Your personal voice-controlled virtual assistant powered by AI

Visit Project

Project Overview

Eren AI Assistant is a voice-controlled virtual assistant built with Python, designed to automate tasks, provide information, and assist users in daily computing activities. It integrates AI (GPT-4), speech recognition, automation, and web services to function as a personal assistant.

This project was built to automate repetitive tasks, showcase Python's capabilities in AI & automation, provide a personalized assistant for productivity, and experiment with GPT-4 and voice recognition technologies.

Key Features

Voice & Text Interaction

Advanced speech recognition combined with GPT-4 for natural conversations in English and Hindi.

Smart Automation

Automate file management, app control, WhatsApp messaging, and Spotify playback with voice commands.

AI-Powered Responses

Leverages GPT-4 for intelligent, context-aware conversations and information retrieval.

Task Management

Manage to-do lists, set goals, and create reminders to boost your productivity.

System Control

Control your PC with voice commands - shutdown, restart, lock, volume control, and more.

Web Integration

Access news, weather, Wikipedia, dictionary lookups, and more through web APIs.

Technical Implementation

Eren AI Assistant combines multiple technologies to deliver a seamless voice-controlled experience.

Core Technologies Used

Python

Backend Logic

GPT-4

AI Responses

SpeechRecognition

Voice Input

Spotify API

Music Playback

OpenWeather API

Weather Data

NewsAPI

News Headlines

Eel

Web UI Integration

How It Works?

  1. User speaks → Speech converted to text using speech_recognition library.
  2. Command Detection → System checks for keywords (e.g., "weather," "play song") to determine action.
  3. Action Execution → Performs the appropriate task (API calls, automation, GPT-4 response generation).
  4. Response → Speaks back using gTTS or displays output on the web interface.

Command List

Eren AI Assistant supports 100+ voice commands across various categories.

Basic Interactions

Command Action
"Hello" / "Hi" Greets the user
"Exit" / "Stop" Shuts down the assistant
"Chat mode" Talks with GPT-4
"Switch to Hindi" Changes language to Hindi

System Control

Command Action
"Shutdown" Turns off the PC
"Restart" Reboots the system
"Lock PC" Locks the computer
"Volume up/down" Adjusts system volume
"Open settings" Launches Windows settings
"Turn WiFi on/off" Toggles WiFi

Productivity

Command Action
"Write note" Saves a note in Notepad
"Add task" Adds a To-Do item
"Set goal" Tracks life goals
"Write email" Drafts & sends emails
"Make meme" Generates a meme
"Extract text from image" Reads text from images

Entertainment

Command Action
"Play [song] on Spotify" Plays music
"News" Reads headlines
"Weather in [city]" Gives weather updates
"Who is [person]?" Wikipedia summary

AI & Advanced Features

Command Action
"Make code for [task]" Generates Python/Java/etc. code
"Meaning of [word]" Dictionary lookup
"Find location of [number]" Phone number tracker
"Remember [info]" Stores notes in memory
"Set alarm for [time]" Creates a timer

Security & Privacy

  • Password-protected (Voice/Text Authentication)
  • No cloud storage (All data saved locally in memory.json)
  • No unauthorized access (Commands require user confirmation)

Future Improvements

  • Android/iOS App Version
  • Face Recognition Login
  • Home Automation (IoT Integration)
  • Advanced AI Memory (Long-term context)