Picovoice/porcupine
On-device wake word detection powered by deep learning
Supports custom wake word model training via Picovoice Console and detects multiple keywords simultaneously with zero added runtime cost. Built on lightweight deep neural networks optimized for resource-constrained devices, it runs efficiently on microcontrollers, Raspberry Pi, mobile platforms, and browsers with SDKs across Python, Java, .NET, Flutter, React Native, iOS, Android, and WebAssembly.
4,743 stars. Actively maintained with 23 commits in the last 30 days.
Stars
4,743
Forks
572
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 14, 2026
Commits (30d)
23
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Picovoice/porcupine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
MycroftAI/mycroft-precise
A lightweight, simple-to-use, RNN wake word listener
arcosoph/nanowakeword
A lightweight, open-source, and intelligent wake word detection engine. Train custom,...
mozilla/DeepSpeech
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run...
OAID/cortex-m-kws
Cortex M KWS example with Tengine Lite.
vineeths96/Spoken-Keyword-Spotting
In this repository, we explore using a hybrid system consisting of a Convolutional Neural...