Building voice agents with Nvidia open models

#1

Post by kwindla » Wed, Jan 07, 2026, 4:08 PM UTC

Building voice agents with Nvidia open models
daily.co

Re: Building voice agents with Nvidia open models

#2

Post by amelius » Wed, Jan 07, 2026, 6:11 PM UTC

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"?

Re: Building voice agents with Nvidia open models

#3

Post by sigmonsays » Wed, Jan 07, 2026, 8:57 PM UTC

amelius wrote: post #2

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"?

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

Re: Building voice agents with Nvidia open models

#4

Post by jjcm » Wed, Jan 07, 2026, 10:06 PM UTC

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.

Re: Building voice agents with Nvidia open models

#5

Post by gunalx » Wed, Jan 07, 2026, 10:48 PM UTC

sigmonsays wrote: post #3

amelius wrote: post #2

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"?

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

You can in fact apt install piper.

Re: Building voice agents with Nvidia open models

#6

Post by nowittyusername » Wed, Jan 07, 2026, 10:52 PM UTC

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.

Re: Building voice agents with Nvidia open models

#7

Post by amelius » Wed, Jan 07, 2026, 10:56 PM UTC

gunalx wrote: post #5

sigmonsays wrote: post #3

Earlier quoted context omitted.

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

You can in fact apt install piper.

That's a different piper.

    piper - GTK application to configure gaming devices

Re: Building voice agents with Nvidia open models

#8

Post by jauntywundrkind » Wed, Jan 07, 2026, 11:41 PM UTC

There's also the excellent also open source unmute.sh. which alas is also Nvidia only at this point. https://unmute.sh/

Re: Building voice agents with Nvidia open models

#9

Post by vikboyechko » Thu, Jan 08, 2026, 12:40 AM UTC

jauntywundrkind wrote: post #8

There's also the excellent also open source unmute.sh. which alas is also Nvidia only at this point. https://unmute.sh/

The game show is pretty good. Have a feeling this project will consume all my attention this week, thanks for the tip.

Re: Building voice agents with Nvidia open models

#10

Post by deckar01 » Thu, Jan 08, 2026, 5:17 AM UTC

It supports Turing T4, but not Ampere…