Dutch transcription: audio and video to text

By the Potok teamUpdated ~2 min read

Potok is a strong choice for Dutch: published tests of the large-v3 model report a word error rate of 5.57, one of the lower figures on our list. Send Dutch voice messages, audio or video to the Telegram bot, with files up to 2 GB, and read the note about user reports below.

Transcribe a recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram

Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages

Key facts

  • The 5.57 word error rate is a published test result, not a measurement we made.
  • Some users report that large-v3 does worse than the earlier model on their own Dutch data, so benchmarks and real audio can differ.
  • Dutch writes many compound words as one, and the test figure says nothing about how they are split.
  • The transcript stays in Dutch; nothing is translated.

What a transcript looks like

Sample sentence in Dutch
[00:00] Speaker 1: Laten we de vergadering beginnen. Eerst bespreken we de resultaten van vorige week, daarna plannen we de volgende stappen.

Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.

Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.

Published quality

Quality for this language
LanguageVerdictPublished resultNotes
Dutch (Nederlands)Recommendedword error rate 5.57% (large-v3, FLEURS)
Canary-1B-v2 paper
Published tests show a low error rate for this language.
Some users report that large-v3 does worse than the earlier model on their own Dutch data.

These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.

How to do it

  1. Try your own sample. Because users report mixed experience, send a short file to @potok_now_bot and judge it before the big job.
  2. Then send the full recording. Voice notes, audio, video and YouTube links work. Up to 2 GB per file, with the mini app's Upload button for the largest.
  3. Use timestamps for meetings. They make it easy to return to a doubtful sentence.
  4. Fix compounds and names. Check how long compound words and surnames with prefixes appear.
  5. Export. TXT, MD, DOCX, PDF, SRT or VTT, depending on whether you need a record or captions.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Relying on the benchmark aloneYour accent, microphone or topic may give worse results than the test.Run a short real sample first.
Splitting compound wordsSpelling checks flag correct Dutch words.Join them in your editor.
Expecting separate handling of Flemish speechThe published figure gives one result for Dutch in general.Test clips from your own speakers.
Skipping a check of numbersA date or amount spoken quickly may be written wrongly.Verify figures against the audio.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

How accurate is Dutch transcription?

Published tests of the large-v3 model give a word error rate of 5.57 for Dutch. Treat it as another group's result.

What is the caveat for Dutch?

Some users report that large-v3 does worse than the earlier model on their own data, so a real sample matters more than the average.

Does it cover Belgian Dutch?

The published figure does not report Flemish speech separately, so check a clip from your own speakers.

Can I get a Word file?

Yes. DOCX is one of the export formats, along with PDF, TXT, MD, SRT and VTT.

Is Dutch speech translated?

No. You receive the Dutch text exactly as spoken, with no translation into another language offered.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. Word error rate (Wikipedia), Wikipedia · checked
  2. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  3. Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked

Try it on your own recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram