@Cato exactly my point. We already live “in the future” how all these campaigns promise :)

Another one: “MagicMirror² has an extensive documentated API.”
It should probably be “MagicMirror² has an extensively documented API.”

Very nice!

@wjdw87 The links are on the Youtube page

There’s another option to use a cloud service from Microsoft https://www.microsoft.com/cognitive-services/en-us/face-api. It should be enough to have just one good picture of your student uploaded to the server. I’ve got a basic module working that uses these api’s, but it’s not at the stage that I can publish it for everybody yet.

-Alex

Sorry, guys, the problem should be fixed now. Just pull the latest.

This is all nice and dandy but configuring and installing all of these dependencies and then making this run is really fragile process. On a top of that it seems like RPI hardware is not really capable of running this. So a few days ago I’ve got Amazon’t Alexa device - Dot and spend sometime connecting it to the MM on RPI and it works very well. (Voice recognition, passing commands, parameters, etc…)
So essentially we are bypassing all of this goo that these guys put together such as Speech AI, Voice Reco, TTS and connecting the result to MM.

I think using https://snowboy.kitt.ai is the best approach right now for detecting a hot word and then continuing with the google one (annyang). The same way the guy at the http://docs.smart-mirror.io has done it.

@djsunrise19 It looks like their iPhone app doesn’t support notifications which is understandable due to restrictions Apple has for ability to hook into global notifications on the device.

@Cato How hard it would be to add the code to actually play the music on the RaspPi?