Rhino - iOS API

Speech-to-Intent Engine
Domain Specific NLU
Offline NLU
Local Voice Recognition
iOS
Swift
C

This document outlines how to integrate Rhino Speech-to-Intent engine within an iOS application.

Prerequisites

Rhino is implemented in ANSI C and is shipped as a precompiled library accompanied by corresponding header file. To integrate within an iOS application the following items are needed

Precompiled library
Header file
The model file. The standard model is freely available on Rhino's GitHub repository. Enterprises who are commercially engaged with Picovoice can access compressed and standard models as well.
Context model file for your use case. A set of freely-available context files can be found on Rhino's GitHub repository. Enterprises who are engaged with Picovoice can create custom NLU models using Picovoice Console.

Integration

The RhinoManager class manages all activities related to creating an input audio stream feeding it into Rhino's library, and invoking a user-provided detection callback. The class can be initialized as below

let modelFilePath: String = ...
let contextFilePath: String = ...
let onInferenceCallback: ((Inference) -> Void) = {
    // detection event callback
}
 
let manager = RhinoManager(
    modelPath: modelFilePath,
    contextPath: contextFilePath,
    sensitivity: 0.5,
    onInferenceCallback: onInferenceCallback);

when initialized, input audio can be processed using manager.process().