Nicla Voice
Implement always-on speech recognition on the edge, with sensors that hear what you say and a neural processor to understand what you need.
Overview
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.
Key benefits include:
- Powerful processor with integrated Deep Neural Networks in a tiny form factor (22.86 x 22.86 mm)
- Integrated microphone, magnetometer and smart 6-axis IMU
- Onboard Bluetooth® Low Energy connectivity
- Add speech recognition capabilities to your projects
- Ultra-low power for 24/7 always-on sensor data processing
- Standalone when battery powered
- Compatible with Portenta and MKR products
Just say the word
Voice detection and voice recognition can change the way you interact with machines, systems and devices. With always-on sensors – courtesy of low power consumption – all you need is a wake word or trigger sound: no buttons to search for while you are driving, no interfaces to clutter your designs. And Nicla Voice not only hears everything, but understands what sounds mean: thanks to advanced neural processing, it can learn to interpret audio inputs such as passwords and commands.
Tiny but mighty
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 is particularly suitable for wearable products such as helmets and smart bands – also thanks to its long, battery-powered autonomy.
More than words
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.
Peace and quiet
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.
Need Help?
Check the Arduino Forum for questions about the Arduino Language, or how to make your own Projects with Arduino. If you need any help with your product, please get in touch with the official Arduino User Support as explained in our Contact Us page.
Warranty
You can find your board warranty information here.
Tech specs
Microprocessor | Syntiant® NDP120 Neural Decision Processor™ (NDP):
|
Microcontroller | Nordic Semiconductor nRF52832:
|
Sensors |
|
I/O | Castellated pins with the following features:
|
Interface |
|
Memory |
|
Dimensions and weight |
|
Operating temperature | 0° C to +85° C (32° F to 185°F) |
Power |
|
Connectivity |
|
Resources for Safety and Products
Manufacturer Information
The production information includes the address and related details of the product manufacturer.
Arduino S.r.l.
Via Andrea Appiani, 25
Monza, MB, IT, 20900
https://www.arduino.cc/
Responsible Person in the EU
An EU-based economic operator who ensures the product's compliance with the required regulations.
Arduino S.r.l.
Via Andrea Appiani, 25
Monza, MB, IT, 20900
Phone: +39 0113157477
Email: support@arduino.cc
Documentation
Learn more
Get Inspired
An intelligent device to track moves with responses during an interactive space with mapping, backlight, music and smart sculptures. This project makes use of a machine learning algorithm capable of tracking and detecting moves to identify associated gesture recognition through a microcontroller. Smart sculptures, lighting, music and video projection to trigger with each assigned gesture, creating a powerful AV experience highlighting the incredible potential of TinyML for the performing arts. This allows the corresponding media set Tiny ML in interactive to play when the right move was made because all these elements interact to create a new experience. This allows us to create Interactive installations, these sculptures use a combination of motors, sensors, and other electronics to create an immersive and interactive experience for the viewer. They may include projections, sound, and other sensory elements to create a complete experience.
With an array of onboard sensors, Bluetooth® Low Energy connectivity, and the ability to perform edge AI tasks thanks to its nRF52840 SoC, the Arduino Nano 33 BLE Sense is a great choice for a wide variety of embedded applications. Further demonstrating this point, a group of students from the Introduction to Embedded Deep Learning course at Carnegie Mellon University have published the culmination of their studies through 10 excellent projects that each use the Tiny Machine Learning Kit and Edge Impulse ML platform. Wrist-based human activity recognition Traditional human activity tracking has relied on the use of smartwatches and phones to recognize certain exercises based on IMU data. However, few have achieved both continuous and low-power operation, which is why Omkar Savkur, Nicholas Toldalagi, and Kevin Xie explored training an embedded model on combined accelerometer and microphone data to distinguish between handwashing, brushing one’s teeth, and idling. Their project continuously runs inferencing on incoming data and then displays the action on both a screen and via two LEDs. Categorizing trash with sound In some circumstances, such as smart cities or home recycling, knowing what types of materials are being thrown away can provide a valuable datapoint for waste management systems. Students Jacky Wang and Gordonson Yan created their project, called SBTrashCat, to recognize trash types by the sounds they make when being thrown into a bin. Currently, the model can three different kinds, along with background noise and human voices to eliminate false positives. Distributed edge machine learning The abundance of Internet of Things (IoT) devices has meant an explosion of computational power and the amount of data needing to be processed before it can become useful. Because a single low-cost edge device does not possess enough power on its own for some tasks, Jong-Ik Park, Chad Taylor, and Anudeep Bolimera have designed a system where