Interesting, well I'm glad it's working well for you all. I tested with local, HA Cloud, and ChatGPT/Claude and that wasn't the sticking point, it was getting the hardware to hear me or for me to hear it.

I will say, while it was too slow (today) with the my local inference hardware (CPU, older computer and a little on my newer MBP) it was magically to talk to and hear back from HA all locally. I look forward to a future where I can do that at the same speed/quality as the cloud models. Yes, I know cloud models will continue to get better but turning on/off my fans/lights/etc doesn't need to best model available, just needs to be reliable and fast, I'm even fine with it "shelling out" to the cloud if I ask it for something outside of the basics though I doubt I'll care to do that.

> Yes, I know cloud models will continue to get better but turning on/off my fans/lights/etc doesn't need to best model available, just needs to be reliable and fast, I'm even fine with it "shelling out" to the cloud if I ask it for something outside of the basics though I doubt I'll care to do that.

This is exactly how I feel. Its also why I like the multiple wake words - one for remote and one for local.

One of the amazing things I've found with the LLM powered voice assistants is being able to 'recover' from mistakes - e.g. when cooking and forgetting to set the next timer, I can recover by asking about another event like when the last timer ended or when I turned off the bedroom light. Its annoying you can't do that with Alexa. This 'complexity' doesn't need a huge or SOTA model to resolve! I also enjoy being able to ask for a song by half title and half description - my wife was trying to play Ghost by Au/Ra, which we just can't get the Alexa to do, and I can't reasonably get my local LLMs to fail at.

After your comment earlier I took the preview edition into the kitchen, where it did perform a lot worse with the multiple bits of white noise and odd room shape.