AI Assistant (Jarvis) is a Python script that acts as a voice-controlled personal assistant. It can perform various tasks and provide responses to your voice commands. This README provides an overview of the script and how to use it.
Speech Recognition: The script uses the SpeechRecognition library to recognize and interpret voice commands.
Text-to-Speech: It utilizes the pyttsx3 library to convert text into speech and respond to your queries.
AI Interaction: You can interact with AI models via the OpenAI API to obtain responses to your queries.
Web Browsing: It can open websites specified in your voice commands using the webbrowser library.
Time and Date: The assistant can provide you with the current time.
Multimedia: It can play songs on YouTube and retrieve information from the web.
Custom Commands: You can add custom voice commands to expand its functionality.
Before using the AI Assistant, make sure you have the following installed:
Required Python libraries (requests, gTTS, pyttsx3, speech_recognition, openai, gtts, selenium) Web browser (e.g., Google Chrome) OpenAI API key (replace 'apikey' with your actual key) How to Use Clone The Repo. #git clone https://github.com/nawabkh2040/Jarvis.git then #cd Jarvis Install the required Python libraries using #pip install -r requirements.txt.
Replace 'apikey' in the script with your actual OpenAI API key.
Run the script using #python main.py.
Speak a voice command to interact with the assistant.
Follow the provided voice responses or actions as per your commands.
Customization You can customize the assistant by adding more voice command options and expanding its functionality. Review the code for adding custom commands.
"Open YouTube" "What is the weather today?" "Play a song on YouTube" "Tell me a joke" "Open my favorite website"
The script was created by Nawab khan.