Rhino Speech-to-Intent
Unity Quick Start
Platforms
- Linux (x86_64)
- macOS (x86_64, arm64)
- Windows (x86_64)
- Android (5.0+, API 21+) (ARM only)
- iOS (11.0+)
Requirements
- Picovoice Account & AccessKey
- Unity 2017.4+ (Unity 2021.2+ for macOS arm64)
- Unity Build Support modules for desired platforms
Picovoice Account & AccessKey
Signup or Login to Picovoice Console to get your AccessKey
.
Make sure to keep your AccessKey
secret.
Quick Start
Setup
- Download and install Unity .
- Download and import the latest Rhino Unity package .
NOTE: For running Rhino on macOS arm64, use the rhino-*-Apple-silicon.unitypackage
version with Unity 2021.2+.
Usage
Create an instance of Rhino using either a pre-built context file (.rhn
) from the
Rhino GitHub Repository or a
custom context created with the Picovoice Console :
Start audio capture and intent inference with:
Once an inference has been made, the inferenceCallback
will be invoked and audio capture will stop automatically.
Release resources acquired by RhinoManager
with:
Custom Contexts
Create custom contexts using the Picovoice Console . Download the custom context file (.rhn
)
and place it in the StreamingAssets
folder of the Unity project. Pass the relative path (from StreamingAssets
) to the
RhinoManager.Create
constructor.
Non-English Languages
Use the corresponding model file (.pv
) to make inferences in non-English contexts.
The model files for all supported languages are available
on the Rhino GitHub repository .
Pass in the model file using the modelPath
input argument to change the language:
Demo
For the Rhino Unity SDK, we offer demo applications that demonstrate how to use the Speech-to-Intent engine on real-time audio streams (i.e. microphone input).
Setup
Download and import the latest Rhino Unity package .
Usage
- Open the Rhino Demo Scene (
Rhino/RhinoDemo/RhinoDemo.unity
). - Copy
AccessKey
from Picovoice Console into theACCESS_KEY
variable in RhinoDemo.cs - Play the scene in the editor or go to
File > Build Settings
and click theBuild and Run
button to compile and run the scene for the selected platform.
Resources
Package
API
GitHub
Benchmark
Further Reading
Video