PolySub : AI-Powered Multilingual Subtitle and Dubbing with GenAI

Abstract

Language barriers go beyond communication gaps; they can restrict access to knowledge, limit collaboration, and reduce the global reach of digital content. PolySub addresses this challenge by providing an AI-powered platform for multi- lingual subtitling and dubbing, enabling seamless cross-language video accessibility. The system integrates OpenAI Whisper for transcription, Meta NLLB for translation and Meta MMS (TTS) model for audio generation, producing SRT files, dubbed videos with subtitles and original videos with embedded subtitles as outputs. Designed for scale, PolySub supports more than 150 languages, ensuring accessibility for diverse audiences. Evalua- tion shows strong performance, achieving a BLEU score of 37.0 and a BERTScore of 85.8, reflecting accurate, fluent, and se- mantically consistent output. This paper presents the conceptual framework of PolySub, outlines its architecture, and highlights how automated multilingual pipelines can enhance accessibility, scalability, and global communication across education, media, and professional domains.