Norwegian speech to text in Potok is a recommended language, with a published word error rate of 9.5 from the earlier large-v2 model. No large-v3 figure was found. The number is from other people's tests, not our measurement. Send a voice note, audio or video to the Telegram bot.
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
- Norway has two written standards, Bokmal and Nynorsk, and the published figure does not say which one was used.
- Spoken dialects differ a lot from region to region, so a recording from a small town may read less cleanly than a news-style one.
- Large-v2 is the earlier model; a newer one could land higher or lower on your speech.
- The letters ae, o with a slash and a with a ring are ordinary output, so check that they survive in your editor.
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
- Note the speaker's region. If the person speaks a strong local dialect, expect to correct more. Say so in your own notes.
- Send the file. Open @potok_now_bot in Telegram and attach audio or video, forward a voice message, or paste a link.
- Large recordings. A file can be up to 2 GB. The Upload button in the bot's mini app is the route for the biggest.
- Proofread spelling variants. Some words have more than one accepted spelling, so decide on one and edit toward it.
- Check the special letters. Open the DOCX or TXT in your editor and confirm the Norwegian letters display correctly.
- Export what you need. TXT, MD, DOCX, PDF, SRT or VTT are all offered.
| 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 fixed written form | Spoken dialect can come out in a mix of spellings. | Pick the standard you want and edit once at the end. |
| Citing 9.5 without the model | It was published for large-v2. | Mention the model name next to the number. |
| Using a recording with two people talking over each other | Overlap lowers the quality of both lines. | Ask speakers to take turns when possible. |
| Opening a TXT file in an editor with the wrong encoding | Special letters can appear broken. | Open it as UTF-8 or use DOCX. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the published figure for Norwegian?
A word error rate of 9.5 for the large-v2 model, reported by others.
Does it handle dialects?
Published figures do not split by dialect, so try a short clip from your speaker before sending a long file.
Is Nynorsk covered?
The published tests do not say which standard they used, so treat Nynorsk as untested and check the output.
Do I get subtitles?
Yes. Turn timestamps on and export SRT or VTT.
Is the transcript turned into English?
No. The text stays in the language of your 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
- 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