeviceID, filename="snapshot.jpg"):    
  
  
  
      try:
  
          os.remove('snapshot.jpg')
  
      except:
  
          print "did not remove file"
  
  
  
      commandLineDict = {
  
          'Darwin': 'ffmpeg -y -f qtkit -i %s -vframes 1 %s' % (inputDeviceID, filename),
  
          'Linux': '/usr/local/bin/ffmpeg -y -f video4linux2 -i /dev/video%s -vframes 1 -q:v 1000 -vf scale=320:240 %s' % (inputDeviceID, filename),
  
          'Windows': 'ffmpeg -y -s 320x240 -f dshow -i video="%s" -vframes 1 %s' % (inputDeviceID, filename)}
  
  
  
      print commandLineDict[operatingSystem]
  
      os.system(commandLineDict[operatingSystem])
  
  
  
  
  
  
  
  def startVideoCapture():
  
  
  
      videoPort = getVideoPort()
  
      audioPort = getAudioPort()
  
      print "video port:", videoPort
  
      print "audio port:", audioPort
  
  
  
      #if len(sys.argv) >= 3:
  
      #    deviceNumber = sys.argv[2]
  
      #else:
  
      #    deviceNumber = None
  
      deviceNumber = args.video_device_number
  
  
  
      result = None
  
      if platform.system() == 'Darwin':
  
          result = handleDarwin(deviceNumber, videoPort, audioPort)
  
      elif platform.system() == 'Linux':
  
          result = handleLinux(deviceNumber, videoPort, audioPort)
  
      elif platform.system() == 'Windows':
  
          #result = handleWindowsScreenCapture(deviceNumber, videoPort)
  
          result = handleWindows(deviceNumber, videoPort, audioPort)
  
      else:
  
          print "unknown platform", platform.system()
  
  
  
      return result
  
  
  
  
  
  def timeInMilliseconds():
  
      return int(round(time.time() * 1000))
  
  
  
  
  
  
  
  def main():
  
  
  
      print "main"
  
  
  
      streamProcessDict = None
  
  
  
  
  
      twitterSnapCount = 0
  
  
  
      while True:
  
  
  
  
  
  
  
          socketIO.emit('send_video_status', {'send_video_process_exists': True,
  
                                              'camera_id':cameraIDAnswer})
  
  
  
  
  
          if streamProcessDict is not None:
  
              print "stopping previously running ffmpeg (needs to happen if this is not the first iteration)"
  
              streamProcessDict['process'].kill()
  
  
  
          print "starting process just to get device result" # this should be a separate function so you don't have to do this
  
          streamProcessDict = startVideoCapture()
  
          inputDeviceID = streamProcessDict['device_answer']
  
          print "stopping video capture"
  
          streamProcessDict['process'].kill()
  
  
  
          #print "sleeping"
  
          #time.sleep(3)
  
          #frameCount = int(round(time.time() * 1000))
  
  
  
          videoWithSnapshots = False
  
          while videoWithSnapshots:
  
  
  
              frameCount = timeInMilliseconds()
  
  
  
              print "taking single frame image"
  
              snapShot(platform.system(), inputDeviceID, filename="single_frame_image.jpg")
  
  
  
              with open ("single_frame_image.jpg", 'rb') as f:
  
  
  
                  # every so many frames, post a snapshot to twitter
  
                  #if frameCount % 450 == 0:
  
                  if frameCount % 6000 == 0:
  
                          data = f.read()
  
                          print "emit"
  
                          socketIO.emit('snapshot', {'frame_count':frameCount, 'image':base64.b64encode(data)})
  
                  data = f.read()
  
  
  
              print "emit"
  
              socketIO.emit('single_frame_image', {'frame_count':frameCount, 'image':base64.b64encode(data)})
  
              time.sleep(0)
  
  
  
              #frameCount += 1
  
  
  
  
  
          if False:
  
           if platform.system() != 'Windows':
  
              print "taking snapshot"
  
              snapShot(platform.system(), inputDeviceID)
  
              with open ("snapshot.jpg", 'rb') as f:
  
                  data = f.read()
  
              print "emit"
  
  
  
              # skip sending the first image because it's mostly black, maybe completely black
  
              #todo: should find out why this black image happens
  
              if twitterSnapCount > 0:
  
                  socketIO.emit('snapshot', {'image':base64.b64encode(data)})
  
  
  
  
  
  
  
  
  
          print "starting video capture"
  
          streamProcessDict = startVideoCapture()
  
  
  
  
  
          # This loop counts out a delay that occurs between twitter snapshots.
  
          # Every 50 seconds, it kills and restarts ffmpeg.
  
          # Every 40 seconds, it sends a signal to the server indicating status of processes.
  
          period = 2*60*60 # period in seconds between snaps
  
          for count in range(period):
  
              time.sleep(1)
  
  
  
              if count % 20 == 0:
  
                  socketIO.emit('send_video_status', {'send_video_process_exists': True,
  
                                                      'camera_id':cameraIDAnswer})
  
