AI-Based Multilingual Story Generation and Speech Synthesis System

Abstract

Storytelling plays an important role in education, creativity, and entertainment, but writing stories manually requires time, imagination, and language proficiency. This project presents an AI-Powered Multilingual Story Generation and Speech Synthesis System that automatically generates meaningful stories from user-provided keywords. The system allows users to register, log in, select their preferred language, and generate stories in languages such as English, Hindi, Odia, and Telugu. It is developed using Python, Django, and MySQL, while the Gemini AI model is used to understand the input keywords and produce coherent, grammatically correct, and context-aware stories. In addition to text generation, the system converts the generated stories into speech, providing a more engaging and accessible experience for users. The proposed system reduces manual effort, supports multilingual communication, and enhances storytelling through artificial intelligence. It offers a simple, interactive, and efficient platform suitable for educational, learning, and entertainment applications.