Recherche avancée

Sur d’autres sites (8584)

• FFmpeg encoding live audio to aac issue

  12 juillet 2015, par Ruurd Adema

  I’m trying to encode live raw audio coming from a Blackmagic Decklink input card to a mov file with AAC encoding.

  The issue is that the audio sounds distorted and plays to fast.

  I created the software based on a couple of examples/tutorials including the Dranger tutorial and examples on Github (and of course the examples in the FFmpeg codebase).

  Honestly, at this moment I don’t exactly know what the cause of the problem is. I’m thinking about PTS/DTS values or a timebase mismatch (because of the too fast playout), I tried a lot of things, including working with an av_audio_fifo.

  • When outputting to the mov file with the AV_CODEC_ID_PCM_S16LE codec, everything works well
  • When outputting to the mov file with the AV_CODEC_ID_AAC codec, the problems occur
  • When writing RAW audio VLC media info shows :
    Type : Audio, Codec : PCM S16 LE (sowt), Language : English, Channels : Stereo, Sample rate : 48000 Hz, Bits per sample.
  • When writing with AAC codec VLC media info shows :
    Type : Audio, Codec : MPEG AAC Audio (mp4a), Language : English, Channels : Stereo, Sample rate : 48000 Hz.

  Any idea(s) of what’s causing the problems ?

  Code

  // Create output context
  
  
  
  output_filename = "/root/movies/encoder_debug.mov";
  
  output_format_name = "mov";
  
  if (avformat_alloc_output_context2(&output_fmt_ctx, NULL, output_format_name, output_filename) < 0)
  
  {
  
      printf("[ERROR] Unable to allocate output format context for output: %s\n", output_filename);
  
  } 
  
  
  
  // Create audio output stream
  
  
  
  static AVStream *encoder_add_audio_stream(AVFormatContext *oc, enum AVCodecID codec_id)
  
  {
  
      AVCodecContext  *c;
  
      AVCodec         *codec;
  
      AVStream        *st;
  
  
  
      st = avformat_new_stream(oc, NULL);
  
      if (!st) 
  
      {
  
          printf("[ERROR] Could not allocate new audio stream!\n");
  
          exit(-1);
  
      }
  
  
  
      c                 = st->codec;
  
      c->codec_id       = codec_id;
  
      c->codec_type     = AVMEDIA_TYPE_AUDIO;
  
      c->sample_fmt     = AV_SAMPLE_FMT_S16;
  
      c->sample_rate    = decklink_config()->audio_samplerate;
  
      c->channels       = decklink_config()->audio_channel_count;
  
      c->channel_layout = av_get_default_channel_layout(decklink_config()->audio_channel_count);
  
      c->time_base.den  = decklink_config()->audio_samplerate;
  
      c->time_base.num  = 1;
  
  
  
      if (codec_id == AV_CODEC_ID_AAC)
  
      {
  
          c->bit_rate       = 96000;  
  
          //c->profile = FF_PROFILE_AAC_MAIN; //FIXME Generates error: "Unable to set the AOT 1: Invalid config"
  
          // Allow the use of the experimental AAC encoder
  
          c->strict_std_compliance = FF_COMPLIANCE_EXPERIMENTAL; 
  
      }
  
  
  
      // Some formats want stream headers to be seperate (global?)
  
      if (oc->oformat->flags & AVFMT_GLOBALHEADER)
  
      {
  
          c->flags |= CODEC_FLAG_GLOBAL_HEADER;
  
      }
  
  
  
      codec = avcodec_find_encoder(c->codec_id);
  
      if (!codec)
  
      {
  
          printf("[ERROR] Audio codec not found\n");
  
          exit(-1);
  
      }
  
  
  
      if (avcodec_open2(c, codec, NULL) < 0)
  
      {
  
          printf("[ERROR] Could not open audio codec\n");
  
          exit(-1);
  
      }
  
  
  
      return st;
  
  }
  
  
  
  // En then, at every incoming frame this function gets called:
  
  
  
  void encoder_handle_incoming_frame(IDeckLinkVideoInputFrame *videoframe, IDeckLinkAudioInputPacket *audiopacket)
  
  {
  
      void *pixels = NULL;
  
      int   pitch = 0;
  
      int got_packet = 0;
  