  
  
              if count % 40 == 30:
  
                  print "stopping video capture just in case it has reached a state where it's looping forever, not sending video, and not dying as a process, which can happen"
  
                  streamProcessDict['video_process'].kill()
  
                  streamProcessDict['audio_process'].kill()
  
                  time.sleep(1)
  
  
  
              if count % 80 == 75:
  
                  print "send status about this process and its child process ffmpeg"
  
                  ffmpegProcessExists = streamProcessDict['process'].poll() is None
  
                  socketIO.emit('send_video_status', {'send_video_process_exists': True,
  
                                                      'ffmpeg_process_exists': ffmpegProcessExists,
  
                                                      'camera_id':cameraIDAnswer})
  
  
  
              #if count % 190 == 180:
  
              #    print "reboot system in case the webcam is not working"
  
              #    os.system("sudo reboot")
  
  
  
              # if the video stream process dies, restart it
  
              if streamProcessDict['video_process'].poll() is not None or streamProcessDict['audio_process'].poll():
  
                  # wait before trying to start ffmpeg
  
                  print "ffmpeg process is dead, waiting before trying to restart"
  
                  randomSleep()
  
                  streamProcessDict = startVideoCapture()
  
  
  
          twitterSnapCount += 1
  
  
  
  if __name__ == "__main__":
  
  
  
  
  
      #if len(sys.argv) > 1:
  
      #    cameraIDAnswer = sys.argv[1]
  
      #else:
  
      #    cameraIDAnswer = raw_input("Enter the Camera ID for your robot, you can get it by pointing a browser to the runmyrobot server %s: " % server)
  
  
  
      cameraIDAnswer = args.camera_id
  
  
  
  
  
      main()

  ERROR :

  ffmpeg -n -f mpegts -i http://54.183.232.63:12221 -i logo.png -filter_complex "[0:v]setsar=sar=1[v];[v][1]blend=all_mode='overlay':all_opacity=0.7" -movflags +faststart tmb/video.mp4
  
  ffmpeg version N-86215-gb5228e4 Copyright (c) 2000-2017 the FFmpeg developers
  
    built with gcc 4.9.2 (Raspbian 4.9.2-10)
  
    configuration: --arch=armel --target-os=linux --enable-gpl --enable-libx264 --enable-nonfree --extra-libs=-ldl
  
    libavutil      55. 63.100 / 55. 63.100
  
    libavcodec     57. 96.101 / 57. 96.101
  
    libavformat    57. 72.101 / 57. 72.101
  
    libavdevice    57.  7.100 / 57.  7.100
  
    libavfilter     6. 90.100 /  6. 90.100
  
    libswscale      4.  7.101 /  4.  7.101
  
    libswresample   2.  8.100 /  2.  8.100
  
    libpostproc    54.  6.100 / 54.  6.100
  
  [mpegts @ 0x1a57390] Could not detect TS packet size, defaulting to non-FEC/DVHS
  
  http://54.183.232.63:12221: could not find codec parameters

• FFmpeg : Parallel encoding with custom thread pool

  13 novembre 2017, par ZeroDefect

  One of the things I’m trying to achieve is parallel encoding via FFmpeg’s c API. This looks to work out of the box quite nicely ; however, I’ve changed the goal posts slightly :

  In an existing application, I already have a thread pool at hand. Instead of using another thread pool via FFmpeg, I would like reuse the existing thread pool in my application. Having studied the latest FFmpeg trunk docs, it very much looks possible.

  Using some FFmpeg sample code, I’ve created a sample application to demonstrate what I’m trying to achieve (see below). The sample app generates a video-only mpeg2 ts using the mp2v codec.

  The problem I’m experiencing is that the custom ’thread_execute’ or ’thread_execute2’ are never invoked. This is despite the fact that the codec appears to indicate that threading is supported. Please be aware that I have not yet plumbed in the thread pool just yet. My first goal is for it to call the custom function pointer.

  I’ve tried to get assistance on the FFmpeg mailing lists but to no avail.

  #include <iostream>
  
  #include <thread>
  
  #include 
  
  #include 
  
  #include 
  
  #include <cstring>
  
  #include <future>
  
  
  
  extern "C"
  
  {
  
  #include <libavutil></libavutil>avassert.h>
  
  #include <libavutil></libavutil>channel_layout.h>
  
  #include <libavutil></libavutil>opt.h>
  
  #include <libavutil></libavutil>timestamp.h>
  
  #include <libavformat></libavformat>avformat.h>
  
  //#include <libswscale></libswscale>swscale.h>
  
  #include <libswresample></libswresample>swresample.h>
  
  }
  
  
  
  #define STREAM_DURATION   1000.0
  
  #define STREAM_FRAME_RATE 25 /* 25 images/s */
  
  #define STREAM_PIX_FMT    AV_PIX_FMT_YUV420P /* default pix_fmt */
  
  
  
  #define SCALE_FLAGS SWS_BICUBIC
  
  
  
  // a wrapper around a single output AVStream
  
  typedef struct OutputStream {
  
      AVStream *st;
  
