[Brian] sent in this writeup on his voice controlled home automation system. Starting with the Microsoft SAPI, a voice recognition system, he programmed some basic home automation. In a move that makes this project decidedly more awesome, he decided to build a physical representation of his automation system. This disembodied head is “Stephanie”. She responds to her name, has an articulated jaw that moves with the syllables in the words, and even ejects her “brain tray” on command. We want one.
There is lots of information on his site about the circuitry involved, as well as source code and a video. You can see the video after the break.
[youtube=http://www.youtube.com/watch?v=DqCXbP85oX0]
Yeah this is awesome but I personally couldn’t handle the face.
Imagine sleeping next to that…
I have that same Spiderman poster!
id have to give it a guys name, id be worried id ask for the door to open or lights off to get the response “no, not till u say your sorry for making me from microsoft”……but this thing is really cool, i want one for my flat, would mount it in the corner and put sercurty cams in the eyes aswell, maby a ir detection system aswell so it can tell what room your in
a cool idea, a life size version using robotics for movement would be even cooler, because then i dont have to get off my arse and open the door!!!!!!
Man!!! I am totally gonna do this-
like, to my whole freakin’ house!!
Oh good god…
And I jsut finished re-watching the Animatrix. Thanks al lot for creeping the hell out of me. :p
Still cool as well though, keep up the good work!
You know, of course, this thing is going to kill you one day..
Hey dude this is awsome, ive made up my own software after seeing how it could be done. All working but i was wondering how you got ‘Stephanie’ to mouth each syllable (ie the code not the hardware). any info you could shed would be great, cheers dude
I wasn’t expecting much when I saw the headline but after watching the video…that is AWESOME.
I could just imagine putting these all around the house to speak the current status of things – would be creepy but cool.
Excelent… creepy… awesome…disturbing… a lot of favorite thinks :p. Really impresive, I asume that robot is a mini pc whit face in simply words but the controle voice is impresive. I give you 10 start… wait… this is not youtube :p
@Raymond
Sorry it’s about a year late… the part of the code that makes the mouth move with syllables is in the ‘Viseme’ event of the SpVoice object. SAPI calls this even for various sounds. It passes a parameter, CurrentVisemeId, that corresponds to the sound the voice is currently making. Sounds 1 through 11 are vowel-y (ae, er, ow, aw as opposed to sh, th, v, g), so if the CurrentVisemeId is >0 and <=11, the program sends a command to the head to pulse the mouth motor
MS SAPI sucks. simon-project.org is way better for that and with a bt dongle you get better results.
Actually, with a bit of animatronics and some more advanced coding….this could become something pretty amazing.