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

The era of open voice assistants

home-assistant.io

Post reply on HN
Print view View original

261–270 of 290 posts

Re: The era of open voice assistants

#261

Post by thumbsup-_- »

lokar wrote: post #165
sofixa wrote: post #64

Earlier quoted context omitted.

Do you mean the move away from YAML first configs? I was originally somewhat frustrated, but overall, it's much better (let's be honest, YAML sucks) and more user friendly (by that I mean having a form with pre-filled fields is easier than having to copy paste YAML).

Yes, config is a major part of it. But also a lack of good APIs, very poor dev documentation, not great logging. A general “take it or leave it” attitude, not interesting in enabling engineers to build.

I don’t think that’s true. Their docs are great and the community is active and responsive in forums and github

Re: The era of open voice assistants

#262

Post by jorvi »

entropicdrifter wrote: post #192
staunton wrote: post #183

Earlier quoted context omitted.

> Yes, I do understand that "privacy" here is mostly about not sending it for processing to third parties. Then why does it puzzle you?

Because you wouldn't ask it deeply private questions in front of your mom, for instance

You wouldn’t ask your partner deeply private questions in front of your mom either. Not sure how you think it’s a dig against voice assistant privacy.

Re: The era of open voice assistants

#263

Post by adrianN »

mattmaroon wrote: post #259
gregmac wrote: post #257

Earlier quoted context omitted.

FWIW that's not even how Alexa or Google Assistant work. Both listen locally for the wake word with onboard processing, and only when they recognize it do they send the audio stream to the server to fully interpret. You can test this in a couple ways: they'll respond to their wake word when the internet is down (but have an error response). You can also look at the outbound data and see they're not sending continuous…

The developers could do sneaky things with any device that has wifi and a mic.

And yet most people have a phone in their pocket.

Re: The era of open voice assistants

#264

Post by ijidak »

pimeys wrote: post #108
Jarwain wrote: post #7

I'm actually really excited for this! I noticed recently there weren't any good open source hardware projects for voice assistants with a focus on privacy. There's another project I've been thinking about where I think the privacy aspect is Important, and figuring out a good hardware stack has been a Process. The project I want to work on isn't exactly a voice assistant, but same ultimate hardware requirements Someth…

I'm also very excited. I've had some ESP32 microphones before, but they were not really able to understand the wake word, sometimes even when it was quiet and you were sitting next to the mic. This one looks like it can recognize your voice very well, even when music is playing. Because... when it works, it's amazing. You get that Star Trek wake word (KHUM-PUTER!), you can connect your favorite LLM to it (ChatGPT, Cl…

I'm trying to understand. Is there an SDK I can use to enhance this? Or is this a package product?

I'm really hoping it's the former. But I don't see any information about how to develop with this.

Re: The era of open voice assistants

#265

Post by 8n4vidtmkvmk »

IgorPartola wrote: post #255
burningChrome wrote: post #224

Earlier quoted context omitted.

>> I want 5-20, one for every space in my house. I don't have a small house, but I'm trying to think why I would need even 5 of these, let alone 20. The majority of the time my family spends together is in the open layout on our main floor where the kitchen flows into the living room with an adjacent sun room off the living room. I'm genuinely curious why you need so many of these. I do agree that if you do have a le…

I have four bedrooms, living/family room, study, office, rumpus room, garage, workshop, and trying to build out a basement with three more rooms. Each of these rooms have some form of smart lighting or devices like TVs or thermostats that people have a much easier time controlling with voice than phone apps. Granted this may sound extravagant but I have a large family so all this space is all very well utilized hence…

What's condition 2?

Re: The era of open voice assistants

#266

Post by lurking_swe »

yurishimo wrote: post #125
btreecat wrote: post #110

Earlier quoted context omitted.

HA long ago blew past OpenHAB in functionality and community. Unless you have a hard-on for JVM services, HA is the better XP these days.

When I was evaluating both projects about 5 years ago, I went with openHAB because they had native apps with native controls (and thus nicer design imo). At the time, HA was still deep in YML config files and needed validation before saving etc etc. Not great UX. Nowadays, HA has more of the features I would want and other external projects exist to create your own dashboards that take advantage of native controls. T…

I keep it simple, I use the HomeKit bridge integration to expose the Home Assistant devices that I want in iOS. I don’t expose everything, though, some of the more advanced or obscure devices I purposely keep hidden in Home Assistant. It strikes a nice balance in my opinion.

i’m assuming you can do something similar with Google home, etc.

but like you said, you could always build your own dashboard from scratch if you wanted to.

