Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189033,
        author = {Nandeesh and Praveen and Nikita and Prof. Santoshi M Pujari},
        title = {SIGN-TO-SPEECH PRO},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4363-4368},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189033},
        abstract = {Communication remains a fundamental challenge for the deaf and hard-of-hearing community, as sign language is not universally understood by the general population. This linguistic barrier significantly impacts accessibility in essential sectors such as healthcare, education, and public services. Existing technological solutions, including sensor-based gloves and early computer vision systems, often suffer from high costs, hardware dependency, and limited scalability. This paper presents Sign-to-Speech Pro, a novel, lightweight, and real-time web-based framework designed to bridge this communication gap. The proposed system leverages Google MediaPipe for efficient, hardware-independent hand landmark detection and employs Geometric Vector Analysis for high-speed gesture classification, eliminating the need for computationally intensive deep learning models for static signs. Furthermore, the system integrates advanced Generative AI (Large Language Models) to convert raw gesture glosses into grammatically correct, natural language sentences, which are then synthesized into spoken audio using Neural Text-to-Speech (TTS). The platform supports multilingual translation, a "Custom Gesture Trainer" for user-specific adaptability, and an interactive "Learn Mode" for educational purposes. Experimental results demonstrate that the system achieves high recognition accuracy with low latency on standard consumer hardware, offering a scalable and inclusive solution for assistive communication.},
        keywords = {Sign Language Recognition, MediaPipe, Generative AI, Human-Computer Interaction, Assistive Technology, Text-to-Speech.},
        month = {December},
        }