VideoLingo

VideoLingo is an open-source AI video localization platform that automates transcription, subtitle translation, synchronization, and dubbing. It combines speech recognition with word-level alignment to produce accurately timed subtitles. AI-assisted segmentation divides speech into readable subtitle lines using configurable length limits. Its translation workflow supports terminology management, contextual rewriting, and optional review stages. Users can generate multilingual subtitles and synthesized voiceovers through several text-to-speech providers. The software also supports downloading YouTube videos through yt-dlp. A Streamlit interface manages processing, model selection, logs, and task recovery. VideoLingo runs on Windows, macOS, and Linux and can export subtitle files or completed subtitled and dubbed videos.