Synoptix Summarizer: A Role and Style Adaptive Text Summarization Tool with Multi-Input Support

Text summarization plays a pivotal role in Natural Language Processing (NLP), enabling efficient distillation of key information from extensive and diverse textual content. This paper introduces Synoptix Summarizer, a modular, customizable summarization tool designed to accommodate multiple input types—including plain text, web URLs, image files, and PDFs—through an integrated and user-friendly interface. The system combines Optical Character Recognition (OCR) via EasyOCR, PDF parsing through PyMuPDF, and a large language model (LLM) accessed through a backend API currently under development. A Gradio-based frontend provides interactive controls that allow users to personalize summaries based on preferred output style (e.g., bullet points, simplified), target reader role (e.g., student, CEO), optional entity focus, and custom prompt instructions. Synoptix Summarizer explores the integration of diverse NLP components into a cohesive summarization pipeline. It emphasizes adaptability, extensibility, and real-world usability, contributing a flexible platform for intelligent content summarization across educational, professional, and everyday use cases.