Voice/motion control

[alexyak]

Besides the ability to recognize the speech you also need to start the recognition with annyang. There should be an always listening component that reacts on a key word and starts annyang.

[tyho]

@alexyak at the moment annyang is always lisening. If i come back in à couple of hours i can still make my commands.

[alexyak]

@tyho You will quickly run out of quota if it listens continuously.

[alexyak]

It looks like this guy has figured it out:

http://docs.smart-mirror.io

[tyho]

@alexyak true, hè got à separate speech module for unlock annyang. Still you get max 50 commands a day. If i use annyang in chrome i got unlimited commands. So i guess it has something to do with api key what is burned into chrome browser. Maybe there is a way to use this api key.

[tyho]

i can’t get it to work with the sphinx package. simply cuz i am not smart enough -_-
I get pocketsphinx regognize my words but not in the js envirement and i don’t get response out of it.

I think i just use “blather” for the time being to control my monitor on and off. I hope someone make a voice module soon. ^^

[tyho]

@michmich @KirAsh4 running a simple html with the following code gets me more results then 50. and also run more then a hour already.

I run it with https in chrome and get:

has this something to do with chrome that there is no limit?

[KirAsh4]

What’s the HTML/CSS output look like? That’s usually the first thing to look at when stuff like this happens and it’s not the expected result.

[tyho]

nvm i already see it depends on the chrome api key and not the chromium…

What about cloud voice api?

[KirAsh4]

FYI, setting 'TEXTAREA' size works fine in Chrome, both by using 'cols' and 'rows' as well as using CSS styling 'width' and 'height'.