      AVCodecContext *enc;
  
  
  
      /* pts of the next frame that will be generated */
  
      int64_t next_pts;
  
      int samples_count;
  
  
  
      AVFrame *frame;
  
      AVFrame *tmp_frame;
  
  
  
      float t, tincr, tincr2;
  
  
  
      struct SwsContext *sws_ctx;
  
      struct SwrContext *swr_ctx;
  
  } OutputStream;
  
  
  
  /////////////////////////////////////////////////////////////////////////////
  
  //  The ffmpeg variation raises compiler warnings.
  
  char *cb_av_ts2str(char *buf, int64_t ts)
  
  {
  
      std::memset(buf,0,AV_TS_MAX_STRING_SIZE);
  
      return av_ts_make_string(buf,ts);
  
  }
  
  
  
  /////////////////////////////////////////////////////////////////////////////
  
  //  The ffmpeg variation raises compiler warnings.
  
  char *cb_av_ts2timestr(char *buf, int64_t ts, AVRational *tb)
  
  {
  
      std::memset(buf,0,sizeof(AV_TS_MAX_STRING_SIZE));
  
      return av_ts_make_time_string(buf,ts,tb);
  
  }
  
  
  
  /////////////////////////////////////////////////////////////////////////////
  
  //  The ffmpeg variation raises compiler warnings.
  
  char *cb_av_err2str(char *errbuf, size_t errbuf_size, int errnum)
  
  {
  
      std::memset(errbuf,0,errbuf_size);
  
      return av_make_error_string(errbuf,errbuf_size,errnum);
  
  }
  
  
  
  int thread_execute(AVCodecContext* s, int (*func)(AVCodecContext *c2, void *arg2), void* arg, int* ret, int count, int size)
  
  {
  
      // Do it all serially for now
  
      std::cout &lt;&lt; "thread_execute" &lt;&lt; std::endl;
  
  
  
      for (int k = 0; k &lt; count; ++k)
  
      {
  
          ret[k] = func(s, arg);
  
      }
  
  
  
      return 0;
  
  }
  
  
  
  int thread_execute2(AVCodecContext* s, int (*func)(AVCodecContext* c2, void* arg2, int, int), void* arg, int* ret, int count)
  
  {
  
      // Do it all serially for now
  
      std::cout &lt;&lt; "thread_execute2" &lt;&lt; std::endl;
  
  
  
      for (int k = 0; k &lt; count; ++k)
  
      {
  
          ret[k] = func(s, arg, k, count);
  
      }
  
  
  
      return 0;
  
  }
  
  
  
  
  
  static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt)
  
  {
  
      char s[AV_TS_MAX_STRING_SIZE];
  
  
  
      AVRational *time_base = &amp;fmt_ctx->streams[pkt->stream_index]->time_base;
  
  
  
      printf("pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
  
             cb_av_ts2str(s,pkt->pts), cb_av_ts2timestr(s,pkt->pts, time_base),
  
             cb_av_ts2str(s,pkt->dts), cb_av_ts2timestr(s,pkt->dts, time_base),
  
             cb_av_ts2str(s,pkt->duration), cb_av_ts2timestr(s,pkt->duration, time_base),
  
             pkt->stream_index);
  
  }
  
  
  
  static int write_frame(AVFormatContext *fmt_ctx, const AVRational *time_base, AVStream *st, AVPacket *pkt)
  
  {
  
      /* rescale output packet timestamp values from codec to stream timebase */
  
      av_packet_rescale_ts(pkt, *time_base, st->time_base);
  
      pkt->stream_index = st->index;
  
  
  
      /* Write the compressed frame to the media file. */
  
      log_packet(fmt_ctx, pkt);
  
      return av_interleaved_write_frame(fmt_ctx, pkt);
  
  }
  
  
  
  /* Add an output stream. */
  
  static void add_stream(OutputStream *ost, AVFormatContext *oc,
  
                         AVCodec **codec,
  
                         enum AVCodecID codec_id)
  
  {
  
      AVCodecContext *c;
  
      int i;
  
  
  
      /* find the encoder */
  
      *codec = avcodec_find_encoder(codec_id);
  
      if (!(*codec)) {
  
          fprintf(stderr, "Could not find encoder for '%s'\n",
  
                  avcodec_get_name(codec_id));
  
          exit(1);
  
      }
  
  
  
      ost->st = avformat_new_stream(oc, NULL);
  
      if (!ost->st) {
  
          fprintf(stderr, "Could not allocate stream\n");
  
          exit(1);
  
      }
  
      ost->st->id = oc->nb_streams-1;
  
      c = avcodec_alloc_context3(*codec);
  
      if (!c) {
  
          fprintf(stderr, "Could not alloc an encoding context\n");
  
          exit(1);
  
      }
  
      ost->enc = c;
  
  
  
      switch ((*codec)->type)
  
      {
  
          case AVMEDIA_TYPE_AUDIO:
  
              c->sample_fmt  = (*codec)->sample_fmts ?
  
