Picovoice/porcupine

On-device wake word detection powered by deep learning

67
/ 100
Established

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.

voice-user-interface embedded-systems IoT-development hands-free-control voice-assistants
No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

4,743

Forks

572

Language

Python

License

Apache-2.0

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.