Abstract :

The Rapid Growth Of Digital Multimedia Platforms Has Led To A Significant Increase In The Availability Of Online Video Content. Educational Lectures, Webinars, Podcasts, Interviews, And News Broadcasts Contain Valuable Information But Often Require Considerable Time To Watch Completely. This Project, Titled An Intelligent Speech-Based Video Content Summarization And Audio Generation Framework Using Automatic Speech Recognition And Large Language Models, Presents An Intelligent Framework For Automatically Generating Concise Text And Audio Summaries From Video Content. The Proposed System Accepts A YouTube Video URL As Input And Extracts The Audio From The Downloaded Video. The Extracted Audio Is Converted Into Text Using An Automatic Speech Recognition (ASR) Model With High Transcription Accuracy. The Generated Transcript Is Then Processed By A Large Language Model (LLM) To Produce A Context-aware And Coherent Abstractive Summary. The Summarization Process Preserves The Essential Information While Eliminating Redundant And Less Relevant Content. To Improve Accessibility, The Generated Text Summary Is Converted Into Natural-sounding Speech Using A Text-to-Speech (TTS) Engine. This Enables Users To Listen To The Summarized Content Without Reading The Text. The Proposed Framework Integrates Speech Recognition, Intelligent Summarization, And Speech Synthesis Into A Single Automated Workflow. The System Significantly Reduces The Time Required To Understand Lengthy Videos While Maintaining The Quality And Relevance Of The Summarized Content. It Is Particularly Useful For Students, Researchers, Professionals, And Visually Impaired Users Who Require Quick Access To Important Information. The Integration Of Automatic Speech Recognition And Large Language Models Enhances Transcription Accuracy And Contextual Understanding. The Developed Framework Provides An Efficient, Scalable, And User-friendly Solution For Multimedia Content Processing. Overall, The Proposed System Demonstrates The Practical Application Of Artificial Intelligence In Intelligent Video Summarization And Audio Generation.

Published:

07-7-2026

Issue:

Vol. 26 No. 7 (2026)

Page Nos:

236-242

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite