“As it stands today, we’re not ready yet to tell people that our voice assistant is a replacement for Google/Amazon,” Schoutsen wrote. “We don’t have to be as good as their systems, but there is a certain bar of usable that we haven’t reached yet.”
Key among the improvements that need to happen, according to Schoutsen:
- Audio input needs to be cleaned up (speaker voice separated) before it is processed
- Error messages need to be more clear about what’s going wrong, and input has to have more flexibility
- Non-English languages need a lot of commands and variables
- Compatible hardware that features far-listening microphones has to be more widely available
- Most people will want local processing to be faster
I use it to set and manage timers in the kitchen. It’s not as good as Google, and the setup to get timers working is hacky, but it does the job and has fully replaced my Google Home when combined with a home assistant dashboard I have on my kitchen wall.
That would be the one thing I’d want it for, I’m thinking about it. I never really found the need to use one of those until I was making a large dinner for friends and they used their watch to help me keep track of everything.
That is amazing and very interesting,
I think all the stuff with home automation is kinda unnecessary, but sometimes I find it cool and interesting, mostly when it is something local.
https://heywillow.io/ seems to solve the voice recognition pretty well. I don’t know how good the home automation integration is, though.
Honestly, just having it call out to a script would be plenty to interest me. I could rig it up to search YouTube for music or something and get a ton of value out of it.
Well there is an OpenAI integration which can be configured to work with local gpt. Then everything is local. It is not perfect, but in some aspects definitely impressive.
This is the best summary I could come up with:
Right now, with some off-the-shelf gear and the patience to flash and fiddle, you can ask “Nabu” or “Jarvis” or any name you want to turn off some lights, set the thermostat, or run automations.
It’s not entirely fair to compare locally run, privacy-minded voice control to the “assistants” offered by globe-spanning tech companies with secondary motives.
While outgrowers are happy to leave behind the inconsistent behavior, privacy concerns, or limitations of their old systems, they can miss being able to just shout from anywhere in a room and have a device figure out their intent.
Here’s a look at what you can do today with your human voice and Home Assistant, what remains to be fixed and made easier, and how it got here.
All that said, it’s impressive how far Home Assistant has come since late 2022, when it made its pronouncement, despite not really having a clear path toward its end goal.
And the work continues; between writing and publishing this post, Home Assistant has already improved its voice error responses.
The original article contains 486 words, the summary contains 174 words. Saved 64%. I’m a bot and I’m open source!
Yeah it’s still pretty bad