  
  
      void *audiopacket_data          = NULL;
  
      long  audiopacket_sample_count  = 0;
  
      long  audiopacket_size          = 0;
  
      long  audiopacket_channel_count = 2;
  
  
  
      if (audiopacket)
  
      {  
  
          AVPacket pkt = {0,0,0,0,0,0,0,0,0,0,0,0,0,0};
  
          AVFrame *frame;
  
          BMDTimeValue audio_pts;
  
          int requested_size;
  
          static int last_pts1, last_pts2 = 0;
  
  
  
          audiopacket_sample_count  = audiopacket->GetSampleFrameCount();
  
          audiopacket_channel_count = decklink_config()->audio_channel_count;
  
          audiopacket_size          = audiopacket_sample_count * (decklink_config()->audio_sampletype/8) * audiopacket_channel_count;
  
  
  
          audiopacket->GetBytes(&audiopacket_data);
  
  
  
          av_init_packet(&pkt);    
  
  
  
          printf("\n=== Audiopacket: %d ===\n", audio_stream->codec->frame_number);
  
  
  
          if (AUDIO_TYPE == AV_CODEC_ID_PCM_S16LE)
  
          {
  
              audiopacket->GetPacketTime(&audio_pts, audio_stream->time_base.den);
  
  
  
              pkt.pts          = audio_pts;
  
              pkt.dts          = pkt.pts; 
  
              pkt.flags       |= AV_PKT_FLAG_KEY;                 // TODO: Make sure if this still applies
  
              pkt.stream_index = audio_stream->index;
  
              pkt.data         = (uint8_t *)audiopacket_data;
  
              pkt.size         = audiopacket_size;
  
  
  
              printf("[PACKET] size:              %d\n", pkt.size);
  
              printf("[PACKET] pts:               %li\n", pkt.pts);
  
              printf("[PACKET] pts delta:         %li\n", pkt.pts - last_pts2);
  
              printf("[PACKET] duration:          %d\n", pkt.duration);
  
              last_pts2 = pkt.pts;
  
  
  
              av_interleaved_write_frame(output_fmt_ctx, &pkt);
  
          } 
  
          else if (AUDIO_TYPE == AV_CODEC_ID_AAC)
  
          {
  
              frame = av_frame_alloc();
  
              frame->format = audio_stream->codec->sample_fmt;
  
              frame->channel_layout = audio_stream->codec->channel_layout;
  
              frame->sample_rate = audio_stream->codec->sample_rate;
  
              frame->nb_samples = audiopacket_sample_count;
  
  
  
              requested_size = av_samples_get_buffer_size(NULL, audio_stream->codec->channels, audio_stream->codec->frame_size, audio_stream->codec->sample_fmt, 1);
  
  
  
              audiopacket->GetPacketTime(&audio_pts, audio_stream->time_base.den);
  
  
  
              printf("[DEBUG] Sample format:      %d\n", frame->format);
  
              printf("[DEBUG] Channel layout:     %li\n", frame->channel_layout);
  
              printf("[DEBUG] Sample rate:        %d\n", frame->sample_rate);
  
              printf("[DEBUG] NB Samples:         %d\n", frame->nb_samples);
  
              printf("[DEBUG] Datasize:           %li\n", audiopacket_size);
  
              printf("[DEBUG] Requested datasize: %d\n", requested_size);
  
              printf("[DEBUG] Too less/much:      %li\n", audiopacket_size - requested_size);
  
              printf("[DEBUG] Framesize:          %d\n", audio_stream->codec->frame_size);
  
              printf("[DEBUG] Audio pts:          %li\n", audio_pts);
  
              printf("[DEBUG] Audio pts delta:    %li\n", audio_pts - last_pts1);
  
              last_pts1 = audio_pts;
  
  
  
              frame->pts = audio_pts;
  
  
  
              if (avcodec_fill_audio_frame(frame, audiopacket_channel_count, audio_stream->codec->sample_fmt, (const uint8_t *)audiopacket_data, audiopacket_size, 0) < 0)
  
              {
  
                  printf("[ERROR] Filling audioframe failed!\n");
  
                  exit(-1);
  
              }
  
  
  
              got_packet = 0;
  
              if (avcodec_encode_audio2(audio_stream->codec, &pkt, frame, &got_packet) != 0)
  
              {
  
                  printf("[ERROR] Encoding audio failed\n");
  
