PersonaPlex
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Jan 23, 2026first mention
Mar 5, 2026latest mention
Why people recommend it
“you'll enjoy the new stuff coming out from nvidia”
“try PersonaPlex, Nvidia's new model that would completely replace this architecture”
Show 2 more
“the NVIDIA Personaplex demos [2] are very impressive in this regard”
“You should look into the new Nvidia model”
Caveats and dissent
“couldn't get even PersonaPlex to run properly”
Often compared with
Who recommends it in their own words
From the makers not counted in the ranking
“it works well for me to toggle lights on and off”
Threads where it came up
- Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift 4 mentions
- Show HN: I built a sub-500ms latency voice agent from scratch 3 mentions
- Show HN: LemonSlice – Give your voice agents a face 2 mentions
- Ask HN: What's the current best local/open speech-to-speech setup? 2 mentions
- Ask HN: Who is hiring? (March 2026) 1 mention
Data: personaplex.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 11
https://gist.github.com/gabereiser/cd8c67262717afd2539dc9c3d00d2c2f
“This is interactive:”
“this full duplex architecture is still a bit off in terms of giving you good accuracy/performance”
“Since Personaplex is just a finetuned Moshi model”
“you'll enjoy the new stuff coming out from nvidia”
“try PersonaPlex, Nvidia's new model that would completely replace this architecture”
“it uses a duplex architecture”
“couldn't get even PersonaPlex to run properly”
“the NVIDIA Personaplex demos [2] are very impressive in this regard”
“I'm going to put this on my list to play around with.”
“You should look into the new Nvidia model”