Keyword Spotting Python Packages

pvporcupine

On-device wake word detection powered by deep learning

spokestack

Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.

precise-runner

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

nanowakeword

A lightweight, wake word detection engine. Train custom, high-accuracy models with minimal effort.

heed-wakeword

Tiny, Apache-2.0 wake-word detection you train yourself and run on-device in Python, the browser, and on mobile.

pvporcupinedemo

On-device wake word detection powered by deep learning

tinykw

A lightweight keyword spotting engine for Wake word detection and Voice commands

local-wake

Wake word detection with custom phrases without model training

violawake

Open-source wake word SDK — production TemporalCNN model, 8-phase training pipeline, ONNX inference, Python-first. The open alternative to Porcupine.

kikita-wake-word-runtime

Offline wake-word detection and two-stage verification for self-contained .kww models.

ppnrespeakerdemo

On-device wake word detection powered by deep learning

mycroft-precise

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

wav2aug

A general purpose task-agnostic speech augmentation policy

prob-phoc

Probabilistic relevance scores from PHOC embeddings

voxrt-kws

On-device 14-way keyword spotter for Linux x86_64 + aarch64 — one glibc-2.17 .so behind Python (PyPI), Node.js (npm), Go (go get), C / C++ (tarball + CMake). Streaming Conformer, RTF 1 % on WSL AVX2, 32 % on Pi Zero 2 W NEON. Same runtime as voxrt-kws-{android,ios} (upcoming).

liant-precise

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

ovos-ww-plugin-nyumaya

mycroft wake word plugin for nyumaya v1.0.0