Runtime
Python 3.11+
The whole stack runs on modern Python. A virtualenv keeps it tidy.
// Get started
Up and running in a few commands.
A one-line installer is on the way. Until then — and any time you want full control — the manual path below takes about five minutes.
Linux quick install · coming soon
$ curl -fsSL https://kenzy.dev/install.sh | bash
// installer is in the works — it will pull from GitHub and bootstrap a node. A pip install kenzy package is planned too. For now, use the manual setup below.
On a Pi / Debian
PortAudio
sudo apt-get install libportaudio2 portaudio19-dev for the room node's audio.
Optional keys
Bring your own
OpenAI for hosted TTS/LLM, Home Assistant for smart-home control. Go fully local and you need neither.
01 Manual setup
Install the pieces you need.
Every service is an optional extra. Put the lightweight node on each room device and the rest on a server — or install everything on one box to start.
Step 1 · Get the code
Clone & create a virtualenv
$ git clone https://github.com/lnxusr1/kenzy $ cd kenzy $ python3 -m venv .venv $ source .venv/bin/activate
Step 2 · Install services
Pick your extras
# a room node only $ pip install -e ".[node]" # the full server stack $ pip install -e ".[server,stt,tts,llm,speaker]"
Step 3 · Models
Download once
# wake-word + speaker-ID models $ kenzy-setup
Fetches the openWakeWord and SpeechBrain models for offline use.
Step 4 · Configure
Keys & settings
$ cp .env.example .env # edit .env and configs/*.yaml # point llm at a local or cloud model
Defaults in configs/ are sensible starting points.
02 Run it
Start the services.
Each reads its config from configs/<service>.yaml. Start them in any order; the node connects to the server.
$ kenzy-server # WebSocket hub + orchestrator $ kenzy-stt # speech-to-text $ kenzy-llm # LLM + skills $ kenzy-tts # text-to-speech $ kenzy-speaker # speaker identification $ kenzy-node # on each room device
// useful helpers: kenzy-enroll (add a speaker) · kenzy-devices (find your mic)
03 · GO FURTHER
Deploy across the house
Once one node works, roll out the rest with kenzy-deploy — it syncs source, builds virtualenvs, writes systemd units, and manages services across every host over SSH.
- SSH key auth + passwordless sudo on each host
init → install → upgrade
$ kenzy-deploy init $ kenzy-deploy install $ kenzy-deploy upgrade
// Need the details?
The docs have every step.
Full configuration reference, the skill-writing guide, speaker enrollment, and deployment — all documented.