MonoSub – Local AI subtitle generator from audio or video

Summary: MonoSub is a desktop app that generates subtitles and video summaries entirely offline using local AI. It processes multiple files with support for Chinese and English, producing SRT, VTT, and TXT formats without relying on cloud services.

What it does

MonoSub uses FunASR for local AI transcription and summary generation, enabling batch processing of video files with automatic thumbnail creation. It runs on a Tauri and React framework, storing results flexibly on the user’s device.

Who it's for

It is designed for users needing private, offline transcription and subtitle generation without recurring subscription costs, such as video creators managing their own workflows.

Why it matters

MonoSub eliminates dependence on cloud transcription services, reduces costs, and protects video content privacy by processing everything locally.