                               (*codec)->sample_fmts[0] : AV_SAMPLE_FMT_FLTP;
  
              c->bit_rate    = 64000;
  
              c->sample_rate = 44100;
  
              if ((*codec)->supported_samplerates) {
  
                  c->sample_rate = (*codec)->supported_samplerates[0];
  
                  for (i = 0; (*codec)->supported_samplerates[i]; i++) {
  
                      if ((*codec)->supported_samplerates[i] == 44100)
  
                          c->sample_rate = 44100;
  
                  }
  
              }
  
              c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);
  
              c->channel_layout = AV_CH_LAYOUT_STEREO;
  
              if ((*codec)->channel_layouts) {
  
                  c->channel_layout = (*codec)->channel_layouts[0];
  
                  for (i = 0; (*codec)->channel_layouts[i]; i++) {
  
                      if ((*codec)->channel_layouts[i] == AV_CH_LAYOUT_STEREO)
  
                          c->channel_layout = AV_CH_LAYOUT_STEREO;
  
                  }
  
              }
  
              c->channels        = av_get_channel_layout_nb_channels(c->channel_layout);
  
              ost->st->time_base = (AVRational){ 1, c->sample_rate };
  
              break;
  
  
  
          case AVMEDIA_TYPE_VIDEO:
  
              c->codec_id = codec_id;
  
  
  
              c->bit_rate = 400000;
  
              /* Resolution must be a multiple of two. */
  
              c->width    = 352;
  
              c->height   = 288;
  
              /* timebase: This is the fundamental unit of time (in seconds) in terms
  
               * of which frame timestamps are represented. For fixed-fps content,
  
               * timebase should be 1/framerate and timestamp increments should be
  
               * identical to 1. */
  
              ost->st->time_base = (AVRational){ 1, STREAM_FRAME_RATE };
  
              c->time_base       = ost->st->time_base;
  
  
  
              c->gop_size      = 12; /* emit one intra frame every twelve frames at most */
  
              c->pix_fmt       = STREAM_PIX_FMT;
  
              if (c->codec_id == AV_CODEC_ID_MPEG2VIDEO) {
  
                  /* just for testing, we also add B-frames */
  
                  c->max_b_frames = 2;
  
              }
  
              if (c->codec_id == AV_CODEC_ID_MPEG1VIDEO) {
  
                  /* Needed to avoid using macroblocks in which some coeffs overflow.
  
                   * This does not happen with normal video, it just happens here as
  
                   * the motion of the chroma plane does not match the luma plane. */
  
                  c->mb_decision = 2;
  
              }
  
              break;
  
  
  
          default:
  
              break;
  
      }
  
  
  
      if (c->codec->capabilities &amp; AV_CODEC_CAP_FRAME_THREADS ||
  
          c->codec->capabilities &amp; AV_CODEC_CAP_SLICE_THREADS)
  
      {
  
          if (c->codec->capabilities &amp; AV_CODEC_CAP_FRAME_THREADS)
  
          {
  
              c->thread_type = FF_THREAD_FRAME;
  
          }
  
          if (c->codec->capabilities &amp; AV_CODEC_CAP_SLICE_THREADS)
  
          {
  
              c->thread_type = FF_THREAD_SLICE;
  
          }
  
  
  
          c->execute = &amp;thread_execute;
  
          c->execute2 = &amp;thread_execute2;
  
          c->thread_count = 4;
  
  
  
          // NOTE: Testing opaque.
  
          c->opaque = (void*)0xff;
  
      }
  
  
  
      /* Some formats want stream headers to be separate. */
  
      if (oc->oformat->flags &amp; AVFMT_GLOBALHEADER)
  
          c->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
  
  }
  
  
  
  /**************************************************************/
  
  /* video output */
  
  
  
  static AVFrame *alloc_picture(enum AVPixelFormat pix_fmt, int width, int height)
  
  {
  
      AVFrame *picture;
  
      int ret;
  
  
  
      picture = av_frame_alloc();
  
      if (!picture)
  
          return NULL;
  
  
  
      picture->format = pix_fmt;
  
      picture->width  = width;
  
      picture->height = height;
  
  
  
      /* allocate the buffers for the frame data */
  
      ret = av_frame_get_buffer(picture, 32);
  
      if (ret &lt; 0) {
  
          fprintf(stderr, "Could not allocate frame data.\n");
  
          exit(1);
  
      }
  
  
  
      return picture;
  
  }
  
  
  
  static void open_video(AVFormatContext *oc, AVCodec *codec, OutputStream *ost, AVDictionary *opt_arg)
  
  {
  
      int ret;
  
      AVCodecContext *c = ost->enc;
  
      //AVDictionary *opt = NULL;
  
  
  
      //av_dict_copy(&amp;opt, opt_arg, 0);
  
  
  
      /* open the codec */
  
      ret = avcodec_open2(c, codec, NULL);
  
