Depends on which one you have. If you buy their own smart speaker (Voice PE), which is designed to stay entirely local if you have the right hardware and software locally, and even has a hardware switch to temporarily disable the microphone, it’s pretty easy. And of you don’t have all that locally you need a paid subscription to use their cloud a little bit, but they won’t store anything. So still pretty easy.
I want to run my own voice processing service, ideally. Something that runs off of my home assistant server, would be cool if it made use of a Coral AI or similar.
You can. There are simple options, that only recognise predefined sentences, that even work on a Raspberry Pi, and at the other end of the spectrum you can host an LLM locally and chat with that if you have the right hardware (Coral isn’t powerful enough for that, you want a GPU with lots of VRAM). Obviously setting this up is more complicated, but there are a lot of options to do it your way.
IIRC it’s supposed to be getting better rapidly, as it’s an active focus of development for Home Assistant.
That said, I thought this seemed like a good guide on how to set it up as of 8 months ago. (I’m not necessarily a fan of that guy’s bombastic over-enthusiasm, but the info seems good.)
Buy this. You can use your own voice processing on another machine on your network. You could even hook it up to your Ollama. I have it and it’s completely replaced Google Home for voice control.
How is the speaker in that? I have some atoms and the speaker sucks. Thinking about buying a bunch of these Google devices and replacing the PCB but I’d rather save the time if something like this actually has good sound.
For music, it’s not great. For voice, it’s pretty good. It’s decently loud and legible. There’s no bass. The mics however are pretty good. As far as I’ve read, you can’t get the mics to work well unless they’re tuned for that speaker in physical placement and hardware/firmware. The HA speaker uses the same kind of DSP chip that makes it possible for it to hear well in worse than ideal conditions which makes speech recognition work so well. So yeah, if you don’t wanna faff with stuff and you don’t care about music, just get it. It’s got 3.5mm TRS out if you wanna hook a proper speaker for music. The DAC is probably not amazing for HiFi but should you want to hook up something like a JBL Charge, I imagine it should work. In fact I’m planning to do this in another room where I used to use a larger Google Nest speaker for music.
It does! I have my bedroom one controlled through it and even showing up as a play target for Spotify Connect. I’ve got my speakers I was plugging into my phone to play music before, or into a Raspi briefly, plugged into the 3.5mm jack on that one.
My kitchen one I just leave as-is. I DID modify the ESPHome firmware on each, extending to add an OLED (I think) clock display that also shows remaining time for timers in numbers. I do really like the LED ring animation for timers built-in though, it’s pretty slick!
Not sure what a music assistant is. The speaker acts like a media player in Home Assistant. Actually now that I think about it, I don’t know how I’d play music on it. It doesn’t seem to do cast. 🤭
XD, I totally did this to make a smart alarm clock a couple years ago. That said it is completely stable, don’t think it has ever crashed or locked up on me, unlike the echo show it replaced that did so frequently (not to mention it occasionally updating in the middle of the night and waking me up at full brightness)
Is it easy to set up a smart speaker with Home Assistant? Last I heard, it was kind of a PITA.
Depends on which one you have. If you buy their own smart speaker (Voice PE), which is designed to stay entirely local if you have the right hardware and software locally, and even has a hardware switch to temporarily disable the microphone, it’s pretty easy. And of you don’t have all that locally you need a paid subscription to use their cloud a little bit, but they won’t store anything. So still pretty easy.
I want to run my own voice processing service, ideally. Something that runs off of my home assistant server, would be cool if it made use of a Coral AI or similar.
You can. There are simple options, that only recognise predefined sentences, that even work on a Raspberry Pi, and at the other end of the spectrum you can host an LLM locally and chat with that if you have the right hardware (Coral isn’t powerful enough for that, you want a GPU with lots of VRAM). Obviously setting this up is more complicated, but there are a lot of options to do it your way.
IIRC it’s supposed to be getting better rapidly, as it’s an active focus of development for Home Assistant.
That said, I thought this seemed like a good guide on how to set it up as of 8 months ago. (I’m not necessarily a fan of that guy’s bombastic over-enthusiasm, but the info seems good.)
Buy this. You can use your own voice processing on another machine on your network. You could even hook it up to your Ollama. I have it and it’s completely replaced Google Home for voice control.
How is the speaker in that? I have some atoms and the speaker sucks. Thinking about buying a bunch of these Google devices and replacing the PCB but I’d rather save the time if something like this actually has good sound.
For music, it’s not great. For voice, it’s pretty good. It’s decently loud and legible. There’s no bass. The mics however are pretty good. As far as I’ve read, you can’t get the mics to work well unless they’re tuned for that speaker in physical placement and hardware/firmware. The HA speaker uses the same kind of DSP chip that makes it possible for it to hear well in worse than ideal conditions which makes speech recognition work so well. So yeah, if you don’t wanna faff with stuff and you don’t care about music, just get it. It’s got 3.5mm TRS out if you wanna hook a proper speaker for music. The DAC is probably not amazing for HiFi but should you want to hook up something like a JBL Charge, I imagine it should work. In fact I’m planning to do this in another room where I used to use a larger Google Nest speaker for music.
Does it work with music assistant in HA? Thanks for the response btw
It does! I have my bedroom one controlled through it and even showing up as a play target for Spotify Connect. I’ve got my speakers I was plugging into my phone to play music before, or into a Raspi briefly, plugged into the 3.5mm jack on that one.
My kitchen one I just leave as-is. I DID modify the ESPHome firmware on each, extending to add an OLED (I think) clock display that also shows remaining time for timers in numbers. I do really like the LED ring animation for timers built-in though, it’s pretty slick!
Not sure what a music assistant is. The speaker acts like a media player in Home Assistant. Actually now that I think about it, I don’t know how I’d play music on it. It doesn’t seem to do cast. 🤭
Probably 200$ of raspberry pi gear plus a few weekends messing around should net you something awesome that only catastrophically fails sometimes.
XD, I totally did this to make a smart alarm clock a couple years ago. That said it is completely stable, don’t think it has ever crashed or locked up on me, unlike the echo show it replaced that did so frequently (not to mention it occasionally updating in the middle of the night and waking me up at full brightness)
I’m curious about this as well. I think all the components are available, but nobody’s clicked them together yet.
My understanding is the software is the problem, I don’t understand why though.
Because software is hard to write and not many people want to spend their free time writing it???
Instead of complaining, Go be the change you want. It’s all open source…