Live data from Hacker News

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

community.home-assistant.io

101–110 of 153 posts

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

#101

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…

On the plus side, mine misdetected a wake word during a funny conversation and said "Sorry, I can't find any area called _____[60 second repeat of funny conversation]___" and it made my family laugh harder than we've laughed in a really long time. I even went into the tts cache and saved the wav b/c it was sooo funny.

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

#103

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…

Train a custom wakeword with this? https://github.com/TaterTotterson/microWakeWord-Trainer-Nvid...

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

#104

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…

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

That’s what Google Home does. “Hey, Google, good night”. Beep response then turns off the lights, brings down the blinds etc. but if something is out of whack it talks. I find it convenient.

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

#105

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…

How about a button? I'd prefer to physically press a button on an intercom box than having something churning away constantly processing sound.

Like a light switch?

Or do you mean a button that activates chunked recording, passes it to a speech-to-text model, forwards to an LLM to infer intent, which triggers HA to issue a command, over a wireless network, to the computer with the light attached, to tell the light to turn on.

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

#110

Earlier quoted context omitted.

How about a button? I'd prefer to physically press a button on an intercom box than having something churning away constantly processing sound.

Rules out a bunch of cases where your hands are busy handling ingredients in the kitchen, etc

Put it at foot level and kick it.
Post reply on HN