Bought a bunch for a client project. Pretty decent form-factor, but they really need to have hardware that can do on-device AI inference. There are lots of reasonably priced choices out there.
Their whole “private” voice assistant story falls apart when they have to send everything to the cloud, including third-party services.
I think that the pipeline they made for managing voice chat is a great framework - specifically how you can point it to either local systems, their cloud, or third party systems is awesome.
I also think that while they are the champions of home automaton, they are playing catch-up on the voice assistant side.
On the whole I believe they still want to achieve on-prem voice, but the tech to do that is still being baked, and they’re not a Google or an Amazon, so they don’t have the money to be first in line.
I did set up a local LLM on a pretty beefy machine and Whisper to do local voice assistance, but it kept falling apart. The only one that worked reasonably was tying it to a commercial API. This was more than a year ago, so things might have improved.
But if they want to sell these things as an Alexa/Google Home alternative, they’ll have a hell of a story if they built a one-stop hub that ran an on-device model and did everything locally. There are a lot of smaller models now and companies like MediaTek make decent edge-processors with beefy NPUs.
I’m still a big fan of their approach. Sad to see them drop the yellow, but I hope it means they’ll come out with something better.
I agree that the private assistant thing falls apart if only using a green/yellow, but O don’t think that compute should be bolted on to these devices.
I have had an home assistant green for soon a year and it is great for what I need.
If I want the whole AI-thing I wpuld lile that to be run on a separate device that can be reached by the HA-green.
Bought a bunch for a client project. Pretty decent form-factor, but they really need to have hardware that can do on-device AI inference. There are lots of reasonably priced choices out there.
Their whole “private” voice assistant story falls apart when they have to send everything to the cloud, including third-party services.
I think that the pipeline they made for managing voice chat is a great framework - specifically how you can point it to either local systems, their cloud, or third party systems is awesome.
I also think that while they are the champions of home automaton, they are playing catch-up on the voice assistant side.
On the whole I believe they still want to achieve on-prem voice, but the tech to do that is still being baked, and they’re not a Google or an Amazon, so they don’t have the money to be first in line.
I did set up a local LLM on a pretty beefy machine and Whisper to do local voice assistance, but it kept falling apart. The only one that worked reasonably was tying it to a commercial API. This was more than a year ago, so things might have improved.
But if they want to sell these things as an Alexa/Google Home alternative, they’ll have a hell of a story if they built a one-stop hub that ran an on-device model and did everything locally. There are a lot of smaller models now and companies like MediaTek make decent edge-processors with beefy NPUs.
I’m still a big fan of their approach. Sad to see them drop the yellow, but I hope it means they’ll come out with something better.
I agree that the private assistant thing falls apart if only using a green/yellow, but O don’t think that compute should be bolted on to these devices.
I have had an home assistant green for soon a year and it is great for what I need.
If I want the whole AI-thing I wpuld lile that to be run on a separate device that can be reached by the HA-green.