Stitch'n'Sense — Setup Guide

Stitch'n'Sense is a modular, AI-powered video editing and generation platform. Follow these steps to get the project running on your local machine in minutes.

---

🚀 Quick Start (Fast Setup)

1. Prerequisites

Ensure you have the following installed:

• FFmpeg (Search "Install FFmpeg" for your OS - required for all video processing)
• Python 3.10+
• Node.js 18+

2. Clone and Prepare

git clone https://github.com/nothariharan/Switch_N_Sense.git
cd StitchNSense

---

3. Backend Setup (FastAPI)

The engine that powers the AI agents and video surgery.

1. Navigate & Virtual Env:

   cd backend
   python -m venv venv
   # Windows:
   .\venv\Scripts\activate
   # Mac/Linux:
   source venv/bin/activate

2. Install & Env:

   pip install -r requirements.txt

   Create a .env file in the /backend folder:

   AWS_ACCESS_KEY_ID=your_key
   AWS_SECRET_ACCESS_KEY=your_secret
   AWS_REGION=us-east-1

3. Run:

   python -m uvicorn main:app --reload

   Running on: http://localhost:8000

---

4. Frontend Setup (React + Vite)

The sleek, high-performing workbench UI.

1. Navigate & Install:

   cd ../frontend
   npm install

2. Run:

   npm run dev

   Running on: http://localhost:5173

---

🧪 Core Features to Test

1. Generate: Upload a PDF/Document in the Generate tab to see it split into a video storyboard.
2. Edit: Upload a video, click a SceneNode on the infinite canvas, and use a Natural Language command like "Make this shorter" or "Lower the tone depth".
3. Regenerate: Click the green button to see Surgical Regeneration in action (only that scene rebuilt).
4. Export: Click Export in the top bar for a modular FFmpeg concatenation.

🛠 Tech Stack

• Frontend: React, TypeScript, Vite, Framer Motion, Zustand.
• Backend: FastAPI, Boto3 (AWS Bedrock & Polly), FFmpeg.
• AI: Amazon Bedrock (Nova Pro), faster-whisper (local STT), OpenCV.