      //av_dict_free(&amp;opt);
  
      if (ret &lt; 0) {
  
          char s[AV_ERROR_MAX_STRING_SIZE];
  
          fprintf(stderr, "Could not open video codec: %s\n", cb_av_err2str(s,AV_ERROR_MAX_STRING_SIZE,ret));
  
          exit(1);
  
      }
  
  
  
      /* allocate and init a re-usable frame */
  
      ost->frame = alloc_picture(c->pix_fmt, c->width, c->height);
  
      if (!ost->frame) {
  
          fprintf(stderr, "Could not allocate video frame\n");
  
          exit(1);
  
      }
  
  
  
      /* If the output format is not YUV420P, then a temporary YUV420P
  
       * picture is needed too. It is then converted to the required
  
       * output format. */
  
      ost->tmp_frame = NULL;
  
      if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
  
          ost->tmp_frame = alloc_picture(AV_PIX_FMT_YUV420P, c->width, c->height);
  
          if (!ost->tmp_frame) {
  
              fprintf(stderr, "Could not allocate temporary picture\n");
  
              exit(1);
  
          }
  
      }
  
  
  
      /* copy the stream parameters to the muxer */
  
      ret = avcodec_parameters_from_context(ost->st->codecpar, c);
  
      if (ret &lt; 0) {
  
          fprintf(stderr, "Could not copy the stream parameters\n");
  
          exit(1);
  
      }
  
  }
  
  
  
  /* Prepare a dummy image. */
  
  static void fill_yuv_image(AVFrame *pict, int frame_index,
  
                             int width, int height)
  
  {
  
      int x, y, i;
  
  
  
      i = frame_index;
  
  
  
      /* Y */
  
      for (y = 0; y &lt; height; y++)
  
          for (x = 0; x &lt; width; x++)
  
              pict->data[0][y * pict->linesize[0] + x] = x + y + i * 3;
  
  
  
      /* Cb and Cr */
  
      for (y = 0; y &lt; height / 2; y++) {
  
          for (x = 0; x &lt; width / 2; x++) {
  
              pict->data[1][y * pict->linesize[1] + x] = 128 + y + i * 2;
  
              pict->data[2][y * pict->linesize[2] + x] = 64 + x + i * 5;
  
          }
  
      }
  
  }
  
  
  
  static AVFrame *get_video_frame(OutputStream *ost)
  
  {
  
      AVCodecContext *c = ost->enc;
  
  
  
      /* check if we want to generate more frames */
  
      if (av_compare_ts(ost->next_pts, c->time_base,
  
                        STREAM_DURATION, (AVRational){ 1, 1 }) >= 0)
  
          return NULL;
  
  
  
      /* when we pass a frame to the encoder, it may keep a reference to it
  
       * internally; make sure we do not overwrite it here */
  
      if (av_frame_make_writable(ost->frame) &lt; 0)
  
          exit(1);
  
  
  
      if (c->pix_fmt != AV_PIX_FMT_YUV420P) {
  
          /* as we only generate a YUV420P picture, we must convert it
  
           * to the codec pixel format if needed */
  
          /*if (!ost->sws_ctx) {
  
              ost->sws_ctx = sws_getContext(c->width, c->height,
  
                                            AV_PIX_FMT_YUV420P,
  
                                            c->width, c->height,
  
                                            c->pix_fmt,
  
                                            SCALE_FLAGS, NULL, NULL, NULL);
  
              if (!ost->sws_ctx) {
  
                  fprintf(stderr,
  
                          "Could not initialize the conversion context\n");
  
                  exit(1);
  
              }
  
          }
  
          fill_yuv_image(ost->tmp_frame, ost->next_pts, c->width, c->height);
  
          sws_scale(ost->sws_ctx,
  
                    (const uint8_t * const *)ost->tmp_frame->data, ost->tmp_frame->linesize,
  
                    0, c->height, ost->frame->data, ost->frame->linesize);*/
  
      } else {
  
          fill_yuv_image(ost->frame, ost->next_pts, c->width, c->height);
  
      }
  
  
  
      ost->frame->pts = ost->next_pts++;
  
  
  
      return ost->frame;
  
  }
  
  
  
  /*
  
   * encode one video frame and send it to the muxer
  
   * return 1 when encoding is finished, 0 otherwise
  
   */
  
  static int write_video_frame(AVFormatContext *oc, OutputStream *ost)
  
  {
  
      int ret;
  
      AVCodecContext *c;
  
      AVFrame *frame;
  
      int got_packet = 0;
  
      AVPacket pkt = { 0 };
  
  
  
      c = ost->enc;
  
  
  
      frame = get_video_frame(ost);
  
  
  
      if (frame)
  
      {
  
          ret = avcodec_send_frame(ost->enc, frame);
  
          if (ret &lt; 0)
  
          {
  
              char s[AV_ERROR_MAX_STRING_SIZE];
  
              fprintf(stderr, "Error encoding video frame: %s\n", cb_av_err2str(s, AV_ERROR_MAX_STRING_SIZE, ret));
  
              exit(1);
  
          }
  
      }
  
  
  
      av_init_packet(&amp;pkt);
  