Re: The era of open voice assistants

#267

Post by pimeys »

ijidak wrote: post #264
pimeys wrote: post #108

Earlier quoted context omitted.

I'm also very excited. I've had some ESP32 microphones before, but they were not really able to understand the wake word, sometimes even when it was quiet and you were sitting next to the mic. This one looks like it can recognize your voice very well, even when music is playing. Because... when it works, it's amazing. You get that Star Trek wake word (KHUM-PUTER!), you can connect your favorite LLM to it (ChatGPT, Cl…

I'm trying to understand. Is there an SDK I can use to enhance this? Or is this a package product? I'm really hoping it's the former. But I don't see any information about how to develop with this.

Yep, ESPHome SDK. It's all open source and well-documented:

https://esphome.io/

Some notable blog posts, docs and a video on the wake words and voice assistant usage:

https://community.home-assistant.io/t/on-device-wake-word-on...

https://esphome.io/components/voice_assistant.html

https://www.home-assistant.io/voice_control/create_wake_word...

https://www.youtube.com/watch?v=oSKBWtBJyDE

Re: The era of open voice assistants

#268

Post by snailmailman »

thfuran wrote: post #54
lokar wrote: post #44

Earlier quoted context omitted.

It’s a great project overall, but I’ve been frustrated by how anti-engineer it has been trending.

How so?

Im a different user- but I can say I’ve been frustrated with their refusal to support OIDC/oauth/literally any standard login system. There is a very long thread on their forums documenting the many attempts for people to contribute this feature.[0] The devs simply shut it down every time, with little to no explanation.

I run many self hosted applications on my local network. Homeassistant is the only one I’m running that has its own dedicated login. Everything else I’m using has OIDC support, or I can at least unobtrusively stick a reverse proxy in front to require OIDC login.

[0] https://community.home-assistant.io/t/open-letter-for-improv...

Edit: things like this [1] don’t help either. Where one of the HA devs threatens to relicense a dependency so that NixOS can’t use it, because… he doesn’t want them to? The license permits them to. Seemed very against the spirit of open source to me.

[1] https://news.ycombinator.com/item?id=27505277

Re: The era of open voice assistants

#269

Post by darkwater »

IgorPartola wrote: post #33
Jarwain wrote: post #7

I'm actually really excited for this! I noticed recently there weren't any good open source hardware projects for voice assistants with a focus on privacy. There's another project I've been thinking about where I think the privacy aspect is Important, and figuring out a good hardware stack has been a Process. The project I want to work on isn't exactly a voice assistant, but same ultimate hardware requirements Someth…

A group buy for an existing product makes sense. Want to buy a 24TB Western Digital hard drive? It’s $350. But if you and your 1000 closest friends get together the price can be $275. But for a first time unknown product? You get a lot fewer interested parties. Lots of people want to wait for tech reviews and blog posts before committing to it. And group buys being the only way to get them means availability will be…

There are two types of "group buy". The one that you illustrated, but also one not only focused on saving bucks but also helping small, independent makers/producers to sell their usually more sustainable or more private product (which is also usually more expensive due to the lack of economies of scale).

Re: The era of open voice assistants

#270

Post by djtango »

imiric wrote: post #213
gorbachev wrote: post #195

Earlier quoted context omitted.

Even the richest company in the world doesn't run unprofitable projects forever. Just see Killed by Google.

That depends on the company. There is precedent of large companies keeping unprofitable projects alive because they can make up for it in other ways, or it's good for marketing, etc. I.e. the razor and blades business model. Perhaps Echo/Alexa entice users to become Prime members, and they're not meant to be market leaders. We can only speculate as outsiders. My point is that claiming that a product of one the riches…

Just because they're rich doesn't mean that they can or will fund features like this if they can't justify the business case for it.

Amazon is a business and frugality is/was a core tenet. Just because they can put Alexa in front of LLMs and use GPU hours to power it doesn't mean that is the best reinvestment of their profits.

The idea of using LLMs for Alexa is so painfully obvious that people all the way from L3 to S Team will have considered it, and Amazon are already doing interesting R&D with genAI so we should assume that it isn't corporate inertia or malaise for why they haven't. The most feasible explanation from the outside is that it is not commercially viable especially "free" versus a subscription model. At least with Apple (and Siri is still painfully lacking) you are paying for it being locked into the Apple ecosystem and paying thousands for their hardware and paying eyewatering premiums for things like storage on the iPhone

Post reply on HN