An AI voice assistant working fully locally. It's also able to perform tasks.

Following tasks are implemented:

• Taking notes and setting reminders for them.

• Ollama
• PyTorch
• RealtimeSTT
• pyttsx3
• plyer (for reminders)

First, you need to install Ollama: https://ollama.com/download

Then, Install necessary PyPI packages using:

pip install RealtimeSTT pyttsx3 plyer

To install the gpu version of PyTorch:

pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu121

Download the app folder and Run app.py script in background:

python app.py &

You can configure the models and parameters at the beginning of the script:

# --------------------------
# Configuration
# --------------------------
LLM_MODEL = "phi3.5:3.8b"
WHISPER_MODEL = 'small.en'
TTS_RATE = 170
TTS_VOICE_INDEX = 0

Command for taking notes is:

Take me note

• Say cancel if you changed your mind.
• Use yes and no to give positive and negative responses.
• The format to give the day, month and the year information: <day> <month name> <year> for example, 2025年06月29日 -> 29 June 2025
• The format to give the clock information: <hour>.<minute> for example, 1:05 PM -> 13.5