Skip to main content

​
Prerequisites

Before you begin, ensure you have the following installed:
  • Python 3.8+ with pip
  • Node.js 16+ with npm
  • FFmpeg (for video processing)
  • Git (to clone the repository)
You’ll also need API keys from:

​
Get Started in 5 Minutes

1

Clone the repository

git clone https://github.com/Kamal-Nayan-Kumar/AI-Video-Gen
cd AI-Video-Gen
2

Set up the backend

Navigate to the backend directory and create a virtual environment:
cd backend
python -m venv venv
Activate the virtual environment:
venv\Scripts\activate
Install dependencies:
pip install -r requirements.txt
Install Manim (animation library):
pip install manim
3

Configure environment variables

Create a .env file in the backend/ directory:
cp .env.example .env
Edit .env and add your API keys:
GEMINI_API_KEY=your_gemini_api_key_here
SARVAM_API_KEY=your_sarvam_api_key_here
UNSPLASH_ACCESS_KEY=your_unsplash_access_key_here
The backend uses Sarvam AI for text-to-speech. Make sure to get your API key from Sarvam AI.
4

Start the backend server

With your virtual environment still activated, run:
python app.py
The FastAPI backend will start on http://localhost:8000. You should see:
INFO:     Started server process
INFO:     Uvicorn running on http://0.0.0.0:8000
5

Set up the frontend

Open a new terminal and navigate to the frontend directory:
cd frontend
Install dependencies:
npm install
Start the development server:
npm run dev
The React frontend will start on http://localhost:5173.
6

Generate your first presentation

  1. Open your browser and go to http://localhost:5173
  2. Enter a topic (e.g., “Introduction to Machine Learning”)
  3. Set the number of slides (e.g., 5)
  4. Choose a language (English, Hindi, Kannada, or Telugu)
  5. Select a tone (Formal, Casual, or Educational)
  6. Click Generate
The system will:
  • Generate presentation content using Gemini AI
  • Create narration scripts for each slide
  • Generate voice audio using Sarvam AI
  • Fetch relevant images from Unsplash or create animations with Manim
  • Compose everything into a final MP4 video
The generation process takes 2-5 minutes depending on the number of slides and complexity.

​
What’s Next?

Installation Guide

Detailed installation instructions for all platforms

Configuration

Learn about advanced configuration options

API Reference

Explore the FastAPI endpoints

Creating Presentations

Learn how to create and customize presentations

​
Troubleshooting

Make sure:
  • Your virtual environment is activated
  • All dependencies are installed: pip install -r requirements.txt
  • FFmpeg is installed and accessible in your PATH
  • Port 8000 is not already in use
  • Verify the backend is running on http://localhost:8000
  • Check browser console for CORS errors
  • Ensure your .env file has the correct API keys
Common issues:
  • Invalid API keys in .env
  • FFmpeg not installed or not in PATH
  • Insufficient disk space in backend/outputs/
  • API rate limits exceeded

Build docs developers (and LLMs) love

Get started for freeTalk to us