AI voice assistant made with python and powered by GEMINI and MISTRAL.
This is a virtual assistant application built in Python that can understand voice commands and complete tasks like opening websites, playing music, telling the time, sending emails, searching Wikipedia, and more.
- Voice recognition using SpeechRecognition
- Text-to-speech using pyttsx3
- Opening websites like YouTube, Google
- Playing music
- Telling the time
- Sending emails
- Making Google searches
- Telling jokes
- Searching Wikipedia
- Taking screenshots
- Writing notes
- Getting weather information
- Integrated with Google's generative AI models
- Integrated with HuggingFace's Mistral AI model
- python 3.x
- pyaudio
- pyttsx3
- speechRecognition
- wikipedia
- webbrowser
- smtplib
- pyjokes
- datetime
- wolframalpha
- os
- pyautogui
- google.generativeai
- huggingface_hub
And other common Python libraries listed in requirements.txt
Run python assistant {model_name}.py to start the virtual assistant. Just run it to activate it. Other example voice commands:
- "What time is it?"
- "Search YouTube for funny videos"
- "Send an email to [email protected]"
- "Take a screenshot"
See the code comments for full documentation of features.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.