The Potok Telegram bot can convert Norwegian audio to text; just send the file. No large-v3 figure was found for Norwegian, so published tests of others on the earlier large-v2 model, not our measurements, give a word error rate of 9.5. Files up to 2 GB are fine.
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 large-v2, an earlier model, because no newer figure turned up for Norwegian.
- Norwegian has two written standards, Bokmal and Nynorsk, and speech does not say which one to write.
- Spoken dialects differ a lot across regions, and the text follows the sound.
- Three extra letters appear in the output, so use a Unicode editor.
- Speech with Swedish or Danish loan words is a common source of odd spellings, so scan for them after the first pass.
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
- Decide on the written form. Know whether your readers expect Bokmal or Nynorsk. Plan to adjust spelling afterwards if the transcript uses the other.
- Open the bot. Open @potok_now_bot in Telegram and attach the recording.
- Send big files with Upload. Recordings up to 2 GB go through the mini app's Upload button.
- Read the dialect passages. Strong regional speech is where the text most often drifts from standard spelling.
- Switch on timestamps if citing. They help when you need to point at a minute in the recording.
- Export. DOCX or TXT for edits, SRT or VTT for subtitles.
| 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 |
|---|---|---|
| Expecting one spelling standard | The bot writes what it hears, which may mix forms. | Normalise spelling in one pass. |
| Using a plain-text tool that cannot show Norwegian letters | Special letters turn into symbols. | Open the DOCX or a UTF-8 text file. |
| Leaving place names unchecked | Local names are easy to misspell. | Compare with a map or a source. |
| Mixing in Swedish or Danish quotes | Closely related speech in one file confuses the output. | Split the file at the change. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is the 9.5 recent?
It comes from the earlier large-v2 model in published tests by others, not from us.
Does it choose Bokmal or Nynorsk?
It writes what it hears, so check the form and adjust to your standard.
Is there a size limit?
Yes, 2 GB per file, with Upload for large ones.
Can I get SRT subtitles?
Yes, export SRT or VTT after turning timestamps on.
Does the transcript get translated?
No. The transcript stays in Norwegian, the same language as the recording you send, and it is never converted into another one.
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