Free Danish transcription: test any tool on a short clip

By the Potok teamUpdated ~2 min read

To test a free Danish transcription tool, use a clip where people speak softly and fast, then compare text and sound. Potok relies on a published word error rate of 12.57 for Danish with large-v3, measured by others and not on your recording.

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 12.57 is a word error rate for large-v3 in a published test, not our measurement.
  • Spoken Danish often swallows word endings, so a clip with relaxed speech shows real weaknesses.
  • Compound words are written together, and a tool may split them wrongly.
  • The transcript stays in Danish and is not translated.

What a transcript looks like

Sample sentence in Danish
[00:00] Speaker 1: Lad os begynde mødet. Først gennemgår vi sidste uges resultater, og derefter planlægger vi de næste skridt.

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
Danish (Dansk)Recommendedword error rate 12.57% (large-v3, FLEURS)
Canary-1B-v2 paper
Published tests show a low error rate for this language.

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. Pick relaxed speech. Choose a casual conversation rather than a read-out text, since that is where gaps appear.
  2. Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message or an audio file.
  3. Hunt for split compounds. Danish writes many compounds as one word. Note any that arrive as two.
  4. Mark swallowed endings. Where the speaker trails off, check whether the tool invents an ending or leaves it out.
  5. Go to the full file. Up to 2 GB is accepted, with Upload in the mini app. Short results land in the chat; long ones arrive as a file.
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
Testing only with read-aloud speechIt sounds clean and hides trouble with natural talk.Include a stretch of casual conversation.
Ignoring split compound wordsMeaning can change when a word is cut in two.Mark them while comparing.
Trusting a guess where the speaker trails offThe tool may fill in a plausible but wrong ending.Check unclear spots against the audio.
Quoting 12.57 as your resultIt describes other recordings.Run your own clip.

More

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

Frequently asked questions

How is Danish rated?

Danish is among the languages with good published results; large-v3 shows a word error rate of 12.57.

Why use casual speech for a test?

Relaxed talk is harder than read text, so it shows more of a tool's limits.

Are results long files or chat messages?

A short result comes as text in the chat, and a long one arrives as a file.

Can I save a subtitle file?

Yes. SRT and VTT exports exist, and they work best when timestamps were switched on before you sent the file.

Will I receive English text?

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.

  1. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  2. Word error rate (Wikipedia), Wikipedia · 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