News for hackers. Stuff that matters.

A comment on Show HN: I built a sub-500ms latency voice agent from scratch. Parent comment

Re:Show HN: I built a sub-500ms latency voice agent from scr... by lukax on Monday March 02, 2026 @05:37PM (#47225181)
Sorry, I commented too soon. Did you also try Soniox? Why did you decide to use Deepgram's Flux (English only)?
[ Parent | on HN ]
Re:Show HN: I built a sub-500ms latency voice agent from scr... by nicktikhonov on Monday March 02, 2026 @05:41PM (#47225234)
I didn't try Soniox, but I made a note to check it out! I chose Flux because I was already using Deepgram for STT and just happened to discover it when I was doing research. It would definitely be a good follow-up to try out all the different endpointing solutions to see what would shave off additional latency and feel most natural.

Another good follow-up would be to try PersonaPlex, Nvidia's new model that would completely replace this architecture with a single model that does everything:

https://research.nvidia.com/labs/adlr/personaplex/

[ Parent | on HN ]