Nexaura is an AI-powered virtual assistant developed in Python that combines voice recognition, automation, and conversational AI into a single system.

It listens to voice commands, understands user requests, performs tasks such as opening websites and applications, and generates intelligent responses using AI.

The project is designed to help users interact with their computers naturally through voice commands while also serving as a learning project for AI, automation, and Python development.

• 🎙️ Voice recognition and speech processing
• 🧠 AI-powered intelligent conversations
• 🌐 Open websites using voice commands
• 💻 Launch desktop applications
• 🔎 Perform internet searches
• 📅 Time and date utilities
• ⚡ Fast and lightweight architecture
• 🛠️ Modular and expandable design
• 📂 Beginner-friendly project structure

User Speaks
      │
      ▼
Speech Recognition
      │
      ▼
Command Processing
      │
      ▼
Task Execution / AI Response
      │
      ▼
Output to User

• Python

NEXAURA/
│
├── main.py               # Main assistant program
├── requirements.txt      # Project dependencies
├── README.md             # Documentation
├── assets/               # Images, icons, resources
├── modules/              # Assistant modules
└── .gitignore

git clone https://github.com/sam-dev-161127/Nexaura.git

cd Nexaura

pip install -r requirements.txt

Nexaura supports multiple AI providers. Choose any one (or combine them) based on your preference.

Install the library:

pip install google-generativeai

Configure and use:

import google.generativeai as genai

genai.configure(api_key="YOUR_GEMINI_API_KEY")

model = genai.GenerativeModel("gemini-pro")

def ask_gemini(prompt):
    response = model.generate_content(prompt)
    return response.text

# Example usage
reply = ask_gemini("What is artificial intelligence?")
print(reply)

🔗 Get your API key from Google AI Studio

Install the library:

pip install openai

Configure and use:

from openai import OpenAI

client = OpenAI(api_key="YOUR_OPENAI_API_KEY")

def ask_openai(prompt):
    response = client.chat.completions.create(
        model="gpt-4o",  # or "gpt-3.5-turbo" for a faster, cheaper option
        messages=[
            {"role": "system", "content": "You are a helpful assistant named Nexaura."},
            {"role": "user", "content": prompt}
        ]
    )
    return response.choices[0].message.content

# Example usage
reply = ask_openai("What is artificial intelligence?")
print(reply)

🔗 Get your API key from OpenAI Platform

Available Models:

Install the library:

pip install anthropic

Configure and use:

import anthropic

client = anthropic.Anthropic(api_key="YOUR_ANTHROPIC_API_KEY")

def ask_claude(prompt):
    message = client.messages.create(
        model="claude-sonnet-4-5",  # or "claude-haiku-4-5" for faster responses
        max_tokens=1024,
        messages=[
            {"role": "user", "content": prompt}
        ]
    )
    return message.content[0].text

# Example usage
reply = ask_claude("What is artificial intelligence?")
print(reply)

🔗 Get your API key from Anthropic Console

Available Models:

Install the library:

pip install openai  # DeepSeek uses the OpenAI-compatible SDK

Configure and use:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_DEEPSEEK_API_KEY",
    base_url="https://api.deepseek.com"
)

def ask_deepseek(prompt):
    response = client.chat.completions.create(
        model="deepseek-chat",  # or "deepseek-reasoner" for step-by-step reasoning
        messages=[
            {"role": "system", "content": "You are a helpful assistant named Nexaura."},
            {"role": "user", "content": prompt}
        ]
    )
    return response.choices[0].message.content

# Example usage
reply = ask_deepseek("What is artificial intelligence?")
print(reply)

🔗 Get your API key from DeepSeek Platform

Available Models:

You can easily switch between providers with a simple config variable:

# Set your preferred AI provider: "gemini", "openai", "claude", "deepseek"
AI_PROVIDER = "gemini"

def get_ai_response(prompt):
    if AI_PROVIDER == "gemini":
        return ask_gemini(prompt)
    elif AI_PROVIDER == "openai":
        return ask_openai(prompt)
    elif AI_PROVIDER == "claude":
        return ask_claude(prompt)
    elif AI_PROVIDER == "deepseek":
        return ask_deepseek(prompt)
    else:
        return "No AI provider configured."

This way, you only need to change one line to switch providers.

Start the assistant using:

python main.py

After launching, Nexaura will begin listening for voice commands.

1. Nexaura listens for voice input.
2. Speech Recognition converts audio into text.
3. The command is cleaned and analyzed.
4. Appropriate actions are executed.
5. AI generates responses when needed.
6. Results are returned to the user.

This project demonstrates:

• 🤖 Artificial Intelligence Integration
• 🎙️ Speech Recognition
• ⚡ Automation Systems
• 💻 Human-Computer Interaction
• 🐍 Python Development
• 🔌 API Integration

Planned improvements include:

• 🎯 Higher voice recognition accuracy
• 🧠 Better conversational memory
• 🌤️ Weather information support
• 📧 Email automation
• 📁 File management commands
• 🖥️ Modern graphical user interface
• 🔊 Text-to-Speech responses
• 🤖 Custom AI agent capabilities

Contributions, ideas, and suggestions are welcome.

1. Fork the repository
2. Create a new branch

git checkout -b feature-name

3. Commit your changes

git commit -m "Added new feature"

4. Push to GitHub

git push origin feature-name

5. Create a Pull Request

🎓 Student 🐍 Python Developer 🤖 AI Enthusiast 🔧 Robotics Learner

If you like this project, consider giving it a Star ⭐ on GitHub.

It motivates further development and helps others discover the project.

This project is licensed under the MIT License.