# dscripka/openWakeWord

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

Repository: https://github.com/dscripka/openWakeWord
Canonical: https://ross.abutalabs.com/products/openwakeword
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2025-12-30T16:47:27+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 59, release rhythm 8, longevity 100
- inputs: {"age_days": 1558, "days_push": 246, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2702, forks 326 (observed 2026-08-28T04:07:11.454362+00:00)

## What it is
openWakeWord is an open-source Python library for detecting wake words (or phrases) in streaming audio, with pre-trained models for common phrases. It focuses on performance and simplicity, supporting both ONNX and TFLite inference runtimes.

## Use cases
- detect a wake word to trigger a voice assistant
- add always-listening voice activation to a home automation setup
- run keyword spotting locally on a microphone stream
- train a custom wake word model for a specific phrase
- build voice-enabled applications without cloud speech APIs

## When to choose
- you need lightweight, on-device wake word detection with minimal dependencies
- you want pre-trained models for common phrases that work in real-world environments
- you want to train a custom wake word model quickly using provided notebooks

## When to avoid
- you need full speech-to-text transcription rather than wake word detection
- you require cloud-scale speaker verification or multi-language production support

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, audio-processing, llm-inference
- domain: speech-processing, machine-learning
- platform: python, windows, cross-platform
- tags: wake-word-detection, voice-assistant, onnx, tflite, pre-trained-models, keyword-spotting, audio, linux, macos

## Member repositories
- dscripka/openWakeWord (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.454362+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:57.552244+00:00, confidence not recorded.
  - readme: https://github.com/dscripka/openWakeWord (fetched 2026-08-28T04:07:11.454362+00:00, sha ee57007865a8)
  - registry_pypi: https://pypi.org/pypi/openwakeword/json (fetched 2026-08-29T09:58:58.053463+00:00, sha 17b864344042)
- Data as of 2026-08-30T08:39:29.467469+00:00.