On-device wake word detection powered by deep learning
This is a list of interesting papers and projects about TinyML.
OpenClaw voice assistant app for Android - Wake word activation & system assistant integration
wake word engine benchmark framework
A lightweight, wake word detection engine. Train custom, high-accuracy models with minimal effort.
Create any wake word, deploy on any device and operating system.
Wake word detection with custom phrases without model training
GPT powered personal voice assistant, immitates GLaDOS from Portal.
Use Porcupine wake word to trigger a voice assistant pipeline in Home-Assistant
OVOS voice satellite for HiveMind — full on-device voice stack (microphone, VAD, wake word, STT, TTS)
Speech2Speech-AIAssistant; A lightweight, offline-capable voice assistant that listens for a wake phrase, converts speech to text, runs local or API-based intent handling, and replies with natural-sounding TTS. Built for quick local deployment, it supports configurable wake words, microphone I/O, and easy integration with custom actions or LLMs.
Key word/wake word detection with espressif esp32s3
轻量离线关键词识别 / 唤醒词识别。ONNX 通用格式，模型 < 1MB，推理 < 10ms，支持 Android、ESP32、Linux、Web 全平台。不联网，不耗流量
Cross-platform desktop AI companion — Live2D character, always-on wake word, continuous voice chat, dreaming long-term memory, autonomous behavior, and built-in tools (web search / weather / reminders). Electron + React + TypeScript.
Voice interface for OpenClaw with speaker recognition, voice-gated security, real-time barge-in, and multi-provider streaming TTS
Local-first personal wake-word training with ONNX export.
AI voice-activated girlfriend assistant with wake word detection, speech recognition, and animated GIF overlay. Powered by Liebea Model, Whisper.cpp, and Edge-TTS.
Hands-free voice activation for VS Code, Cursor, and compatible editors. Route voice commands to any AI assistant or editor feature.
Add a description, image, and links to the wake-word topic page so that developers can more easily learn about it.
To associate your repository with the wake-word topic, visit your repo's landing page and select "manage topics."