The 22.86 x 22.86 mm Nicla Voice allows for easy implementation of always-on speech recognition on the edge, because it integrates Syntiant’s powerful NDP120 Neural Decision processor to run multiple AI algorithms, leveraging bio-inspired, advanced machine learning to automate complex tasks. Nicla Voice comes with a comprehensive package of sensors: in addition to its microphone, it features a smart 6-axis motion sensor and a magnetometer, making it the ideal solution for predictive maintenance, gesture/voice recognition and contactless applications.

Nicla Voice offers onboard Bluetooth® Low Energy connectivity to easily interact with existing devices, and is compatible with Nicla, Portenta and MKR products. Finally, its ultra-low power consumption makes 24/7 always-on sensor data processing possible, with the option of battery-powered standalone operation. Small enough to fit into wearables or retrofit existing machinery, enabling AI yet requiring minimal energy: Nicla Voice is the “impossible” combination that makes voice recognition on the edge possible – and easier than ever.

The Nicla family features Arduino Pro’s smallest form factor to date. This means Nicla Voice can easily be used to upgrade or retrofit existing machines and systems, and it is particularly suitable for wearable products such as helmets and smart bands – also thanks to its long, battery-powered autonomy.

Nicla Vision can handle multiple applications simultaneously to recognize different speakers, pick up on multiple wake-up words and run keyword spotting at the same time. But there’s more than voice commands out there, of course. Nicla Voice can be trained to identify noisy bearings that require maintenance, glass shattering or intruders trying to enter, and more.

Nicla Voice lets you tune out in complete safety: integrated into smart headphones, it offers enhanced audio quality with echo-cancellation and noise-suppression features that allow users to focus on their job, spare their ears from loud industrial environments, yet still be warned immediately if an alarm sound is detected.