🧠 AI-Powered Virtual Assistant

This project is an intelligent assistant that combines computer vision and speech synthesis to detect and narrate real-world objects via webcam, logging them in a local file.

💡 Features

• Real-time object detection with TensorFlow + OpenCV
• Text-to-Speech narration using Hugging Face Transformers or Google TTS
• Logs recognized objects with timestamps
• Docker-ready deployment

🚀 Getting Started

1. Clone the repo:

git clone https://github.com/mohanpriya20/ai-virtual-assistant.git
cd ai-virtual-assistant

2. Install dependencies:

pip install -r requirements.txt

3. Run the assistant:

python assistant/app.py

🐳 Docker

To run in Docker:

docker build -t virtual-assistant .
docker run -p 5000:5000 virtual-assistant