Recherche avancée

Sur d’autres sites (5515)

• ffmpeg to lower/fade audio volume of one audio stream when microphone voice detected ?

  11 juin 2021, par Lectos Lacious

  I want to do live audio translation via microphone, to get streamed live vid/audio from Facebook, plug the mic into laptop and do live translation by mixing existing audio stream with one coming from the mic (translation). This is OK, somehow I got this part by using audio filter "amix" and mix two audio streams together into one. Now I want to add more perfection to it, is it possible to (probably is) upon mic voice detection to automatically decrease/fade down 20% volume of input/original audio stream to hear translation (mic audio) more loudly and then when mic action/voice stops for lets say 3-5 seconds the volume of original audio stream fades up/goes up to normal volume... is this too much, i can play with sox or similar ?

  


• FFmpeg RTP payload 96 instead of 97

  26 octobre 2016, par bot1131357

  I am trying to create an rtp audio stream with ffmpeg. The application output and SDP file configuration are as follows :

  Output #0, rtp, to 'rtp://127.0.0.1:8554':
  
      Stream #0:0: Audio: pcm_s16be, 8000 Hz, stereo, s16, 256 kb/s
  
  
  
  SDP:    
  
  v=0
  
  o=- 0 0 IN IP4 127.0.0.1
  
  s=No Name
  
  c=IN IP4 127.0.0.1
  
  t=0 0
  
  a=tool:libavformat 57.25.101
  
  m=audio 8554 RTP/AVP 96
  
  b=AS:256
  
  a=rtpmap:96 L16/8000/2

  However, when I try to read it with ffplay -i test.sdp -protocol_whitelist file,udp,rtp, it fails,shows the following :

  ffplay version N-78598-g98a0053 Copyright (c) 2003-2016 the FFmpeg developers
  
    built with gcc 5.3.0 (GCC)
  
    configuration: --disable-static --enable-shared --enable-gpl --enable-version3 --disable-w32threads --enable-avisynth --enable-bzlib --enable-fontconfig --enable-frei0r --enable-gnutls --enable-iconv --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libdcadec --enable-libfreetype --enable-libgme --enable-libgsm --enable-libilbc --enable-libmodplug --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-librtmp --enable-libschroedinger --enable-libsoxr --enable-libspeex --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvo-amrwbenc --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs --enable-libxvid --enable-libzimg --enable-lzma --enable-decklink --enable-zlib
  
    libavutil      55. 18.100 / 55. 18.100
  
    libavcodec     57. 24.103 / 57. 24.103
  
    libavformat    57. 25.101 / 57. 25.101
  
    libavdevice    57.  0.101 / 57.  0.101
  
    libavfilter     6. 34.100 /  6. 34.100
  
    libswscale      4.  0.100 /  4.  0.100
  
    libswresample   2.  0.101 /  2.  0.101
  
    libpostproc    54.  0.100 / 54.  0.100
  
      nan    :  0.000 fd=   0 aq=    0KB vq=    0KB sq=    0B f=0/0
  
      (...waits indefinitely.)

  The only way to make it work again is to modify the payload type in the SDP file from 96 to 97. Can someone tell me why ? Where is this number defined ?

  Here is my source. See if you can replicate it.

  #include 
  
  extern "C"
  
  {
  
  #include <libavutil></libavutil>opt.h>
  
  #include <libavcodec></libavcodec>avcodec.h>
  
  #include <libavutil></libavutil>channel_layout.h>
  
  #include <libavutil></libavutil>common.h>
  
  #include <libavutil></libavutil>imgutils.h>
  
  #include <libavutil></libavutil>mathematics.h>
  
  #include <libavutil></libavutil>samplefmt.h>
  
  #include <libavformat></libavformat>avformat.h>
  
  }
  
  
  
  
  
  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);
  
  
  
      /* Write the compressed frame to the media file. */
  
      return av_interleaved_write_frame(fmt_ctx, pkt);
  
  }
  
  
  
  /*
  
  * Audio encoding example
  
  */
  
  static void audio_encode_example(const char *filename)
  
  {
  
      AVPacket pkt;
  
      int i, j, k, ret, got_output;
  
      int buffer_size;
  
