Swedish speech to text in Potok is a recommended language, with a published word error rate of 7.88 for the large-v3 model. This is a result from other people's tests, not our measurement. Send voice notes, audio or video to the bot and read the first page before you share the text.
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
- Swedish builds long compound words, and word error rate counts a wrongly split compound as an error even when the sound is right.
- The letters with a ring and with two dots are normal output, so check they survive in your editor.
- A score of 7.88 means roughly one word in thirteen can differ from a human reference.
- Several regional accents exist, and the published figure does not break them out.
What a transcript looks like
[00:00] Speaker 1: Låt oss börja mötet. Först går vi igenom förra veckans resultat, sedan planerar vi nästa steg.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 |
|---|---|---|---|
| Swedish (Svenska) | Recommended | word error rate 7.88% (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
- Pick a test minute. Choose a stretch with plain speech, then one with names, to see where mistakes cluster.
- Send the file. Open @potok_now_bot in Telegram and send audio, video, a forwarded voice message or a link.
- Large files. Anything up to 2 GB; press Upload in the mini app for the heaviest.
- Check compounds. Scan for words that were split in two or glued together wrongly.
- Check special letters. Open the file in your editor and look at the ring and two-dot letters.
- Export. Pick 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 |
|---|---|---|
| Counting a split compound as a sound error | The speech may be right while the spelling is not. | Read the text, not just the score. |
| Quoting 7.88 as our measurement | It is a published figure. | Cite it as a result from tests of others. |
| Recording two speakers on one weak microphone | Voices overlap. | Use separate microphones if you can. |
| Pasting the text where the encoding is wrong | Special letters turn into symbols. | Use UTF-8 or DOCX. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the published figure?
A word error rate of 7.88 for the large-v3 model on Swedish.
Who published it?
Other people did. We did not run our own measurement.
Why do compounds matter?
Word error rate counts words, so a split or joined compound can count against a transcript that sounds correct.
Can I get subtitles?
Yes. Turn timestamps on and export SRT or VTT.
Does the bot change the transcript into another language?
No. It stays in Swedish, written the way it was spoken, with no second language version.
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
- 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