FRESH

Hacker News

Building voice agents with Nvidia open models

126 points by kwindla

by amelius

1 subcomments

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"?

by smusamashah

1 subcomments

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.

by rickydroll

0 subcomment

<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."

by jjcm

0 subcomment

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.

by nowittyusername

0 subcomment

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.

by jauntywundrkind

1 subcomments

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

by atonse

0 subcomment

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.

by deckar01

1 subcomments