  
  
      ret = avcodec_receive_packet(ost->enc,&amp;pkt);
  
      if (ret &lt; 0)
  
      {
  
          if (ret == AVERROR(EAGAIN)) { ret = 0; }
  
          else
  
          {
  
              char s[AV_ERROR_MAX_STRING_SIZE];
  
              fprintf(stderr, "Error receiving packet: %s\n", cb_av_err2str(s,AV_ERROR_MAX_STRING_SIZE,ret));
  
              exit(1);
  
          }
  
      }
  
      else
  
      {
  
          got_packet = 1;
  
          ret = write_frame(oc, &amp;c->time_base, ost->st, &amp;pkt);
  
      }
  
  
  
      if (ret &lt; 0) {
  
          char s[AV_ERROR_MAX_STRING_SIZE];
  
          fprintf(stderr, "Error while writing video frame: %s\n", cb_av_err2str(s,AV_ERROR_MAX_STRING_SIZE,ret));
  
          exit(1);
  
      }
  
  
  
      return (frame || got_packet) ? 0 : 1;
  
  }
  
  
  
  static void close_stream(AVFormatContext *oc, OutputStream *ost)
  
  {
  
      avcodec_free_context(&amp;ost->enc);
  
      av_frame_free(&amp;ost->frame);
  
      av_frame_free(&amp;ost->tmp_frame);
  
      //sws_freeContext(ost->sws_ctx);
  
      //swr_free(&amp;ost->swr_ctx);
  
  }
  
  
  
  /**************************************************************/
  
  /* media file output */
  
  
  
  int main(int argc, char **argv)
  
  {
  
      OutputStream video_st = { 0 }, audio_st = { 0 };
  
      const char *filename;
  
      AVOutputFormat *fmt;
  
      AVFormatContext *oc;
  
      AVCodec /**audio_codec,*/ *video_codec;
  
      int ret;
  
      int have_video = 0, have_audio = 0;
  
      int encode_video = 0, encode_audio = 0;
  
      AVDictionary *opt = NULL;
  
      int i;
  
  
  
      /* Initialize libavcodec, and register all codecs and formats. */
  
      av_register_all();
  
      avformat_network_init();
  
  
  
      if (argc &lt; 2) {
  
          printf("usage: %s output_file\n"
  
                     "API example program to output a media file with libavformat.\n"
  
                     "This program generates a synthetic audio and video stream, encodes and\n"
  
                     "muxes them into a file named output_file.\n"
  
                     "The output format is automatically guessed according to the file extension.\n"
  
                     "Raw images can also be output by using '%%d' in the filename.\n"
  
                     "\n", argv[0]);
  
          return 1;
  
      }
  
  
  
      filename = argv[1];
  
      for (i = 2; i+1 &lt; argc; i+=2) {
  
          if (!strcmp(argv[i], "-flags") || !strcmp(argv[i], "-fflags"))
  
              av_dict_set(&amp;opt, argv[i]+1, argv[i+1], 0);
  
      }
  
  
  
      const char *pfilename = filename;
  
  
  
      /* allocate the output media context */
  
      avformat_alloc_output_context2(&amp;oc, NULL, "mpegts", pfilename);
  
      if (!oc) {
  
          printf("Could not deduce output format from file extension: using MPEG.\n");
  
          avformat_alloc_output_context2(&amp;oc, NULL, "mpeg", pfilename);
  
      }
  
      if (!oc)
  
          return 1;
  
  
  
      fmt = oc->oformat;
  
  
  
      /* Add the audio and video streams using the default format codecs
  
       * and initialize the codecs. */
  
      if (fmt->video_codec != AV_CODEC_ID_NONE) {
  
          add_stream(&amp;video_st, oc, &amp;video_codec, fmt->video_codec);
  
          have_video = 1;
  
          encode_video = 1;
  
      }
  
      /*if (fmt->audio_codec != AV_CODEC_ID_NONE) {
  
          add_stream(&amp;audio_st, oc, &amp;audio_codec, fmt->audio_codec);
  
          have_audio = 1;
  
          encode_audio = 1;
  
      }*/
  
  
  
      /* Now that all the parameters are set, we can open the audio and
  
       * video codecs and allocate the necessary encode buffers. */
  
      if (have_video)
  
          open_video(oc, video_codec, &amp;video_st, opt);
  
  
  
      //if (have_audio)
  
      //    open_audio(oc, audio_codec, &amp;audio_st, opt);
  
  
  
      av_dump_format(oc, 0, pfilename, 1);
  
  
  
      /* open the output file, if needed */
  
      if (!(fmt->flags &amp; AVFMT_NOFILE)) {
  
          ret = avio_open(&amp;oc->pb, pfilename, AVIO_FLAG_WRITE);
  
          if (ret &lt; 0) {
  
              char s[AV_ERROR_MAX_STRING_SIZE];
  
              fprintf(stderr, "Could not open '%s': %s\n", pfilename,
  
                      cb_av_err2str(s,AV_ERROR_MAX_STRING_SIZE,ret));
  
              return 1;
  
