Recherche avancée

Sur d’autres sites (10468)

• How to convert a GIF to optimized mp4 video using FFMPEG on android ?

  6 novembre 2017, par Omar Hezi

  I successfully integrated FFMPEG as a library on android and I am using JNI to communicate my JAVA classes with C and C++ classes.

  Background and my question
  A chat app where GIFs can be sent, the issue is that one GIF could weigh up to 2MB, after a lot of research I found that the best solution is converting those gifs to mp4 (Something that Facebook messenger, whatsapp and telegram do).

  My question is, how can I convert a gif to mp4 in order to reduce its size, using ffmpeg (not in command line, in android) as Telegram mentions here ?

  What I have attempted

  • Understanding and implementing the gifvdeo.cpp from Telegram (it was extremely complicated and I could not understand it fully)
  • Converting the gif to frames of bitmaps, and compressing each bitmap and then converting those bitmaps to mp4 (I was not able to pass the bitmap object to C through JNI because of " Fatal signal 11 (SIGSEGV), code 1, fault addr 0x31f in tid 26952" which is another question)

  Research I have done

  • using ffmpeg to convert gif to mp4 , output doesn’t play on android
  • How to convert GIF to Mp4 is it possible ?
  • Convert GIF to Video in Android
  • https://unix.stackexchange.com/questions/40638/how-to-do-i-convert-an-animated-gif-to-an-mp4-or-mv4-on-the-command-line

  the problem with above questions is that they use command line FFMPEG which is not what I am doing, I am using JNI and direct access to c classes of mentioned library.

• m4a/mp3 files to wav for Bing Speech API

  17 décembre 2018, par Waqas

  Bing Speech API only accepts wav files so I have been trying to convert m4a (Skype) and mp3 (Facebook) audio files I am getting in my chatbot to wav format. I am using fluent-ffmpeg in node.js.

  For now, I am downloading the audio file, converting it to wav and returning the piped output for use ahead.

  if (attachment.contentType === 'audio/x-m4a') {
  
    request.get(attachment.contentUrl).pipe(fs.createWriteStream('file.m4a'));
  
    var command = ffmpeg('file.m4a')
  
          .toFormat('wav')
  
          .on('error', function (err) {
  
              console.log('An error occurred: ' + err.message);
  
          })
  
          .on('progress', function (progress) {
  
              // console.log(JSON.stringify(progress));
  
              console.log('Processing: ' + progress.targetSize + ' KB converted');
  
          })
  
          .on('end', function () {
  
              console.log('Processing finished !');
  
          });
  
  
  
    return command.pipe();
  
  }

  Right now, the conversion works when I send the m4a file through the botframework-emulator on my pc. But when I specify my pc as the endpoint (through ngrok) and try to send the m4a file from the chat test at the bot framework developer end, ffmpeg returns an error :

  An error occurred: ffmpeg exited with code 1: file.m4a: Invalid data found when processing input

  But when I play the downloaded m4a file, it plays alright.

  The content URL is https in the second case if that matters.

  Kindly help me with two things :

  1. Downloading, Converting and Returning without storing anything on my end
  2. Downloading/Accessing m4a/mp3 files properly

  I am new to streams, pipes and ffmpeg and all the above code is after googling.

• Is ffmpeg able to read ArrayBuffer input from stream

  7 juillet 2017, par jAndy

  I want to accomplish the following tasks :

  • Record Video+Audio from any HTML5 (MediaStream) capable browser
  • Send that data via WebSocket as Blob / ArrayBuffer chunks to a server
  • Broadcast that input stream-data to multiple clients

  As it turns out, this brought me into a world of pain. The first task is fairly simple using the HTML5 MediaStream objects alongside WebSockets.

  // ... for simplicity...
  
  navigator.mediaDevices.getUserMedia({ audio: true, video: true }).then(stream => {
  
      let mediaRecorder = new MediaRecorder( stream );
  
      // ...
  
      mediaRecorder.ondataavailable = e => {
  
          webSocket.send( 'newVideoData', e.data ); // configured for binary data
  
      };
  
  });

  Now, I want to receive those data fragments and stream those via nginx vod module, because I guess I want the output stream in HLS or DASH.
  I could write a little nodejs script as backend, which just receives the binary chunks and write them to a file or stream, and just reference it so nginx vod module could possibly read it and create the m3u8 manifest on the fly ?

  I am wondering now,

  • if ffmpeg is able to read that binary data directly (should be webm format), without a man-in-the-middle script, "somehow" ?
  • If not, do I have to write the data down into a file and pass that as input to ffmpeg or can I (should I) pipe the data to a self spawned ffmpeg instance ? (if so, how ?)
  • Do I actually need the nginx server (probably alongside rtmp module) to deliver the output stream as HLS or could I just use ffmpeg to also create a dynamic manifest ?
  • Is the nginx vod module capable of creating a dynamic hls/dash manifest or must the input data be complete beforehand ?
  • Ultimately, am I on the totally wrong track here ? :P

  Actually I just want to create a little video-live-chat demo, without any plugins or 3rd party encoding software, pure browser.