Porcupine Wake Word
Node.js Quick Start
- Linux (x86_64)
- macOS (x86_64, arm64)
- Windows (x86_64)
- NVIDIA Jetson Nano
- Raspberry Pi (2, 3, 4)
Looking to run Porcupine in-browser?
- Picovoice Account & AccessKey
- Node.js 10+
Picovoice Account & AccessKey
Signup or Login to Picovoice Console to get your
Make sure to keep your
Create an instance of
Porcupine that detects the included built-in wake words
sensitivities of 0.5 and 0.65, respectively.
Pass in frames of audio to the
Release resources explicitly when done with Porcupine:
Create custom keywords using the Picovoice Console. Download the custom wake word
.ppn) and create an instance of Porcupine by passing in the path to the keyword file.
Use the corresponding model file (
.pv) to detect non-English wake words.
The model files for all supported languages are available
on the Porcupine GitHub repository.
Pass in the model file to change the detection language:
For the Porcupine Node.js SDK, we offer demo applications that demonstrate how to use the Wake Word engine on real-time audio streams (i.e. microphone input) and audio files.
Install the Porcupine demo package:
This package installs command-line utilities for the Porcupine Nodejs demos.
--help flag to see the usage options for the demo:
Ensure you have a working microphone connected to your system and run the following command to detect the built-in keyword
For more information on our Porcupine demos for Nodejs, head over to our GitHub repository.