          }
  
      }
  
  
  
      /* Write the stream header, if any. */
  
      ret = avformat_write_header(oc, &amp;opt);
  
      if (ret &lt; 0) {
  
          char s[AV_ERROR_MAX_STRING_SIZE];
  
          fprintf(stderr, "Error occurred when opening output file: %s\n",
  
                  cb_av_err2str(s,AV_ERROR_MAX_STRING_SIZE,ret));
  
          return 1;
  
      }
  
  
  
      while (encode_video || encode_audio) {
  
          /* select the stream to encode */
  
          if (encode_video &amp;&amp;
  
              (!encode_audio || av_compare_ts(video_st.next_pts, video_st.enc->time_base,
  
                                              audio_st.next_pts, audio_st.enc->time_base) &lt;= 0)) {
  
              encode_video = !write_video_frame(oc, &amp;video_st);
  
          } else {
  
              //encode_audio = !write_audio_frame(oc, &amp;audio_st);
  
          }
  
  
  
          //std::this_thread::sleep_for(std::chrono::milliseconds(35));
  
      }
  
  
  
      /* Write the trailer, if any. The trailer must be written before you
  
       * close the CodecContexts open when you wrote the header; otherwise
  
       * av_write_trailer() may try to use memory that was freed on
  
       * av_codec_close(). */
  
      av_write_trailer(oc);
  
  
  
      /* Close each codec. */
  
      if (have_video)
  
          close_stream(oc, &amp;video_st);
  
      if (have_audio)
  
          close_stream(oc, &amp;audio_st);
  
  
  
      if (!(fmt->flags &amp; AVFMT_NOFILE))
  
          /* Close the output file. */
  
          avio_closep(&amp;oc->pb);
  
  
  
      /* free the stream */
  
      avformat_free_context(oc);
  
  
  
      return 0;
  
  }
  
  
  
                                                  //
  
  </future></cstring></thread></iostream>

  Environment :

  • Ubuntu Zesty (17.04)
  • FFmpeg version 3.2.4 (via package manager)
  • gcc 6.3 (C++)

• ffmpeg and pulse audio creating buzzy speech

  17 juin 2017, par flashape

  I’m attempting to record video and audio from an ec2 instance (Ubuntu 16.04), using xvfb and pulse audio. Everything works fine, except that the output file contains "buzzy" speech (not sure if this is what "clipping" is ?). This happens using either aac or mp3 audio codecs.

  Sample audio file : http://s000.tinyupload.com/index.php?file_id=86237391396073526211

  ffmpeg command :

  ffmpeg \
  
  -f x11grab -framerate 30 -video_size ${SCREEN_WIDTH}x${SCREEN_HEIGHT} -i :1.0 \
  
  -f pulse -i default \
  
  -c:v libx264 -preset veryfast -maxrate 2500k -bufsize 2500k -vf "format=yuv420p" -g 60 \
  
  -c:a aac -strict -2 -channel_layout stereo  -ab 256k -ar 48000 -bufsize 512k -ac 2  \
  
  -flags +global_header -f flv "test.mp4"

  The output from ffmpeg when I run the command :

  Input #0, x11grab, from ':1.0':
  
    Duration: N/A, start: 1497567394.762052, bitrate: N/A
  
      Stream #0:0: Video: rawvideo (BGR[0] / 0x524742), bgr0, 1360x764, 30 fps, 30 tbr, 1000k tbn, 30 tbc
  
  Guessed Channel Layout for  Input Stream #1.0 : stereo
  
  Input #1, pulse, from 'default':
  
    Duration: N/A, start: 1497567396.743667, bitrate: 1536 kb/s
  
      Stream #1:0: Audio: pcm_s16le, 48000 Hz, 2 channels, s16, 1536 kb/s
  
  [libx264 @ 0x1977d20] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 AVX2 LZCNT BMI2
  
  [libx264 @ 0x1977d20] profile High, level 3.2
  
  [libx264 @ 0x1977d20] 264 - core 148 r2643 5c65704 - H.264/MPEG-4 AVC codec - Copyleft 2003-2015 - http://www.videolan.org/x264.html - options: cabac=1 ref=1 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=2 psy=1 psy_rd=1.00:0.00 mixed_ref=0 me_range=16 chroma_me=1 trellis=0 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=0 threads=3 lookahead_threads=1 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=1 keyint=60 keyint_min=6 scenecut=40 intra_refresh=0 rc_lookahead=10 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 vbv_maxrate=2500 vbv_bufsize=512 crf_max=0.0 nal_hrd=none filler=0 ip_ratio=1.40 aq=1:1.00
  
  Output #0, flv, to 'test.mp4':
  
    Metadata:
  
      encoder         : Lavf56.40.101
  
      Stream #0:0: Video: h264 (libx264) ([7][0][0][0] / 0x0007), yuv420p, 1360x764, q=-1--1, max. 2500 kb/s, 30 fps, 1k tbn, 30 tbc
  
