Verbatimly

About Verbatimly

Last updated 15 November 2026

What it does

Verbatimly turns a video or audio file into text with timestamps. You pick a file, it comes back as a transcript you can read, copy, download as SRT or VTT, or export as plain text.

There is no account. There is no file library. Nothing is stored after the request finishes.

How the transcription works

Two steps, and the first one happens entirely on your device:

  1. Your browser extracts the audio track from the file and compresses it to a small mono track. This is why a 500 MB video does not need to be uploaded.
  2. Only that compressed audio goes to our server, which forwards it to a speech-to-text model and returns the transcript.

The original file never leaves your computer. Uploading a two-hour video would take longer than transcribing it, which is the other reason for working this way.

What happens to your files

The compressed audio is forwarded to the transcription provider and discarded after the request. The transcript is returned to your browser; we do not keep a copy. No one reviews your files, and nothing is used to train a model. The privacy policy has the specifics on logging and providers.

Limits

Free transcription is limited per day, and there is a per-file length limit. The limits exist because transcription costs money per minute of audio, and a free tool without limits gets found by people running bulk jobs within a week. A credit pack is available if you need more.

Who makes it

An independent developer. Verbatimly is a focused tool rather than a suite: it does transcription, it does it in the browser, and it does not ask you to sign up.

Getting in touch

Corrections, format requests and bug reports are welcome — see the contact page.