This study presents a machine learning and natural language processing (NLP)-based approach for automatically generating concise summaries of YouTube video content. With the exponential growth of video uploads on YouTube, identifying relevant information efficiently has become increasingly challenging. The proposed system addresses this issue by extracting transcripts from videos and applying the PEGASUS model for abstractive summarization. The result is a coherent and condensed version of the video content, allowing users to quickly grasp the key points without watching the entire video. This approach enhances content accessibility and significantly reduces the time required for information retrieval.