sirmrak/linux-voice-assistant

Fork 0

Files

T

imonlinux d3a020b8f1 Update linux-voice-assistant-2mic-install.md

2025-09-09 20:56:17 -07:00

6.2 KiB

Raw Blame History

Linux Voice Assistant on 2‑Mic Linux — Installation & Configuration Guide

Created using ChatGPT 5 with the following prompt:

      Using the following github document as a guide
      https://github.com/rhasspy/wyoming-satellite/blob/master/docs/tutorial_2mic.md,
      take the attached bash history of commands and create a similar document
      detailing the installation and configuration of this linux-voice-assistant project.

Modeled after the Wyoming Satellite two‑mic tutorial, adapted from actual shell history.

This guide reproduces a working setup of the linux-voice-assistant project with Wyoming OpenWakeWord on a Raspberry PI Zero 2W and a Respeaker 2‑mic HAT (e.g., seeed-2mic-voicecard). It assumes a fresh system with sudo access.

Prerequisites

A Linux system (Debian/Ubuntu/Raspberry Pi OS or compatible)
Python 3.11+ recommended
A 2‑mic sound card
Network access to your Home Assistant instance

1. Install system packages

sudo apt update
sudo apt upgrade
sudo apt install libportaudio2 build-essential git libmpv-dev mpv python3.11-dev
sudo reboot

2. Get the code

git clone https://github.com/imonlinux/linux-voice-assistant.git
git clone https://github.com/rhasspy/wyoming-openwakeword.git

3. Wyoming OpenWakeWord (OWW)

cp ./linux-voice-assistant/wyoming-openwakeword/requirements.txt ./wyoming-openwakeword/requirements.txt
cd wyoming-openwakeword/
script/setup

4. Configure audio devices

Find your sound device names and update the linux-voice-assistant/service/linux-voice-assistant.service file to match sound card details:

arecord -l
aplay -l

5. Systemd services

Copy the 2 service files into /etc/systemd/system/:

sudo cp ./service/linux-voice-assistant.service /etc/systemd/system/linux-voice-assistant.service
sudo cp ./service/wyoming-openwakeword.service /etc/systemd/system/wyoming-openwakeword.service

Start new services and confirm services are running:

sudo systemctl daemon-reload
sudo systemctl enable --now linux-voice-assistant
sudo systemctl status linux-voice-assistant wyoming-openwakeword --no-pager -l

6. Connect to Home Assistant

In Home Assistant, go to "Settings" -> "Device & services"
Click the "Add integration" button
Choose "ESPHome" and then "Set up another instance of ESPHome"
Enter the IP address of your voice satellite with port 6053
Click "Submit"

7. Verification

Expect logs like Connected to Home Assistant
Look for [OWW] Detection: name=... followed by re-arming/cycling
Ask: “What time is it?” and confirm TTS reply

8. Change OWW detection model

Edit the linux-voice-assistant.service file and change the OWW configuration argument for --wake-word-name. Project OWW models include:

alexa_v0.1.tflite
embedding_model.tflite
hey_jarvis_v0.1.tflite
hey_mycroft_v0.1.tflite
hey_rhasspy_v0.1.tflite
melspectrogram.tflite
ok_nabu_v0.1.tflite

Additional community provided OWW models available from this repository: https://github.com/fwartner/home-assistant-wakewords-collection

Edit linux-voice-assistant.service file:

sudo systemctl edit --force --full linux-voice-assistant.service

Service file as provided using OWW 'ok_nabu':

[Unit]
Description=Linux Voice Assistant
Requires=wyoming-openwakeword.service
After=sound.target network-online.target
Wants=network-online.target

[Service]
Type=simple
WorkingDirectory=/home/pi/linux-voice-assistant
ExecStart=/home/pi/linux-voice-assistant/script/run \
  --name 'Linux Satellite' \
  --audio-input-device seeed-2mic-voicecard \
  --audio-output-device alsa/hw:2,0 \
  --wake-uri 'tcp://127.0.0.1:10400' \
  --wake-word-name 'ok_nabu'
Restart=always
RestartSec=2
Environment=PYTHONUNBUFFERED=1

[Install]
WantedBy=multi-user.target

Service file using OWW 'alexa':

[Unit]
Description=Linux Voice Assistant
Requires=wyoming-openwakeword.service
After=sound.target network-online.target
Wants=network-online.target

[Service]
Type=simple
WorkingDirectory=/home/pi/linux-voice-assistant
ExecStart=/home/pi/linux-voice-assistant/script/run \
  --name 'Linux Satellite' \
  --audio-input-device seeed-2mic-voicecard \
  --audio-output-device alsa/hw:2,0 \
  --wake-uri 'tcp://127.0.0.1:10400' \
  --wake-word-name 'alexa'
Restart=always
RestartSec=2
Environment=PYTHONUNBUFFERED=1

[Install]
WantedBy=multi-user.target

Reload systemd with updated linux-voice-assistant.service file and restart linux-voice-assistant.service and confirm successful run:

sudo systemctl daemon-reload
sudo systemctl restart linux-voice-assistant.service
sudo systemctl status linux-voice-assistant wyoming-openwakeword --no-pager -l

9. TODO :Revert to MicroWakeWord

Edit the linux-voice-assistant.service file and remove the OWW configuration arguments: Service file with OWW:

sudo systemctl edit --force --full linux-voice-assistant.service

[Unit]
Description=Linux Voice Assistant
Requires=wyoming-openwakeword.service
After=sound.target network-online.target
Wants=network-online.target

[Service]
Type=simple
WorkingDirectory=/home/pi/linux-voice-assistant
ExecStart=/home/pi/linux-voice-assistant/script/run \
  --name 'Linux Satellite' \
  --audio-input-device seeed-2mic-voicecard \
  --audio-output-device alsa/hw:2,0 \
  --wake-uri 'tcp://127.0.0.1:10400' \
  --wake-word-name 'ok_nabu'
Restart=always
RestartSec=2
Environment=PYTHONUNBUFFERED=1

[Install]
WantedBy=multi-user.target

Service file without OWW:

[Unit]
Description=Linux Voice Assistant
Requires=wyoming-openwakeword.service
After=sound.target network-online.target
Wants=network-online.target

[Service]
Type=simple
WorkingDirectory=/home/pi/linux-voice-assistant
ExecStart=/home/pi/linux-voice-assistant/script/run \
  --name 'Linux Satellite' \
  --audio-input-device seeed-2mic-voicecard \
  --audio-output-device alsa/hw:2,0 
Restart=always
RestartSec=2
Environment=PYTHONUNBUFFERED=1

[Install]
WantedBy=multi-user.target