171–180 of 468 posts
Please, please, please be a completely open, extensible platform... I want to be able to control my Apple TV with my Google Home device. I want to be able to control my Phillips Hue and LiFX bulbs. I want to be able to build my own custom home automation server endpoints and point my Google Home commands at them. I want to be able to remote start my car with a voice command. I want to be able to control my Harmony re…
When I was younger, I dreamed of something like this. Voice control for my home! A Star Trek computer that I can interact with conversationally! I just say what I want and it happens! Now, I just see an internet-connected microphone in a software black box which I can only interpret as a giant frickin' security liability. I want this, but unless it's open source top-to-bottom, I won't ever actually put one in my home…
You probably have on in your pocket already, is the thing. (I agree though, I don't want this in my house, and I turned off the "Ok Google" functionality on my phone)
I'm not at all happy with the trade-off any more.
I've got a tablet, both cameras taped over. Killing the mics would be a Good Thing.
Sigh.
"[...] and manage everyday tasks"
What exactly do we want to automate at home? I think this whole home automation and smart home stuff is complete bullshit. Obviously there are some nice things, like "play me song xyz", but IMHO it is completely oversold. There are just not that much things to automate at home.
And this does not mean that I think 640K are enough memory for everyone.
This project relies on that fact.
Earlier quoted context omitted.
About as much as you can buy Amazon Echo or Google Home actually. At least IBM makes very clear what the usage conditions of Watson are, and it's fully extensible.
So you're saying IBM offers something that could be turned into an Echo-like system? Do you have any links on how to do that? I'm interested.
--
1. http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercl...
2. It's rather amusing, but IBM has a ton of really smart people making cool stuff, then a ton of marketing people seemingly pitching at someone other than the target audience and making it sound dumb. If you can wade through the marketing BS, Watson is very cool.
A company that makes money by collecting and selling access to personal information about people is offering to put a microphone in your home. If you need a product like this, for the sake of your privacy, buy an Echo.
Lets stop this nonsense. They don't sell access to your personal information. There is nowhere that I can buy your personal information from google. What they sell is access to your attention. When advertising, I'm looking for people that match these characteristics, and what I'm purchasing is the possibility to show you an ad if you match certain criteria.
You are also assuming that Google's policy will never change, Google's assets will never end up for sale, etc.[1]
Obviously, we weight these things differently. But calling it nonsense demonstrates either contempt for those you disagree with or a lack of thought on the matter.
[1] Sure, looks unlikely at the moment. But unless you think it is going to rival the Catholic Church for longevity, it is worth thinking about. The average corporate lifespan in the US is 27 years.
Earlier quoted context omitted.
I have only two wishes: > Please, please, please be a completely open, extensible platform... That's one. The second one is, please make it self-hosted. No cloud bullshit. I know I'll probably never live to see the second one coming true.
How would you make it self-hosted without making it suck? High quality voice recognition in a small box doesn't seem to be a thing that's even remotely possible today, let alone the query processing and knowledge database that comes with it. You could build this on a pi with a mic, speakers, some foss stt and tts engines and some basic training data. But it'll suck.
A Pi, though, couldn't do well at all, just like you said. If I wanted to build a system like this for myself, I would target an HTPC form factor.
edit: Another possibility, which was explored elsewhere in this thread, would be to keep the listening device "thin", but have the ability to offload the processing to a machine in my LAN instead of one the "cloud".
Why wasn't this done under Nest?