Overview
Speech Recognition Engine is an extensive software library that allows anyone to quickly and easily interact with devices and machines by talking. It was developed by Cyberon, the worldwide leader in speech recognition, with ease of use and compatibility in mind for instant integration into new applications or existing solutions.
Speech Recognition Engine is compatible with multiple Arduino boards and with the Arduino IDE and requires no additional hardware, software or internet connectivity.
Its AI/ML engine understands commands defined through text input in 40+ languages – regardless of the speaker’s actual voice, tone or accent. This means multiple wake-up words and sequences can be quickly configured, and there is no need to retrain for different users.
Ready to test it?
Get started with a free trial license here.
Do you already have a voucher? Register it here.
Key benefits include:
- Powerful library with integrated AI/ML engine for phoneme-based modeling
- Recognition of multiple wake-up words and sequences of commands
- No vocal training required, commands configurable through text input
- Support for 40+ languages, independent from accent variations
- One configuration for multiple speakers, without retraining
- Recognition on the edge, no need of additional HW/SW or connectivity
- Suitable for noisy environments
- Expand existing projects with speech recognition capabilities
- Compatible with multiple Arduino Nano and Portenta products
- Compatible with Arduino IDE and Arduino CLI
Industrial-grade speech recognition
Speech Recognition Engine was developed in partnership with Cyberon, a leading embedded speech solution provider, to be part of Arduino Pro’s growing ecosystem of advanced professional solutions.
Forget the training period
Your next smart device can immediately understand every major language in the world, regardless of the speaker’s tone or accent. How? Speech Recognition Engine uses text input to define voice commands, translating them into instant results.
Infinite applications
Speech Recognition Engine is ideal for industrial and building automation applications such as hands-free control of machinery, equipment and devices of all kinds, but also for any situation where multiple people may need to interact with objects using their voice: information kiosks, vending machines and lockers, smart beds in hospitals, emergency call systems and more.
Hear, hear!
Speech Recognition Engine helps machines and devices understand multiple users without requiring specific training for individual voices. Also, it’s able to listen to the person speaking to it while filtering background noise, making it suitable for busy or crowded environments.
Need industrial-grade speech recognition? We hear you!
Refund Policy
Price is not refundable.
Arduino Speech Recognition License is permanently valid on the associated product but, due to the automated way that orders are processed and fulfilled, once the Voucher order is processed and the Voucher code is issued and provided, this cannot be canceled. Exceptions are handled on a case-by-case basis and only granted when emergency or extenuating circumstances exist.
Tech specs
| NUMBER OF | RECOG. TIMES | DELAY IN TRIGGER MODE** | HARDWARE BINDING*** | |||
| PLANS | DATASET* | TRIGGERS | COMMANDS | |||
| Free Trial | 1 | 1 | 20 max | 50 | 20s | Yes |
| Cyberon License | 1 | 1 | 20 max | Unlimited | No | Yes |
Voucher Type Selection
| Core Type | ARM® Cortex® M4/M7 | ARM® Cortex® M0 |
| Compatible Product | Nano 33 BLE Sense Rev2 | Nano RP2040 Connect |
| Portenta H7 | ||
| Nicla Vision |
*The dataset cannot be changed after deploying it on the board
**Delay between entering the Trigger Mode and the recognition of the Wake-up Word
***The license is bound to the serial number of a single Arduino board
Learn more
Get Inspired
Simple Code that allows you to solve the 2D flow equation for a flat plate Boundary Layer!!
Who doesn’t want to explore underwater? To take a journey beneath the surface of a lake or even the ocean? But a remotely operated vehicle (ROV), which is the kind of robot you’d use for such an adventure, isn’t exactly the kind of thing you’ll find on the shelf at your local Walmart. You can, however, follow this guide from Ranuga Amarasinghe to build your own ROV for some aquatic fun. Amarasinghe is a 16-year-old Sri Lankan student and this is actually the second iteration of his ROV design. As such, he's dubbed it “ROV2” and it appears to be quite capable. All of its electronics sit safely within a 450mm length of sealed PVC tube. That mounts onto the aluminum extrusion frame structure that also hosts the six thrusters powered by drone-style brushless DC motors. ROV2’s brain is an Arduino Mega 2560 board and it drives the BLDC motors through six electronic speed controllers (ESCs). It receives control commands from the surface via an umbilical. The operator holds a Flysky transmitter that sends radio signals to a receiver floating on the water. An Arduino UNO Rev3 reads those and then communicates the motor commands to the Mega through the tethered serial connection. That limits the maximum length of the tether to about 40 meters, which subsequently limits the maximum operating depth. With the specified lithium battery pack, ROV2 can traverse the depths for 30-45 minutes. And when equipped with the 720p FPV camera, pilots can see and record all of the underwater action.
FAQs
How may I test the Arduino Speech Recognition Engine?
In order to test the Arduino Speech Recognition Engine, you have the possibility to:
- Start a free trial here with the limitations reported in the Tech Specs.
- Purchase the right voucher for your board here.
How can I activate my voucher?
You will get your voucher by email. Once received, you need to register it at this link to start developing your own custom voice recognition model. Check this documentation to learn more.
Which are the main differences between the Free trial and the Cyberon License activatable with the Voucher?
Check the reported Tech Specs to compare the two licenses. If you would like to unlock all the limitations, feel free to contact us.
How can I change the model I have already deployed on my board?
Deployed models are not customizable, but you can always purchase an additional voucher to generate a new model for the same hardware.