Voice AI Agent using Streamlit

This project is a Voice AI Agent that processes user commands and performs actions like file creation, code generation, and summarization.

Architecture:
The system follows a pipeline:
Input → Intent Detection → Action Execution → Text-to-Speech Output

Technologies Used:

• Streamlit for UI
• Python for backend
• pyttsx3 for voice output

Features:

• Intent detection using rule-based approach
• Dynamic file creation
• Code generation
• Audio input support (simulated)

Challenges:

• Integrating real speech-to-text due to API limitations
• Handling dynamic user inputs
• Managing UI responsiveness

Conclusion:
The project demonstrates a complete AI workflow with modular components and can be extended with real speech-to-text models in the future.