A simple local desktop assistant that listens for voice commands and launches applications on your computer.
main.py - entrypoint for CLI or GUI modeassistant/voice_engine.py - local speech recognition supportassistant/commands.py - app launch mappings and helpersassistant/assistant.py - core logic for matching and executing commandsassistant/gui.py - minimal Tkinter-based interactive interfacerequirements.txt - Python dependency listmem.md - notes and mistakes to avoid repeatingpython3-tk installed for GUI modepython3 -m pip install -r requirements.txt
If you want the GUI, also install Tkinter:
sudo apt update
sudo apt install python3-tk
For the best local speech recognition experience, use VOSK.
mkdir -p models
cd models
wget https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip
unzip vosk-model-small-en-us-0.15.zip
python3 main.py --model models/vosk-model-small-en-us-0.15
If you do not have a VOSK model installed, the project can fall back to PocketSphinx if speech_recognition and pocketsphinx are available.
python3 main.py --model models/vosk-model-small-en-us-0.15
python3 main.py --gui --model models/vosk-model-small-en-us-0.15
python3 main.py --list --model models/vosk-model-small-en-us-0.15
open chromeopen vscodeopen file manageropen terminalAdd a new function to assistant/commands.py, then add an entry to COMMANDS with keywords and a description.