OpenAI still has a WebRTC Problem

(moq.dev)

48 points | by surprisetalk 1 hour ago

10 comments

  • Sean-Der 27 minutes ago
    WebRTC doesn't give up on late audio. This isn't factually correct. WebRTC has NACKs[0]. The receiver (AI Inference server) decides when to either accept the gap in RTP packets or if it sends the NACK and waits.

    This article doesn't describe how Voice AI systems I work on operate. For speech-to-speech I am working at 20ms/200ms chunks and doing inference. So I don't want buffers

    [0] https://webrtcforthecurious.com/docs/06-media-communication/...

    • Sean-Der 21 minutes ago
      What I find frustrating about these sales pitches that conflate the different parts of WebRTC. WebRTC is protocol, sdk/software and a API in the browser. So if one part has an issue it is important to explain it with detail.

      It's like attacking HTTP by saying 'HTTP is bad because this server doesn't have Y setting'.

    • cma 17 minutes ago
      You can have opus in-band FEC as well, though he mentions it in the article too.
  • InsidiousWombat 19 minutes ago
    Native apps should probably just run local voice recognition AI
    • Sean-Der 5 minutes ago
      Size is the tough part. These models require 256GB+ of vram, but other then that I think it's possible!
    • cush 9 minutes ago
      This is for communicating with agents and inference, not just dictation.
  • cklscikng 30 minutes ago
    Quite interesting. I found the part about tokens with different priorities super cool.
  • FLeXMurphy 14 minutes ago
    Summary: Long-winded advertisement for MoQ. Author mentions that WebRTC has some limitations and Google needs to address them. Until then, anyone (including OpenAI) trying to use WebRTC for human<->bot communication may run into issues.
  • doctorpangloss 50 minutes ago
    If I were "Sean-Der," I would not reply. The "being wrong on the Internet causes smart people to write smarter stuff that's interesting to read" discourse is over. You have to own how much of a waste of time it is.
    • Sean-Der 30 minutes ago
      I don't understand, mind rephrasing?

      I respond because incorrect info will cause developers to make bad decisions/build the wrong thing.

    • kidq330 33 minutes ago
      Sean is not the only developer who has used WebRTC, and conferencing is not the only thing MoQ can be used for. I'd really like to see more devs weighing in, especially those with WebRTC experience
  • fidotron 22 minutes ago
    The moq people, and they are loud and obnoxious, have this incredible ability to ignore the practical experience that led to the defaults of various systems being what they are while believing the solution is to expose every possible to dial to them so they can eventually rediscover the same results, which presumably they will smugly and obnoxiously broadcast as new discoveries to celebrate their brilliance.

    It's like that famous saying about a certain group of people: you can always rely on them to do the right thing, after they've tried every other possibility. They could at least exhibit some level of self awareness.

  • koolala 20 minutes ago
    This seems like an ad for their voice SaaS?
  • paulez 16 minutes ago
    Just ask "what is le capital of la France" no more confusion then.
  • bob1029 38 minutes ago
    Unhinged indeed.
  • prodigycorp 52 minutes ago
    [flagged]