Building voice agents with Nvidia open models

(daily.co)

116 points | by kwindla 1 day ago

8 comments

  • smusamashah 13 hours ago
    Do any of the top models let you pause and think while speaking? I have to speak non-stop to Gemini assitant and ChatGPT, which is very very useless/unnatural for voice mode. Specially for non-english speakers probably. I sometimes have to think more to translate my thoughts to english.
    • fragmede 12 hours ago
      Have you tried talking to ChatGPT in your native tongue? I was blown away by my mother speaking her native tongue to ChatGPT and having it respond in that language. (It's ever so slightly not a mainstream one.)
      • smusamashah 2 hours ago
        Even in my own language I can't talk without any pauses.
  • amelius 1 day ago
    I've been using festival under Linux.

    https://manpages.ubuntu.com/manpages/trusty/man1/festival.1....

    But it is quite old now and pre-dates the DL/AI era.

    Does anybody know of a good modern replacement that I can "apt install"?

    • sigmonsays 1 day ago
      I used piper with a model I found online. It's _ALOT_ better than festival afaik. I'm not sure you can apt install it though.

      echo "hello" | piper --model ~/.local/share/piper/en_US-lessac-medium.onnx --output_file - | aplay

      • gunalx 1 day ago
        You can in fact apt install piper.
        • amelius 1 day ago
          That's a different piper.

              piper - GTK application to configure gaming devices
  • rickydroll 18 hours ago
    <pedantic>Voice recognition identifies who you are, speech recognition identifies what you say. </pedantic>

    Example:

    Voice recognition: arrrrrrgh! (Oh, I know that guy. He always gets irritated when someone uses terms speech and voice recognition wrong)

    Speech Recognition: "Why can't you guys keep it straight? It is as simple as knowing the difference between hypothesis and theory."

  • jjcm 1 day ago
    These have gotten good enough to really make command-by-voice interactions pleasant. I'd love to try this with Cursor - just use it fully with voice.
  • nowittyusername 1 day ago
    This is perfect for me. I just started working on the voice related stuff for my agent framework and this will be of real use. Thanks.
  • atonse 17 hours ago
    Can't wait for this to land in MacWhisper. I like the idea of the streaming dictation especially when dictating long prompts to Claude Code.
  • deckar01 1 day ago
    It supports Turing T4, but not Ampere…
    • nsbk 22 hours ago
      Any ideas on how to add Ampere support? I have a use case in mind that I would love to try on my 3090 rig
      • deckar01 13 hours ago
        Magpie-TTS needs a kernel compiled targeting Ampere, but it appears to be closed source. It was compiled for the 2018 T4, but not 2020-2024 consumer cards, just 2025 consumer cards.
  • jauntywundrkind 1 day ago
    There's also the excellent also open source unmute.sh. which alas is also Nvidia only at this point. https://unmute.sh/
    • vikboyechko 1 day ago
      The game show is pretty good. Have a feeling this project will consume all my attention this week, thanks for the tip.