Transcript & Subtitle Cleaner (SRT / VTT / Timestamps)

Convert subtitle files and raw transcripts into readable text for articles, summaries or notes.

Use the tool

Why this tool exists

The cleaner removes the WEBVTT header and NOTE blocks, cue numbers, time ranges and leading timestamps, HTML-style tags, optional speaker labels, bracketed sound cues and filler words (um, uh, er, hmm), then joins broken lines into paragraphs and fixes spacing and capitalisation. A setting groups sentences into paragraphs of a chosen length.

It only edits text: no speech recognition happens, and removing "um" can occasionally leave a sentence slightly unnatural, so give it a read.

No data is sent anywhere: the work happens in your browser, so you can use it offline once the page has loaded.

How to use it

  1. Paste the subtitle or transcript text.
  2. Choose which clean-ups to apply.
  3. Optionally set sentences per paragraph.
  4. Copy the cleaned text.

Frequently asked questions

Does it transcribe audio?

No. It cleans text you already have.

Which formats are handled?

SRT, WebVTT and plain transcripts with timestamps like [00:01:23].

Will it remove real words?

Only the listed fillers; "like" and "you know" are left alone.

Is my data sent anywhere?

No. Everything is processed in your browser, and the page makes no network requests with your input.