README.md

# Elite Transcript AI 🚀

GPU-accelerated transcription service powered by Whisper-v3 and DeepSeek Speech API with automatic fallback.

## Features
- 🎙️ High-accuracy verbatim transcription
- ⚡ GPU-accelerated processing (when available)
- 🔄 Automatic fallback to DeepSeek Speech API
- 📼 Supports YouTube & TikTok URLs
- 📝 Multiple export formats (TXT, SRT, DOCX)
- 🏗️ Batch processing mode

## Tech Stack
- Frontend: Vite + React + TailwindCSS
- Backend: FastAPI + Whisper-v3 + DeepSeek SDK
- Deployment: Vercel (frontend) + Render/AWS (backend)

## Setup

### Prerequisites
- Node.js 18+
- Python 3.10+
- NVIDIA GPU with CUDA (recommended)
- FFmpeg installed

### Installation

1. Clone the repository
```bash
git clone https://github.com/yourusername/elite-transcript-ai.git
cd elite-transcript-ai

2. Setup backend

cd server
python -m venv venv
source venv/bin/activate  # Linux/Mac
# venv\Scripts\activate  # Windows
pip install -r requirements.txt

3. Setup frontend

cd ../client
npm install

4. Configure environment variables Copy .env.example to .env and fill in your API keys.

Running Locally

Start backend:

cd server
uvicorn main:app --reload

Start frontend:

cd ../client
npm run dev

Deployment

See DEPLOYMENT.md for detailed cloud deployment instructions.

Environment Variables

See .env.example for all required configurations. ```