  
  
      uint16_t *samples;
  
      float t, tincr;
  
  
  
      AVCodec *outCodec = NULL;
  
      AVCodecContext *outCodecCtx = NULL;
  
      AVFormatContext *outFormatCtx = NULL;
  
      AVStream * outAudioStream = NULL;
  
      AVFrame *outFrame = NULL;
  
  
  
      ret = avformat_alloc_output_context2(&amp;outFormatCtx, NULL, "rtp", filename);
  
      if (!outFormatCtx || ret &lt; 0)
  
      {
  
          fprintf(stderr, "Could not allocate output context");
  
      }
  
  
  
      outFormatCtx->flags |= AVFMT_FLAG_NOBUFFER | AVFMT_FLAG_FLUSH_PACKETS;
  
      outFormatCtx->oformat->audio_codec = AV_CODEC_ID_PCM_S16BE;
  
  
  
      /* find the encoder */
  
      outCodec = avcodec_find_encoder(outFormatCtx->oformat->audio_codec);
  
      if (!outCodec) {
  
          fprintf(stderr, "Codec not found\n");
  
          exit(1);
  
      }
  
  
  
      outAudioStream = avformat_new_stream(outFormatCtx, outCodec);
  
      if (!outAudioStream)
  
      {
  
          fprintf(stderr, "Cannot add new audio stream\n");
  
          exit(1);
  
      }
  
  
  
      outAudioStream->id = outFormatCtx->nb_streams - 1;
  
      outCodecCtx = outAudioStream->codec;
  
      outCodecCtx->sample_fmt = AV_SAMPLE_FMT_S16;
  
  
  
      /* select other audio parameters supported by the encoder */
  
      outCodecCtx->sample_rate = 8000;
  
      outCodecCtx->channel_layout = AV_CH_LAYOUT_STEREO;
  
      outCodecCtx->channels = 2;
  
  
  
      /* open it */
  
      if (avcodec_open2(outCodecCtx, outCodec, NULL) &lt; 0) {
  
          fprintf(stderr, "Could not open codec\n");
  
          exit(1);
  
      }
  
  
  
      // PCM has no frame, so we have to explicitly specify
  
      outCodecCtx->frame_size = 1152;
  
  
  
      av_dump_format(outFormatCtx, 0, filename, 1);
  
  
  
      char buff[10000] = { 0 };
  
      ret = av_sdp_create(&amp;outFormatCtx, 1, buff, sizeof(buff));
  
      printf("%s", buff);
  
  
  
      ret = avio_open2(&amp;outFormatCtx->pb, filename, AVIO_FLAG_WRITE, NULL, NULL);
  
      ret = avformat_write_header(outFormatCtx, NULL);
  
      printf("ret = %d\n", ret);
  
      if (ret &lt;0) {
  
          exit(1);
  
      }
  
  
  
      /* frame containing input audio */
  
      outFrame = av_frame_alloc();
  
      if (!outFrame) {
  
          fprintf(stderr, "Could not allocate audio frame\n");
  
          exit(1);
  
      }
  
  
  
      outFrame->nb_samples = outCodecCtx->frame_size;
  
      outFrame->format = outCodecCtx->sample_fmt;
  
      outFrame->channel_layout = outCodecCtx->channel_layout;
  
  
  
      /* we calculate the size of the samples buffer in bytes */
  
      buffer_size = av_samples_get_buffer_size(NULL, outCodecCtx->channels, outCodecCtx->frame_size,
  
          outCodecCtx->sample_fmt, 0);
  
      if (buffer_size &lt; 0) {
  
          fprintf(stderr, "Could not get sample buffer size\n");
  
          exit(1);
  
      }
  
      samples = (uint16_t*)av_malloc(buffer_size);
  
      if (!samples) {
  
          fprintf(stderr, "Could not allocate %d bytes for samples buffer\n",
  
              buffer_size);
  
          exit(1);
  
      }
  
      /* setup the data pointers in the AVFrame */
  
      ret = avcodec_fill_audio_frame(outFrame, outCodecCtx->channels, outCodecCtx->sample_fmt,
  
          (const uint8_t*)samples, buffer_size, 0);
  
      if (ret &lt; 0) {
  
          fprintf(stderr, "Could not setup audio frame\n");
  
          exit(1);
  
