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 nicktikhonov on Monday March 02, 2026 @05:53PM (#47225366)
If you're of that opinion, you'll enjoy the new stuff coming out from nvidia:

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

[ Parent | on HN ]
Re:Show HN: I built a sub-500ms latency voice agent from scr... by woodson on Monday March 02, 2026 @06:17PM (#47225668)
You mean Moshi (https://github.com/kyutai-labs/moshi)? Since Personaplex is just a finetuned Moshi model.
[ Parent | on HN ]
Re:Show HN: I built a sub-500ms latency voice agent from scr... by mountainriver on Monday March 02, 2026 @07:04PM (#47226083)
Yeah except moshi doesn’t sound good at all
[ Parent | on HN ]
Re:Show HN: I built a sub-500ms latency voice agent from scr... by ilaksh on Tuesday March 03, 2026 @02:11AM (#47229155)
It just about works for our current use case but can't comprehend the concept of an outgoing call. So I am trying to fine tune it. Tricky thing is personaplex forked some of the kyutai code and has not integrated the LoRA stuff they added. So we tried to do update personaplex with the fine tuning stuff. Going to find out tonight or tomorrow whether it's actually feasible when I finish debugg/testing.
[ Parent | on HN ]