Back to Projects
AI Video Lecture Summarizer (Production-Ready Platform)
AI Video Lecture Summarizer (Production-Ready Platform)
2025 – Present
AI + Full-Stack Developer

AI Video Lecture Summarizer (Production-Ready Platform)

Building a scalable AI-powered platform that converts lecture videos into structured study notes. The system processes videos, extracts audio, transcribes speech using Whisper, and generates well-structured notes using Gemini AI. Currently evolving from a desktop application into a full-stack web platform with improved performance, better UI, and scalable architecture.

Project Highlights

  • Built end-to-end video-to-notes automation pipeline.

  • Converted speech to text using Whisper with high accuracy.

  • Generated structured study notes using Gemini AI.

  • Exported outputs as Markdown and styled PDF.

  • Processing multiple videos with batch support.

  • Upgrading to a full-stack production-level web platform.

Explore More Work

Deep dive into other high-performance solutions.

View Full Archive
User Registration and Login System (MERN Stack)

Developed a full-stack user authentication system using the MERN stack. Implemented secure user registration and login with backend validation and database integration. Ensured safe data storage and smooth user experience.

MongoDBExpress.jsReact.jsNode.js
Intelligent Travel Information Assistant

Built a real-time travel assistance platform that provides destination insights, hotel information, and trip recommendations using live API integration. Designed a responsive interface for smooth user interaction.

HTMLCSSJavaScriptREST APIs
AI Video Lecture Summarizer (Production-Ready Platform)

Building a scalable AI-powered platform that converts lecture videos into structured study notes. The system processes videos, extracts audio, transcribes speech using Whisper, and generates well-structured notes using Gemini AI. Currently evolving from a desktop application into a full-stack web platform with improved performance, better UI, and scalable architecture.

PythonWhisperGemini APITkinterFFmpeg