Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

community.home-assistant.io

Post reply on HN
Print view View original

141–150 of 153 posts

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#141

Post by lostmsu »

hamdingers wrote: post #10

If you're less concerned about privacy, I use Gemini 2.5 Flash for this and it's exceptionally good and fast as a HA assistant while being much cheaper than the electricity that would be needed to keep a 3090 awake. The thing that kills this for me (and they even mentioned it) is wake word detection. I have both the HA voice preview and FPH Satellite1 devices, plus have experimented with a few other options like a Ra…

Why do you even need a wake word? Have a model look at full transcript and decide when to engage.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#142

Post by ericmcer »

ljclifford wrote: post #67

actually the hardest part of a locally hosted voice assistant isn't the llm. it's making the tts tolerable to actually talk to every day. the core issue is prosody: kokoro and piper are trained on read speech, but conversational responses have shorter breath groups and different stress patterns on function words. that's why numbers, addresses, and hedged phrases sound off even when everything else works. the fix is t…

Seriously for audio conversations the LLM layer is fairly stable. Getting STT and TTS to be reliable has been a much bigger hurdle.

I hear the same phrases 10+ times in a day and they stress things a bit different each time, it seems like an exceptionally hard problem. My dream of a super reliable [llm output stream -> streaming TTS endpoint -> webRTC audio stream] seems pretty much impossible at this point.

Is the goal to trick people into thinking it is a human or to create a high trust robot? I am hoping as voice agents get more sophisticated the stigma around "It's making me talk to a robot" lessens so we don't need to worry so much about convincing someone it is a real person.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#143

Post by j45 »

phito wrote: post #36
j45 wrote: post #35

Earlier quoted context omitted.

What tech can do vs applying it requires it often to be configured and packaged to be usable in that way.

It also needs to work at least 99% of the time if not more. Not easy to do this with indeterministic models.

Not easy, but doable, especially if it's a local model that is converting inputs into decisions and commands.

Cloud hosted models definitely can not always be consistent, but it's where I'm learning that prompt durability is a thing.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#144

Post by bigiain »

stavros wrote: post #63
CurleighBraces wrote: post #62

Earlier quoted context omitted.

Did you have any luck with the power issues on the new board?

The new board hasn't come yet, but a friend gave me a great idea, to power the mic from a GPIO, which powers it off completely when the ESP is off. Hopefully the new boards will be here soon, but another issue is that I don't really have anything that can measure microamp consumption, so any testing takes days of waiting for the battery to run down :( I do think these clones are the issue, though. They had a LED I co…

Is it worth removing the led from the board? Wont help with any other decisions by the designer that draw excess current, but maybe that's the only or largest one?

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#145

Post by stavros »

bigiain wrote: post #144
stavros wrote: post #63

Earlier quoted context omitted.

The new board hasn't come yet, but a friend gave me a great idea, to power the mic from a GPIO, which powers it off completely when the ESP is off. Hopefully the new boards will be here soon, but another issue is that I don't really have anything that can measure microamp consumption, so any testing takes days of waiting for the battery to run down :( I do think these clones are the issue, though. They had a LED I co…

Is it worth removing the led from the board? Wont help with any other decisions by the designer that draw excess current, but maybe that's the only or largest one?

I did remove it :( It's still pretty bad. I ordered some Xiaos that do explicitly say 14 uA sleep current, but they seem to have gotten lost in the mail!

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#146

Post by konart »

voidUpdate wrote: post #4

Do people like talking to voice assistants? I've used one occasionally (mostly for timers when I'm cooking), but most of the time it would be faster for me to just do it myself, and feels much less awkward than talking to empty air, asking it to do things for me. It might be because I just really don't like making more noise than I have to (Yes, I appreciate that some people may be disabled in such a way that it make…

Voice assistants can be great if you have kids. Sometimes your hands are full in more way than one.

Same for different scenarios when you don't want to use your hands (say you are replanting a flower or something).

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#147

Post by dghlsakjg »

gmueckl wrote: post #75
dghlsakjg wrote: post #69

Earlier quoted context omitted.

This was 2021 (so pre-llm), but I used to work for a company that gathered data for training voice commands (Alexa, Toyota, Sonos, were some clients). Basically, we paid people to read digital assistant scripts at scale. Your assumptions about training data do not match the demographics of data I collected. The majority of what our work revolved around was getting diversity into the training data. We specifically rec…

You are reporting on a deliberately curated effort vs. what I understand is effectively voluntary data donation without incentives. It's not surprising to me that the later dataset ends up biased due to the differences in sourcing.

Your understanding of the datasets I helped create seems at odds with my experience actually creating the datasets. Do you have some insider experience or knowledge with dataset curation and creation for voice assistants that contradicts my own.

The guideline is that the newer your model, the more likely it is to have diverse voice recognition datasets since it solves the earlier problems caused by non representative data. The trend is moving towards better recognition for outliers. The training models are fed data that is very specific and not at all just whatever recordings they have collected in an S3 bucket. Given the amount of post recording work diarization, and QA we had to do on every single recording, I can’t imagine wanting to YOLO in bulk data.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#148

Post by kbelder »

huhtenberg wrote: post #116
hamdingers wrote: post #26

Earlier quoted context omitted.

If I have to go to a thing and push a button, I'd rather the button do the thing I wanted in the first place. Voice assistants are for when my hands are full or I don't want to get up. (I wrote more about my home automation philosophy in another comment[1]). Also I have all my voice assistant devices mounted to the ceiling 1. https://news.ycombinator.com/item?id=47399909

What if you have two things? You'd then need two buttons. The push button is a perfectly viable option, it just needs to be in a form factor that's works. Could be as simple as a tiny low-energy Bluetooth board with a coin battery that will last several months.

Yeah, a touch-sensitive com-badge mounted on your chest would work.

Actually, I would think a small coin-sized button & transmitter that did nothing but emit a signal that your assistant (or phone) interprets as 'start listening' would be pretty useful. In your pocket, on a watch band, etc.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#149

Post by kbelder »

nickthegreek wrote: post #77
cdcarter wrote: post #73

Earlier quoted context omitted.

80% of my home voice assistant requests really need no response other than an affirmative sound effect.

100% agree. I dont want a Yes, Got it, Will do or even worse, I have turned on the Bedroom Light. I want soft success ding or a low failure boop.

I turned on the new 'sassy' personality for Alexa. Now, if you ask it to "set a 5 minute alarm," half the time she'll go off on a short rant about how she must obviously not be good for anything but keeping track of time for us humans.

I haven't figured out how to set her personality to 'brief and succinct' for me, but 'sassy' for my wife.

Re: My Journey to a reliable and enjoyable locally hosted voice assistant (2025)

#150

Post by j45 »

phito wrote: post #36
j45 wrote: post #35

Earlier quoted context omitted.

What tech can do vs applying it requires it often to be configured and packaged to be usable in that way.

It also needs to work at least 99% of the time if not more. Not easy to do this with indeterministic models.

Depending on the use case, it is possible.

It is an adjustment coming from deterministic software and adding non-deterministic software to it, which can be improved by the quality of language and input into it.

Post reply on HN