Open Menu
AllLocalCommunitiesAbout
lotide
AllLocalCommunitiesAbout
Login

FFmpeg 8 can subtitle your videos on the fly with Whisper

⁨120⁩ ⁨likes⁩

Submitted ⁨⁨1⁩ ⁨year⁩ ago⁩ by ⁨along_the_road@beehaw.org⁩ to ⁨technology@beehaw.org⁩

https://www.theregister.com/2025/08/28/ffmpeg_8_huffman/

source

Comments

Sort:hotnewtop
  • melroy@kbin.melroy.org ⁨1⁩ ⁨year⁩ ago

    FFmpeg is one of the most unrated software on Linux. It's so important for the ecosystem very widely used. And you most likely barely notice it.

    Just like curl.

    source
    • Appoxo@lemmy.dbzer0.com ⁨1⁩ ⁨year⁩ ago

      You mean underrated?

      source
      • melroy@kbin.melroy.org ⁨1⁩ ⁨year⁩ ago

        Haha yes. My bad.

        source
    • AnarchistArtificer@slrpnk.net ⁨1⁩ ⁨year⁩ ago

      I remember way back when I was still intimidated by the command line, I was having issues with a video, and the only info I could find was on using ffmpeg to do some conversions directly. I laugh at the memory of me being nonplussed at trying to launch ffmpeg and expecting a GUI to pop up.

      I am glad that I spent some time getting to know ffmpeg directly. There’s been a few times where knowing that it was ffmpeg under the hood helped me.

      source
  • jcr@jlai.lu ⁨1⁩ ⁨year⁩ ago

    So proud of FFmpeg and VLC project ; I want news like this everyday ! Scavenging the good stuff from AI and putting itt to good use, we need more of this ! Next time automatic translation integration from AI models and we don’t need to worry about the dredge of syncing subtitles with videos, one button compilation process and woosh ! -> in fact “on the fly” means no need for compilation, it is even better than I thought 🤩

    source
    • Sina@beehaw.org ⁨1⁩ ⁨year⁩ ago

      I use mpv & it’s just a gui frontend to ffmpeg. I have some layering issues with VLC on Linux…

      source
      • quick_snail@feddit.nl ⁨1⁩ ⁨year⁩ ago

        Isn’t MPV liberally not a GUI?

        source
  • herseycokguzelolacak@lemmy.ml ⁨1⁩ ⁨year⁩ ago

    the people behind ffmpeg need a medal.

    source
  • limerod@reddthat.com ⁨1⁩ ⁨year⁩ ago

    This is superb news. Now, we need audio translation and we can watch any videos in any language in the whole world.

    Currently, doing that is a bit complicated than it needs to be.

    source
    • chahk@beehaw.org ⁨1⁩ ⁨year⁩ ago

      After that - dubbing in realtime.

      source
      • Midnitte@beehaw.org ⁨1⁩ ⁨year⁩ ago

        Call it dubblefish

        source
  • flango@lemmy.eco.br ⁨1⁩ ⁨year⁩ ago

    Ok, but how to use it?

    source
    • MoonMelon@lemmy.ml ⁨1⁩ ⁨year⁩ ago

      I really like this website for exploring all the options. Not sure how up to date it is with this latest ffmpeg.

      ffmpeg.lav.io

      source
    • FundMECFS@anarchist.nexus ⁨1⁩ ⁨year⁩ ago

      following

      source
  • dubyakay@lemmy.ca ⁨1⁩ ⁨year⁩ ago

    I need something like this but for image viewers and for manga/manhwa. It always amazes me how there’s options for this on mobile, even on IOS, but desktop linux doesn’t have anything comparable that has integrated text recognition and translation overlay.

    source
    • limerod@reddthat.com ⁨1⁩ ⁨year⁩ ago

      Can you share those options? I’m curious.

      source
      • dubyakay@lemmy.ca ⁨1⁩ ⁨year⁩ ago

        I’m just going by what the default image viewer on iOS is capable of:

        Image

        Which is pretty yank, but I know that there’s also Google Lens on android, which does a lot better job, so I assume there’s actual better, more manga reading suited software out there for both mobile OSes.

        I saw some implementation on Linux that worked a bit, but…

        source
  • LukeZaz@beehaw.org ⁨1⁩ ⁨year⁩ ago

    The changelog lists 30 significant changes, of which the top new feature is integrating Whisper. This means whisper.cpp, which is Georgi Gerganov’s entirely local and offline version of OpenAI’s Whisper automatic speech recognition model. The bottom line is that FFmpeg can now automatically subtitle videos for you.

    Yeah hey, can anyone chime in if this is at all based off LLMs? Because my problems with the incorrect plagiarism machine don’t end just because it’s now the offline incorrect plagiarism machine. Making OpenAI’s garbage hockey open source doesn’t make it okay. Or should I just start calling this shit FOSSwashing?

    source
    • kayohtie@pawb.social ⁨1⁩ ⁨year⁩ ago

      It’s not AI, it’s neural network models in the same way voice recognition in devices has been working for over a decade. Even Dragon has been utilizing language models vectors for a very long time, just requiring voice training instead of utilizing a premade research or open-source data set.

      I hate generative AI and it’s slop too, but getting angry about neural network models in general is not only absurd, but playing exactly into what corporations want – conflation of the underlying basic technology concepts with the capitalistic vampirism of art.

      source
      • drosophila@lemmy.blahaj.zone ⁨1⁩ ⁨year⁩ ago

        It’s not AI, it’s neural network models

        These used to be called AI before people decided that only LLMs and Diffusion models were AI. Both of which are types of neural networks.

        source
        • -> View More Comments
  • quick_snail@feddit.nl ⁨1⁩ ⁨year⁩ ago

    Is it in the official Debian apt repos yet,m

    source