              }
  
  
  
              if (got_packet) 
  
              {
  
                  pkt.stream_index = audio_stream->index;
  
                  pkt.flags       |= AV_PKT_FLAG_KEY; 
  
  
  
                  //printf("[PACKET] size:              %d\n", pkt.size);
  
                  //printf("[PACKET] pts:               %li\n", pkt.pts);
  
                  //printf("[PACKET] pts delta:         %li\n", pkt.pts - last_pts2);
  
                  //printf("[PACKET] duration:          %d\n", pkt.duration);
  
                  //printf("[PACKET] timebase codec:    %d/%d\n", audio_stream->codec->time_base.num, audio_stream->codec->time_base.den);
  
                  //printf("[PACKET] timebase stream:   %d/%d\n", audio_stream->time_base.num, audio_stream->time_base.den);
  
                  last_pts2 = pkt.pts;
  
  
  
                  av_interleaved_write_frame(output_fmt_ctx, &pkt);
  
              }
  
              av_frame_free(&frame); 
  
          }
  
  
  
          av_free_packet(&pkt);
  
      }
  
      else
  
      {
  
          printf("[WARNING] No audiopacket received!\n");
  
      }
  
  
  
      static int count = 0;
  
      count++;
  
  }

• Live streaming using FFMPEG to web audio api

  19 janvier 2014, par Nayan

  I am trying to stream audio using node.js + ffmpeg to browsers connected in LAN only using web audio api.

  Not using element because it's adding it's own buffer of 8 to 10 secs and I want to get maximum high latency possible (around 1 to 2 sec max).

  Audio plays successfully but audio is very choppy and noisy.

  Here is my node.js (server side) file :

  var ws = require('websocket.io'), 
  
  server = ws.listen(3000);
  
  var child_process = require("child_process");
  
  var i = 0;
  
  server.on('connection', function (socket) 
  
  {
  
  
  
  console.log('New client connected');
  
  
  
  var ffmpeg = child_process.spawn("ffmpeg",[
  
      "-re","-i",
  
      "A.mp3","-f",
  
      "f32le",
  
      "pipe:1"                     // Output to STDOUT
  
      ]);
  
  
  
   ffmpeg.stdout.on('data', function(data)
  
   {
  
      var buff = new Buffer(data);
  
      socket.send(buff.toString('base64'));
  
   });
  
  });

  And here is my HTML :

  var audioBuffer = null;
  
  var context = null;
  
  window.addEventListener('load', init, false);
  
  function init() {
  
      try {
  
          context = new webkitAudioContext();
  
      } catch(e) {
  
          alert('Web Audio API is not supported in this browser');
  
      }
  
  }
  
  
  
  var ws = new WebSocket("ws://localhost:3000/");
  
  
  
  ws.onmessage = function(message)
  
  {
  
      var d1 = base64DecToArr(message.data).buffer;
  
      var d2 = new DataView(d1);
  
  
  
      var data = new Float32Array(d2.byteLength / Float32Array.BYTES_PER_ELEMENT);
  
      for (var jj = 0; jj < data.length; ++jj)
  
      {
  
          data[jj] = d2.getFloat32(jj * Float32Array.BYTES_PER_ELEMENT, true);
  
      }
  
  
  
      var audioBuffer = context.createBuffer(2, data.length, 44100);
  
      audioBuffer.getChannelData(0).set(data);
  
  
  
      var source = context.createBufferSource(); // creates a sound source
  
      source.buffer = audioBuffer;
  
      source.connect(context.destination); // connect the source to the context's destination (the speakers)
  
      source.start(0);
  
  };

  Can any one advise what is wrong ?

  Regards,
  Nayan

• Using ffmpeg to record 15 minute segments of a live audio stream

  6 août 2015, par David

  I currently have a code setup to record a live streaming audio file from a given url to an mp3 file until I terminate the program.

  fmpeg(obj.url)
  
  .noVideo()
  
  .format('mp3')
  
      .on('error', function(err, stdout, stderr) {
  
      console.error(err);
  
      console.error(stdout);
  
      console.error(stderr)
  
    })

  I already have it set up so that it will create a new file every time the ffmpeg is called. All I need is a way to have ffmpeg stop, and then start again, every 15 minutes.

  I know duration will stop it after 15 minutes, but I don’t know of anything that will start the same ffmpeg file again after this.