Verbatim transcription writes down everything said, including stutters, false starts and sounds, so the text mirrors the speech as closely as possible.
Verbatim transcription writes down everything said, including stutters, false starts and sounds, so the text mirrors the speech as closely as possible. It is the most literal transcription style and the opposite of a cleaned-up transcript. It is used when the way something was said matters, such as legal or research records.
Also searched as "verbatim", "true verbatim" and "full verbatim".
The app has no verbatim or clean-verbatim switch (nothing in app/src offers one). What a person can control is punctuation (on by default) and speaker labels. Speech the engine cannot make out is marked inaudible instead of guessed. Do not confuse this with the word 'verbatim' in the export code: there a 'verbatim SRT' only means one cue per segment with no line wrapping or splitting. Whether the engine keeps every filler word is not documented in the files read, so no claim is made.
Spoken: 'So, uh, we we should, I mean, we should move the meeting to Tuesday.' Verbatim keeps all of it, including 'uh', the doubled 'we' and the restart after 'I mean'.
Verbatim transcription writes down everything said, including stutters, false starts and sounds, so the text mirrors the speech as closely as possible. It is the most literal transcription style and the opposite of a cleaned-up transcript.
The app has no verbatim or clean-verbatim switch (nothing in app/src offers one). What a person can control is punctuation (on by default) and speaker labels.
Verbatim keeps everything spoken, including stutters, false starts and filler sounds. The full answer, with sources, is on the page for Clean verbatim vs verbatim.
It rests on Wikipedia, Transcription (service) and Wikipedia, Speech disfluency, read on 22 October 2026. What each source supports is listed above, next to its link.
Spoken: 'So, uh, we we should, I mean, we should move the meeting to Tuesday.' Verbatim keeps all of it, including 'uh', the doubled 'we' and the restart after 'I mean'.
Send Autrans into your next meeting, use it in the room, or upload a recording. Your first 30 minutes are free, given once, and no credit card is needed to start.
Last checked 22 October 2026. How we measure accuracy. Spotted a mistake? Write to hello@autrans.online.