JustTranscribe

Benchmark · November 13, 2026

English transcription, measured: 80 minutes of real meetings

We ran eight real English meetings — four people around a table, several of them non-native speakers, talking over each other — through JustTranscribe and through OpenAI's whisper-1, and scored both against the human transcripts, word by word. On meetings the two are level: 23.1% word error rate for JustTranscribe, 22.4% for whisper-1. JustTranscribe put the right speaker on 94.3% of the words and finished each ten-minute recording in about eight seconds.

On clean read speech whisper-1 is ahead (4.9% against 6.3%). We publish both results, the method and the data, because “99% accurate” means nothing without the recordings behind it.

23.1%
word error rate, meetings
94.3%
words with the right speaker
7 of 8
meetings with the right number of speakers
≈8 s
to transcribe 10 minutes

Real meetings: the AMI Meeting Corpus

The AMI corpus is 100 hours of recorded meetings released by the University of Edinburgh and partners under CC BY 4.0, with human transcripts timed word by word. We took eight meetings from its three recording sites and used minutes 5:00 to 15:00 of each, from the single mixed recording of all the headsets, saved as a 64 kbps mono MP3 — the kind of file people upload.

MeetingWordsJustTranscribe WERwhisper-1 WERSpeakers foundRight speakerTime (ours / whisper-1)
ES2002aEdinburgh, design-team scenario1,42120.1%19%4 of 495.9%9 s / 35 s
ES2008aEdinburgh, design-team scenario1,49321.4%22.4%4 of 495%7 s / 25 s
IS1001aIdiap (Switzerland), design-team scenario1,23026.2%28.3%4 of 493.7%8 s / 28 s
IS1009aIdiap (Switzerland), design-team scenario1,43921.7%24.9%4 of 492.7%6 s / 24 s
TS3003aTNO (Netherlands), design-team scenario87518.5%16.8%3 of 397.4%8 s / 16 s
TS3005aTNO (Netherlands), design-team scenario1,08929.7%22.9%4 of 494.3%7 s / 22 s
EN2001aEdinburgh, real project meeting2,08515.6%15.4%4 of 596.1%6 s / 33 s
EN2002aEdinburgh, real project meeting2,25630.9%28.1%4 of 490.9%10 s / 36 s
All eight (80 min)11,88823.1%22.4%—94.3%61 s / 220 s

WER = substitutions + deletions + insertions, divided by the words in the human transcript. Lower is better. Bold marks the lower of the two.

Why a fifth of the words count as errors

Because of how people talk in meetings. Of JustTranscribe's 23.1 points, 16.2 are deletions — words in the human transcript that the tool left out — and only 6.3 are words it got wrong; whisper-1 shows the same pattern (16.9 and 4.6). The human transcribers wrote down every “yeah”, “okay” and half-started sentence, including the ones spoken underneath someone else. An automatic transcript of a single mixed recording follows the person who has the floor and drops most of what is said over them.

What that means for you: the transcript of a meeting reads as a clean account of who said what, and it is missing the cross-talk. If the overlapping remarks matter — a deposition, a negotiation — record each person on their own microphone, or expect to listen again at those moments.

Results vary by recording, which is why the table shows all eight and not an average alone: JustTranscribe had the lower error rate in three meetings and whisper-1 in five, and in one (TS3005a) whisper-1 was clearly ahead, 22.9% against 29.7%.

Speaker labels

JustTranscribe labels speakers as part of the same pass, with no setup. It found the right number of speakers in seven of the eight excerpts (in TS3003a that number is three: only three people speak in those ten minutes); in EN2001a five people speak and it found four. Among the words it transcribed correctly, 94.3% carried the right speaker (between 90.9% and 97.4% per meeting). whisper-1 does not label speakers, so it has no figure here.

Clean read speech: FLEURS

For the easy end of the range we used Google's FLEURS set (CC BY 4.0): 40 test sentences of US English, each read by a volunteer, joined into one 6.7-minute file after bringing every clip to the same loudness. whisper-1 scored 4.9% word error rate; JustTranscribe's engine scored 6.3% and 6.4% in two runs. This test counts “25” against “twenty-five” as an error for both, so both figures are higher than a reader would feel.

The same test in Latin American Spanish goes the other way — 2.0% for JustTranscribe against 3.0% for whisper-1 — which is where the product started. See Spanish audio to text.

Method

Data and sources

To cite: JustTranscribe, “English transcription benchmark”, November 13, 2026, justtranscribe.ai/reports/english-transcription-benchmark. Questions or a correction: hello@justtranscribe.ai.