custom-wake-word

Here are 3 public repositories matching this topic...

voicute / onnx-wakeword

Offline keyword spotting & wake word engine. ONNX format, model <130KB, inference <10ms. Runs on Android, ESP32, Linux, Web. No cloud, no data usage.

android offline esp32 voice-control keyword-spotting voice-assistant onnx kws tflite edge-ai wake-word custom-wake-word

Updated Aug 24, 2026
C

lgpearson1771 / openwakeword-trainer

Star

Train custom wake word models with openWakeWord. A granular 13-step pipeline with compatibility patches for torchaudio 2.10+, Piper TTS, and speechbrain. Generates tiny ONNX models (~200 KB) for real-time keyword detection — like building your own "Hey Siri" trigger. WSL2/Linux + CUDA required.

python text-to-speech deep-learning speech-recognition speech-to-text keyword-spotting voice-assistant wake-word-detection onnx on-device training-pipeline edge-ai audio-augmentation wsl2 speechbrain openwakeword piper-tts wake-word-training custom-wake-word

Updated Feb 13, 2026
Python

alfiedennen / microwakeword-trainer

Star

Train custom wake words for Home Assistant + ESPHome (M5Stack Atom Echo, Voice PE) via a single self-driving Colab notebook. Bug-fixed wrapper around kahrendt/microWakeWord with all gotchas patched.

esp32 smart-home colab home-assistant voice-assistant wake-word-detection tensorflow-lite esphome on-device-ml m5stack-atom-echo wake-word piper-tts custom-wake-word micro-wake-word nabu-casa

Updated Apr 26, 2026
Python

Improve this page

Add a description, image, and links to the custom-wake-word topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the custom-wake-word topic, visit your repo's landing page and select "manage topics."

Learn more