The overwhelming majority of people on the planet can understand one another without one bit of Internet traffic involved. Now, the Arduino gets that same ability. Audeme’s new MOVI Arduino shield is a voice recognition system that is not cloud-based and uses 200 customisable sentences. It is said to be ‘Siri-like’, meaning it will recognize full sentences and has a 2GB internal dictionary. It can be programmed to identify almost any complete English sentence and build a dialogue system to change its vocabulary. So now you can add “full sentence recognition capability” to an Arduino project with no Internet access required.

MOVI is stackable, with connections from the header pins and consumes under 3 watts.

The device, culminating from a Kickstarter campaign last year, will respond in the same way to a repeated sentence every time, no matter who is talking to it, while its programmable ‘call sign’ means users can personalize the device to their project.