AI-Powered Text-to-Video Story Generator
Engineered a full-stack AI application converting text to narrated video stories using Python async/await and a Node.js backend API. Implemented NLP text processing, Google Text-to-Speech synthesis, FFmpeg video generation with temporal synchronization, Winston error handling and logging, Bull queue-based processing, and Render deployment with PM2. Achieved a 30% reduction in pipeline execution time through task parallelization.