Convert Swedish audio to text

By the Potok teamUpdated ~2 min read

Potok will convert Swedish audio to text once you send the recording to its Telegram bot. Published tests of others on large-v3, not our measurements, report a word error rate of 7.88 for Swedish. Files up to 2 GB are accepted, with the result as chat text or a file.

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 writes compound words as one long word, so a split in the wrong place counts as an error.
  • Three extra letters, a with a ring and two with dots, must display correctly.
  • A pitch accent changes some word pairs in speech, but writing does not mark it, so context decides.
  • At 7.88, expect a clean draft that still needs a human read for names and numbers.
  • Numbers, dates and times in Swedish can be spoken in several ways, so check the digits against the audio.

What a transcript looks like

Sample sentence in Swedish
[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

Quality for this language
LanguageVerdictPublished resultNotes
Swedish (Svenska)Recommendedword 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

  1. Think about compounds. If your text has long technical compounds, plan to search for the ones you use.
  2. Open the bot. Open @potok_now_bot and send the file.
  3. Bigger than a chat allows? Press Upload in the mini app, up to 2 GB.
  4. Look at the special letters. Check that the ring and dotted letters show in the export.
  5. Join or split compounds. Search for words that were split in two and join them.
  6. Export. DOCX or TXT to edit, SRT or VTT for subtitles.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Leaving a compound splitA split compound reads oddly and may change meaning.Join it.
Reading dialect forms as errorsRegional speech is written as heard.Normalise if needed.
Using an editor with no Swedish lettersLetters turn into symbols.Use Unicode.
Not labelling a panelVoices blend.Turn on speaker labels.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

What does 7.88 tell me?

It is a published word error rate on large-v3, about eight wrong words per hundred in those tests.

Are compound words a problem?

They can be. A compound may come back split, so search for the terms you rely on.

What is the file limit?

The limit is 2 GB per file. For anything too big for a normal chat attachment, use the Upload button in the mini app.

Can I get timestamps?

Yes, you can switch timestamps on before sending the file and export SRT or VTT afterwards.

Is the text translated?

No. The transcript stays in Swedish, 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.

  1. Word error rate (Wikipedia), Wikipedia · checked
  2. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  3. 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