Norwegian audio and video sent to Potok come back as Norwegian text with optional speaker labels and timestamps. Published tests of the earlier large-v2 model report a word error rate of 9.5, since no large-v3 figure was found. Files up to 2 GB are accepted, and results export to six formats.
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 a word error rate for large-v2 taken from published tests, not a measurement of ours.
- Norwegian has two written standards, Bokmal and Nynorsk, while speech follows regional dialects.
- Long compound words are written as one word, which affects how errors are counted.
- Speaker labels are numbered, and real names must be added by hand.
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
- Prepare the recording. A clear single-channel voice file is easiest, but video, a voice message or a YouTube link also work.
- Send it. Open @potok_now_bot and post the file. Over a few hundred megabytes, use the Upload button; the limit is 2 GB.
- Pick the layout. Choose speaker labels when more than one person talks, and timestamps when you will cite the recording.
- Compare the written form with your target. Decide whether the output matches the standard your document needs.
- Save the result. TXT, MD, DOCX, PDF, SRT or VTT.
| 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 |
|---|---|---|
| Assuming the dialect is written as spoken | Text may follow one standard while the voice follows another. | Read it against what the speaker actually said. |
| Splitting compound words in the editor | Spell-check suggestions create two words where one was right. | Keep compounds joined unless a reference says otherwise. |
| Publishing the 9.5 as our result | It misstates who measured it. | Say it is from published tests of large-v2. |
| Using the labels as names | Speaker 2 means nothing to a reader. | Replace each label with a real name. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is the Norwegian transcript in Bokmal or Nynorsk?
The output is written Norwegian. Check it against the standard your readers expect, since both are in use.
Where does 9.5 come from?
From published tests of the large-v2 model. These are results of other groups, not tests we ran.
Can the bot make SRT subtitles?
Yes. Export SRT or VTT and trim any long lines.
Does it separate speakers?
It can mark turns as Speaker 1, Speaker 2 and so on once you enable labels.
Is there a version in English?
No. The transcript stays in Norwegian, and the bot adds no text in any other language.
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
- 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