Digi-Key at Embedded World 2022 with Digi international

Digi SOM solutions provide a highly integrated hardware and software platform designed for rapid development and time-to-market, along with a full suite of tools and resources for scalability of design and ease of maintenance. With robust, industrial system-on-modules, integrated Digi TrustFence security, sophisticated open systems software and device management tools, Digi’s embedded solutions reduce total cost of ownership and help catapult OEMs to market success.

Digi ConnectCore Voice Control is a fully integrated and ready-to-use embedded speech recognition and voice control solution for any Digi ConnectCore enabled product. ConnectCore Voice Control provides a pre-trained 60,000-word language model, customisable vocabulary, customisable wake word, and text-to-speech (TTS) output, enabling zero-touch user interaction with the device.

The speech-recognition technology of ConnectCore Voice Control operates locally on the device at the edge and does not require an Internet connection. This makes it particularly suitable for applications that must function without Internet access, applications that require real-time response to voice commands, or have special data protection requirements. It recognises natural speech, comparable to cloud-based speech recognition services such as Amazon’s Alexa or Google Speech-to-Text Services. Additionally, it is available in 30 national languages for global product deployment, and Digi ConnectCore Voice Control is a fully integrated and ready-to-use embedded speech recognition and voice control solution for any Digi ConnectCore enabled product.

With cloud-independent functionality, Digi ConnectCore Voice Control provides real-time voice recognition capabilities from any location, and features privacy by design. Add text-to-speech synthesis into Digi ConnectCore devices with the embedded voice recognition software to enhance value and capability in industrial IoT, medical, smart city and other applications. It does not require hardware-based AI/ML accelerators or a neural processing unit (NPU) to operate, enabling you to add voice-processing capabilities without additional hardware costs.