83 private links
An AI assistant - not entirely sure what the difference to e.g. MyCroft is - but seems a little newer, coming along well. Can be integrated with a variety of TTS and STT services, and skills created for it
How to track your own position with GPS and use the data in interesting ways -
I am especially fond of the 'magic clock' pointing to your current location (Home, Travelling, Shopping, Pub, ...) which strongly reminds me of Harry Potter wizardry. Put it in a nice enclosure and it's a really neat thing for home.
Very neat new TTS engine, works in a wide variety of languages (e.g. English UK/US, German, Afrikaans) and with different inflections and voices.
Also works locally and (once the generator is downloaded the first time) super fast (on my pc takes around 10 seconds for generating a minute of speech in German). Since you will usually have shorter speech snippets will work even faster.
Can be used in client/server setup, through the local cli or as part of the mycroft engine. Neat!
A blog entry of how somebody got access to an echo and reprogrammed it with his own command interface instead of Alexa.
Very advanced assortment of pre-trained and trainable voice commands. Embeds perfectly in unix pipe flows.
This seems like a real interesting project to glue words and intents together as soon as a voice snippet is available.
I am not sure if it does wake word detection on its own.
Here's how I used Ansible to make my Mycroft AI project work smoothly with my Raspberry Pi.
A versatile and extensible platform for home and life automation with hundreds of supported integrations - GitHub - BlackLight/platypush: A versatile and extensible platform for home and life automation with hundreds of supported integrations
Seems really interesting, like a lighter-weight, more programmatic alternative to e.g. HASSio.
Has a lot of plugins and connections and the blog is very inspiring.
Using some (simple) machine learning to create a really robust smart home presence detection.
Seems like a fun little idea and, combined with e.g. phone mac address and wi-fi signal strength could even identify specific people.
Ready-made stack with installation scripts, making use of docker to install a fully working and nicely integrated stack of containers on your Pi.
Adds additional niceties (like turning off swap, writing logs to memory) that improve Pi performance (and life-time of SD cards) - most of which can be adapted reading through the source.
Especially interesting for things like NodeRED which are not just interesting for IOT.
NEW Stack migrated here: https://github.com/SensorsIot/IOTstack
Post with 101 votes and 145435 views. Shared by mxmln23. DIY SpotifyDevice
Setting up WLED on ESP8266
WLED library gets native Home Assistant API integration. This post walks you through everything you need to get up and running.