OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Porcupine

Porcupine is Picovoice’s developer library for on-device wake-word detection using deep learning. It detects one or a few static voice commands so an application or device can activate a hands-free function or begin a speech-processing pipeline.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Porcupine — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Porcupine when an application needs to listen for one or a few static voice commands. For complex, naturally spoken domain-specific commands, the repository points to Rhino Speech-to-Intent.

Who it is for

  • Developers adding wake-word activation to voice-enabled applications or devices.
  • Teams building hands-free controls that react to a small set of spoken trigger phrases.

Documented uses

  • Detect a wake word in audio processed on-device.
  • Trigger an application or device control with a spoken phrase.
  • Use keyword detection to initiate a later speech-processing stage.
Before you choose

Requirements & limits

  • The repository lists SDKs and demos across mobile, web, desktop, server-side and microcontroller environments.
  • The README lists nine supported languages and says additional languages are available to commercial customers on a case-by-case basis.
  • The documented Python microphone demo requires an access key and working microphone.
  • The project repository identifies an Apache-2.0 license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the Python microphone demo

Use the documented Python demo to listen for the Porcupine wake word and print detections.

Before you start

  • Python demo package installed with pip3.
  • A working microphone connected to the device.
  • A Picovoice access key.

Steps

  1. Install the demo package with sudo pip3 install pvporcupinedemo.

  2. Run porcupine_demo_mic --access_key ${ACCESS_KEY} --keywords porcupine in a terminal, supplying the access key.

Expected outcome

The demo processes microphone audio in real time and outputs when it detects the Porcupine wake word.

Guide limitations

  • This documents a Python microphone demo, not the steps for integrating the library into another application.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Picovoice/porcupine · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

Rhino Speech-to-Intent — Picovoice’s README points to Rhino for understanding complex, naturally spoken commands within a specific domain.

Picovoice platform — The README points to the broader platform for creating more expansive voice experiences.