Clean up a subtitle file
Strip SDH sound descriptions, credits, ads and other cruft; fix mangled encoding, OCR misreads and overlapping timing — pick what to fix, in one pass.
The AI Subtitle Studio desktop app has this same Tools section built in — plus AI transcription, translation and batch processing for a whole season at once, all running locally on your Mac or PC.
Pick what to fix, get the file back
Upload one file
SRT or WebVTT — plain-text dialogue-track subtitles, the kind SDH removal and credit-stripping apply to.
Choose what to clean
Every toggle defaults to what the desktop app's Cleanup tool ships with — uncheck anything you'd rather leave alone.
Download the result
Cues that become empty after cleanup are dropped and the file is renumbered, so it stays valid.
Local pattern matching, not an AI model
This is the same rule-based cleanup the desktop app's Cleanup tool runs — regular-expression pattern matching, not a language model. It's instant and deterministic: the same file and the same options always produce the same output. For AI-assisted cleanup of transcription artifacts specifically, see the desktop app's AI Cleanup feature instead.
Questions about cleanup
What counts as an SDH sound description?
Will this remove dialogue by mistake?
Does this work on ASS/SSA files?
What happens to cue numbers after cues are removed?
Do you keep my file?
Is there an API for this?
/cleanup endpoint, its parameters and curl examples.