That was the theme of the medical machines in Elysium. They just kinda removed all the defects and bad parts from your body. Of course it was reserved only for the ultra-rich up on the space station. Sigh.

Sure, I ended up taking apart the PicoVoice GitHub demo Python for Porcupine to integrate it into a chatGPT-powered chatbot. It’s also using google speechToText and textToSpeech, so a fair bit of cloud stuff. But surprisingly the latency is pretty low. I’m running it on a small form factor Debian Linux box from MeLE. I was trying to run it all on a Pi4B but it didn’t have the GPU I needed for the front end. The chatbot and Python side all ran ok albeit slower, but I abandoned the Pi. This is the example project I drew inspiration from: https://github.com/atxguitarist/BassGPT/blob/main/BassGPT.py

I was using snowboy for a bit but recently switched to PicoVoice Porcupine and it’s been really good. You’re even able to train a custom wakeword etc. For relatively low usage it might be worth checking out. EDIT: ahh forgive me if this is not home-assistant compatible but it might be

I use my lips to bite my ice-cream

I ditched Evernote and moved to Standard Notes. It’s everywhere for me, iOS, windows, Linux and MacOS and it has a web client which is consistent with all versions of the app. My only gripe is easy image embedding. But I’m living without it.