To compare free Dutch transcription tools, run your own short clip through each and keep the results side by side. Potok cites a published word error rate of 5.57 for Dutch with large-v3, yet some users report that large-v3 does worse than the earlier model on their data.
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 is a word error rate for large-v3 from a published test, not our measurement.
- Reports from users who ran their own Dutch recordings are mixed, which is why a personal sample beats a headline score.
- That mixed picture is a reason to test with your own audio rather than lean on one number.
- The transcript stays in Dutch and is not translated.
What a transcript looks like
[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
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Dutch (Nederlands) | Recommended | word 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
- Make your own sample. Take a minute from the kind of recording you really have: a meeting, a lecture or an interview.
- Open the bot. Open @potok_now_bot in Telegram and send the sample as a voice message or an audio file.
- Send the same file to other tools. Use identical audio so any difference belongs to the tool.
- Line the texts up. Paste the results into one document and mark where they disagree, then check those spots against the audio.
- Decide, then scale. Up to 2 GB is accepted, with Upload in the mini app. Export TXT or DOCX of the version you keep.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Relying on a benchmark alone | Users report cases where results fall short of the published figure. | Let your own sample break any tie. |
| Comparing tools on different files | You cannot tell whether the tool or the audio caused a gap. | Use one file for all. |
| Reading only the tool's summary page | Claims on a page say little about your recording. | Judge from the transcript you receive. |
| Skipping names and abbreviations | These expose weaker tools quickly. | Pick a sample that has some. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Dutch well supported?
Published results are good, with a word error rate of 5.57 for large-v3.
Why the warning about large-v3?
Some users report it doing worse than the earlier model on their own Dutch data, so a personal test is wise.
Can I check who said what?
Turn on speaker labels; they appear as numbers like Speaker 1.
Which file types can I send?
Voice messages, audio and video files, and YouTube links.
Can the output be turned into English?
No. The transcript stays in the language of the recording.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- 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