Rhino
Rhino is an on-device speech-to-intent engine from Picovoice that infers a spoken command's intent and slot values directly, in real time, for a defined set of voice commands.
Rhino is Picovoice's Speech-to-Intent engine. Instead of transcribing speech to text and then parsing it, it infers intent directly from a spoken command within a defined context of interest, returning a structured result such as an intent name and slot values, for example extracting a beverage, size and number of shots from a coffee order.
It runs on-device using deep neural networks trained in real-world environments, and is built to be compact and computationally efficient for constrained devices. It is cross-platform, running on Arm Cortex-M, STM32 and Arduino boards, Raspberry Pi, Android, iOS, desktop operating systems, and in the browser via Chrome, Safari, Firefox and Edge. SDKs are available for Python, .NET, Java, Flutter, React Native, Android, iOS, Web and Node.js, and for C.
Developers define and train their own custom voice-command contexts using the Picovoice Console. It supports several languages including English, Mandarin, French, German, Italian, Japanese, Korean, Portuguese and Spanish.