Free Norwegian transcription is worth a clip test, since dialects vary a lot. Published tests of others on the earlier large-v2 model give a word error rate of 9.5 for Norwegian; there was no large-v3 figure for Potok. Compare thirty seconds of text with your audio.
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 9.5 is from published tests of others on large-v2, as no large-v3 figure was found; it is not our measurement.
- Norwegian has two written standards, Bokmal and Nynorsk, so a spelling gap may be a standard choice.
- Spoken dialects can sit far from either written form.
- A short test shows more than a score does.
What a transcript looks like
[00:00] Speaker 1: La oss begynne møtet. Først går vi gjennom resultatene fra forrige uke, og deretter planlegger vi de neste stegene.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 |
|---|---|---|---|
| Norwegian (Norsk) | Recommended | word error rate 9.5% (large-v2, FLEURS) Whisper paper | Published tests show a low error rate for this language. No large-v3 figure was found; the figure is from the earlier large-v2 model. |
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
- Pick your own dialect. Cut a clip where the speaker talks the way you need the tool to handle.
- Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
- Note the written standard. See which spelling the text uses and whether that suits your readers.
- Check compound words. Norwegian joins words together; verify that long compounds are kept whole.
- Export and decide. Save the transcript as TXT, DOCX, PDF, SRT or VTT, or send a bigger file up to 2 GB.
| 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 |
|---|---|---|
| Testing with one clean newsreader | It hides how the tool handles your regional speech. | Include your local dialect. |
| Calling every spelling difference a mistake | Two standards are in everyday use. | Pick the one you want and judge against it. |
| Ignoring split compounds | A broken compound changes the reading. | Scan the long words in the result. |
| Testing with a single speaker only | You never see how the tool separates voices at a family table. | Switch on speaker labels and try a clip with two people. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Which Norwegian does the tool write?
Expect a standard written form; check that it matches what you need.
Where does 9.5 come from?
From published tests of others on large-v2, not from our measurements.
Is the model the newest one?
No large-v3 figure was found, so the one quoted is for large-v2.
Can I get an English version?
No. The transcript stays in the language of the recording.
Should I test more than one clip?
Yes. A calm clip and a noisy one show the range of results you can expect from the same tool.
Is there a size limit?
Files up to 2 GB are accepted, and a longer result comes back as a file you can save and open elsewhere.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · checked
- Whisper paper, Table 13 (large-v2 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