      Metadata:
  
        encoder         : Lavc56.60.100 libx264
  
      Stream #0:1: Audio: aac ([10][0][0][0] / 0x000A), 48000 Hz, stereo, fltp, 256 kb/s
  
      Metadata:
  
        encoder         : Lavc56.60.100 aac
  
  Stream mapping:
  
    Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (libx264))
  
    Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))

  Based on various posts, I thought it might be something in the pulse config, particularly the "resample-method" setting, but that doesn’t appear to do anything. Here is how the /etc/pulse/daemon.conf config file currently stands :

  ; daemonize = no
  
  ; fail = yes
  
  ; allow-module-loading = yes
  
  ; allow-exit = yes
  
  ; use-pid-file = yes
  
  ; system-instance = no
  
  ; local-server-type = user
  
  ; enable-shm = yes
  
  ; shm-size-bytes = 0 # setting this 0 will use the system-default, usually 64 MiB
  
  ; lock-memory = no
  
  ; cpu-limit = no
  
  
  
  ; high-priority = yes
  
  ; nice-level = -11
  
  
  
  ; realtime-scheduling = yes
  
  ; realtime-priority = 5
  
  
  
  ; exit-idle-time = 20
  
  ; scache-idle-time = 20
  
  
  
  ; dl-search-path = (depends on architecture)
  
  
  
  ; load-default-script-file = yes
  
  ; default-script-file = /etc/pulse/default.pa
  
  
  
  ; log-target = auto
  
  ; log-level = notice
  
  ; log-meta = no
  
  ; log-time = no
  
  ; log-backtrace = 0
  
  
  
  ; resample-method = speex-float-1
  
  ; resample-method = speex-float-10
  
  resample-method = speex-fixed-10
  
  ; enable-remixing = yes
  
  enable-lfe-remixing = yes
  
  ; lfe-crossover-freq = 120
  
  
  
  flat-volumes = no
  
  
  
  ; rlimit-fsize = -1
  
  ; rlimit-data = -1
  
  ; rlimit-stack = -1
  
  ; rlimit-core = -1
  
  ; rlimit-as = -1
  
  ; rlimit-rss = -1
  
  ; rlimit-nproc = -1
  
  ; rlimit-nofile = 256
  
  ; rlimit-memlock = -1
  
  ; rlimit-locks = -1
  
  ; rlimit-sigpending = -1
  
  ; rlimit-msgqueue = -1
  
  ; rlimit-nice = 31
  
  ; rlimit-rtprio = 9
  
  ; rlimit-rttime = 200000
  
  
  
  ; default-sample-format = s16le
  
  default-sample-format = s32le
  
  default-sample-rate = 44100
  
  ; default-sample-rate = 48000
  
  ; alternate-sample-rate = 48000
  
  alternate-sample-rate = 44100
  
  ; default-sample-channels = 2
  
  ; default-channel-map = front-left,front-right
  
  
  
  ; default-fragments = 4
  
  ; default-fragment-size-msec = 25
  
  ; default-fragments = 4
  
  ; default-fragment-size-msec = 25
  
  
  
  
  
  ; enable-deferred-volume = yes
  
  deferred-volume-safety-margin-usec = 1
  
  ; deferred-volume-extra-delay-usec = 0

  Edit :

  Ok, updated the ffmpeg command to capture only the audio, but still have the same issue :

  ffmpeg \
  
  -f pulse -i default \
  
  -c:a aac -strict -2 -channel_layout stereo  -ab 256k -ar 48000 -bufsize 512k -ac 2  \
  
  test.aac

  I do get some interesting messages in the output about timestamps being off :

  [aac @ 0x12a4900] Queue input is backward in timeits/s
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 175924
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 176948
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 177972
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 178996
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 180020
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 181044
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 182857 >= 182068
  
  [aac @ 0x12a4900] Queue input is backward in time
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 183406
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 184430
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 185454
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 186478
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 187502
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 188526
  
  [aac @ 0x12a4900] Queue input is backward in time
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 189550
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 190574
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 169622
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 170646
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 171670
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 172694
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 173718
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 174742
  
  [aac @ 0x12a4900] Queue input is backward in time
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 175766
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 176790
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 157020
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 158083
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 159107
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 160131
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 161155
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 162179
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 163203
  
  [aac @ 0x12a4900] Queue input is backward in time
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 164227
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 165251
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 154697
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 159400
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 160424
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 161448
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 162472
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 163496
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 164520
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 165544
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 166568
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 171795
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 172819
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 173843
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 174867
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 175891
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 176915
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 177939
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 178963
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 187279
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 189829
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 190853
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 191877
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 193354 >= 192901
  
  [aac @ 0x12a4900] Queue input is backward in time
  
      Last message repeated 2 times
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 216609 >= 216172
  
  [aac @ 0x12a4900] Queue input is backward in time
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 216609 >= 214950
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 216609 >= 214933
  
  [adts @ 0x12a35a0] Application provided invalid, non monotonically increasing dts to muxer in stream 0: 216609 >= 214836