porcupine and mycroft-precise

Given that both tools are on-device wake-word detection libraries powered by deep learning and capable of standalone operation, they are **competitors** offering alternative implementations for the same core task, where one would typically choose either the Porcupine engine for its higher star count potentially indicating more mature deep learning or Mycroft Precise for its RNN approach and active download count.

porcupine
70
Verified
mycroft-precise
64
Established
Maintenance 23/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 0/25
Adoption 14/25
Maturity 25/25
Community 25/25
Stars: 4,743
Forks: 572
Downloads:
Commits (30d): 23
Language: Python
License: Apache-2.0
Stars: 959
Forks: 246
Downloads: 84
Commits (30d): 0
Language: Python
License: Apache-2.0
No Package No Dependents
Stale 6m No Dependents

About porcupine

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.

About mycroft-precise

MycroftAI/mycroft-precise

A lightweight, simple-to-use, RNN wake word listener

Uses a single GRU (Gated Recurrent Unit) architecture for real-time audio stream processing, with pre-trained models available from a community dataset or trainable on custom wake phrases. Integrates with the Mycroft ecosystem via Python wrapper (`precise-runner`) while remaining framework-agnostic, supporting both x86_64 and ARM (Raspberry Pi) Linux platforms with binary or source installation options.

Scores updated daily from GitHub, PyPI, and npm data. How scores work