Are there any open source full duplex models that are out besides PersonaPlex? There was a chinese open one, maybe Fun Audio chat or something, that said it was going to release a full duplex version but I am not sure if it did.

My dream would be open source full duplex with function calling or some kind of rudimentary text output. PersonaPlex is still interesting although it was looking like we would need to fine tune it to handle outgoing or avoid going off the rails easily.

▲

programjames 4 hours ago | parent | next [-]

Standard Intelligence released one two years ago:

https://si.inc/posts/hertz-dev/

It's only 8.5B and doesn't sound like it's quite conversational.

▲

VladVladikoff 5 hours ago | parent | prev | next [-]

I want to know this too, as I’m hoping to fabricobble up a “smart speaker” that communicates with my local AI assistant. Right now we do everything via iMessage but it would be nice to be able to tell it to add things to my grocery list by voice while my hands are busy in the kitchen. Also would love if anyone has any advice on what microphone & speaker to pick out, was planning on just reusing a raspberry pi I’ve got around for the brain part.

	▲	ilaksh 5 hours ago \| parent \| next [-]
		if you don't find that then you could fake it with personaplex possibly but making another ASR/STT model just listen continuously and transcribe then send to an LLM with function calling. at least that would allow one direction easily.
	▲	Rebelgecko 5 hours ago \| parent \| prev [-]
		If you're in the Home Assistant ecosystem, I'm intrigued by their voice hw

▲

andersthuesen 4 hours ago | parent | prev [-]

Working on this at https://duplexio.ai which will be open weights and free for non-commercial use. If you want to work on this send an email to anders@duplexio.ai