      }
  
  
  
      /* encode a single tone sound */
  
      t = 0;
  
      int next_pts = 0;
  
      tincr = 2 * M_PI * 440.0 / outCodecCtx->sample_rate;
  
      for (i = 0; i &lt; 400000; i++) {
  
          av_init_packet(&amp;pkt);
  
          pkt.data = NULL; // packet data will be allocated by the encoder
  
          pkt.size = 0;
  
  
  
          for (j = 0; j &lt; outCodecCtx->frame_size; j++) {
  
              samples[2 * j] = (uint16_t)(sin(t) * 10000);
  
  
  
              for (k = 1; k &lt; outCodecCtx->channels; k++)
  
                  samples[2 * j + k] = samples[2 * j];
  
              t += tincr;
  
          }
  
          t = (t > 50000) ? 0 : t;
  
  
  
          // Sets time stamp
  
          next_pts += outFrame->nb_samples;
  
          outFrame->pts = next_pts;
  
  
  
          /* encode the samples */
  
          ret = avcodec_encode_audio2(outCodecCtx, &amp;pkt, outFrame, &amp;got_output);
  
          if (ret &lt; 0) {
  
              fprintf(stderr, "Error encoding audio frame\n");
  
              exit(1);
  
          }
  
          if (got_output) {
  
              write_frame(outFormatCtx, &amp;outCodecCtx->time_base, outAudioStream, &amp;pkt);
  
              av_packet_unref(&amp;pkt);
  
          }
  
  
  
          printf("i:%d\n", i); // waste some time to avoid over-filling jitter buffer
  
          printf("Audio: %d\t%d\n", samples[0], samples[1]); // waste some time to avoid over-filling jitter buffer
  
          printf("t: %f\n", t); // waste some time to avoid over-filling jitter buffer
  
      }
  
  
  
      /* get the delayed frames */
  
      for (got_output = 1; got_output; i++) {
  
          ret = avcodec_encode_audio2(outCodecCtx, &amp;pkt, NULL, &amp;got_output);
  
          if (ret &lt; 0) {
  
              fprintf(stderr, "Error encoding frame\n");
  
              exit(1);
  
          }
  
  
  
          if (got_output) {
  
              pkt.pts = AV_NOPTS_VALUE;
  
              write_frame(outFormatCtx, &amp;outCodecCtx->time_base, outAudioStream, &amp;pkt);
  
              av_packet_unref(&amp;pkt);
  
          }
  
      }
  
  
  
      av_freep(&amp;samples);
  
      av_frame_free(&amp;outFrame);
  
      avcodec_close(outCodecCtx);
  
      av_free(outCodecCtx);
  
  }
  
  
  
  
  
  int main(int argc, char **argv)
  
  {
  
      const char *output;
  
  
  
      av_register_all();
  
      avformat_network_init(); // for network streaming
  
  
  
      audio_encode_example("rtp://127.0.0.1:8554");
  
  
  
      return 0;
  
  }

  Update

  Curiously, running on Linux Ubuntu gives me the following instead :

  Output #0, rtp, to 'rtp://127.0.0.1:8554':
  
      Stream #0:0: Unknown: none (pcm_s16be)
  
  v=0
  
  o=- 0 0 IN IP4 127.0.0.1
  
  s=No Name
  
  c=IN IP4 127.0.0.1
  
  t=0 0
  
  a=tool:libavformat 57.48.100
  
  m=application 8554 RTP/AVP 3

  Does anyone know why the stream has been changed from audio to application ?

• FFMPEG : Send Email with output after ffmpeg completes

  13 décembre 2017, par MegaXLR

  I have a VPS running Debian 9 GNU/Linux that transcodes mp4 files, because it’s a cheap single-core server it might take several hours. I want to send an email to myself when it completes with the output from ffmpeg.

  I have tried

  (ffmpeg -i input.mp4 -acodec copy -vcodec copy -y output.mp4 >> ffmpeg.log; cat ffmpeg.log) | mail -s "FFMPEG COMPLETE" email@me.net

  But that left me with the email sending immediatly without body.

  (my SMTP client is Unix Sendmail)