# bjoernkarmann/project_alias

Alias is a teachable “parasite” that is designed to give users more control over their smart assistants, both when it comes to customisation and privacy. Through a simple app the user can train Alias to react on a custom wake-word/sound, and once trained, Alias can take control over your home assistant by activating it for you.

Repository: https://github.com/bjoernkarmann/project_alias
Canonical: https://ross.abutalabs.com/products/project_alias
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: machine-learning, classification, sound-synthesis, speech-recognition, hack, smarthome, alias, wakeword, raspberry-pi, microphone
Last push: 2020-04-05T18:36:58+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3032, "days_push": 2341, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1700, forks 98 (observed 2026-08-28T04:05:24.184874+00:00)

## What it is
Project Alias is an open-source Raspberry Pi-based device that acts as a 'parasite' on smart home assistants, letting users train custom wake words and commands while masking the assistant's built-in microphone with noise. It is configured through a local web interface and uses Pocketsphinx for wake-word detection.

## Use cases
- train a custom wake word for my google home
- block my smart speaker from always listening
- add custom voice commands to my home assistant
- make my smart assistant respond to a different name
- confuse my assistant's voice profiling with a different gender
- build a privacy layer over a smart speaker with raspberry pi

## When to choose
- you want custom wake words and commands on an existing smart speaker
- you care about microphone privacy and want to jam the built-in mic
- you want a DIY hardware project on a Raspberry Pi with a ReSpeaker hat

## When to avoid
- you want a production-grade, actively maintained voice assistant
- you need cloud-quality speech recognition or broad language support
- you don't want to assemble hardware or flash a custom SD card image

## Facets
- artifact type: application
- maturity: maintenance
- function: speech-recognition, machine-learning, audio-processing, security, privacy
- domain: iot, hardware, privacy, machine-learning
- platform: iot, python, embedded
- tags: wake-word, smart-home, voice-assistant, raspberry-pi, privacy-hack, pocketsphinx, custom-wake-word, parasite-device, linux

## Member repositories
- bjoernkarmann/project_alias (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.184874+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 2026-08-30T03:37:45.385938+00:00, confidence not recorded.
  - readme: https://github.com/bjoernkarmann/project_alias (fetched 2026-08-28T04:05:24.184874+00:00, sha d2defb4078c3)
- Data as of 2026-08-30T08:39:29.467469+00:00.