Presently-AI: An AI-Powered Presentation Video Generation System
Dr. Pavan G P Professor
Department of Information Science and Engineering AMC Engineering College
Bengaluru, India drpavangp84@gmail.com
Likitha S Scholar
Department of Information Science and Engineering AMC Engineering College
Bengaluru, India
likithashetty1102004@gmail.com
Keerthana Scholar
Department of Information Science and Engineering AMC Engineering College
Bengaluru, India 1am22is045@amceducation.in
Shobitha D Scholar
Department of Information Science and Engineering AMC Engineering College
Bengaluru, India shobithalatha2004@gmail.com
Manoj Rao S Scholar
Student, Dept. of Information Science and Engineering AMC Engineering College
Bengaluru, India manoj1784004@gmail.com
Abstract: In the digital era, a vast amount of information is available in the form of webpages, articles, and online documents. However, converting this static textual content into engaging multimedia presentations requires significant manual effort, technical expertise, and time. This paper presents Presently-AI, an artificial intelligence based system that automatically transforms web content into professional presentation videos. The proposed system integrates web scraping, natural language processing, AI- based summarization, automated slide generation, text-to-speech narration, background music integration, and video compilation into a single unified platform. Using Google Gemini AI models, the system extracts relevant information from webpages, structures it into slide-wise content, generates narration, and compiles a complete video presentation with minimal user intervention. The system significantly reduces manual workload while ensuring consistent quality and professional output. Experimental results demonstrate that Presently-AI effectively automates the end-to- end workflow of presentation video creation, making it highly suitable for students, educators, and professionals seeking efficient content delivery solutions.
Keywords: Artificial Intelligence, Web Scraping, NLP, Presentation Video Generation, Text-to-Speech.