Picovoice/porcupine
On-device wake word detection powered by deep learning
Porcupine helps product developers add always-listening voice commands to their applications and devices. It takes spoken audio as input and detects specific 'wake words' or phrases, then outputs a signal indicating that the command has been spoken. This allows engineers to build interactive voice-enabled products that respond to simple voice cues.
4,743 stars. Actively maintained with 35 commits in the last 30 days.
Use this if you need to embed a highly efficient and accurate wake word detection feature directly into a device or application, enabling it to respond to specific spoken commands without an internet connection.
Not ideal if you need to process complex natural language commands or conduct full speech-to-text transcription.
Stars
4,743
Forks
572
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 14, 2026
Commits (30d)
35
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...