Convert Slovak audio to text

By the Potok teamUpdated ~2 min read

Use the Potok Telegram bot to convert Slovak audio to text: send the file and wait for the transcript. Published tests of others on the large-v3 model, not our measurements, give a word error rate of 8.4 for Slovak. Files up to 2 GB are accepted.

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

  • Slovak uses a hacek, an acute accent and a few extra marks, and length of a vowel can change a word.
  • It is close to Czech, so Czech spellings can slip into a transcript when speech is fast.
  • A score of 8.4 comes from tests on clean read speech, so spontaneous talk may do worse.
  • Declension changes word endings, which is the first thing to check in a proofread.
  • Names of towns and people often have a Czech or Hungarian variant, so confirm which one your document should use.

What a transcript looks like

Sample sentence in Slovak
[00:00] Speaker 1: Začnime stretnutie. Najprv prejdeme výsledky z minulého týždňa a potom naplánujeme ďalšie kroky.

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
Slovak (Slovenčina)Recommendedword error rate 8.4% (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. Check the recording quality. Fast spontaneous Slovak with background noise is harder than a read text. Pick the cleanest take.
  2. Open the bot. Open @potok_now_bot and send your file.
  3. Go through Upload if needed. The mini app's Upload button takes files up to 2 GB.
  4. Look at long and short vowels. Compare accents on vowels with the audio, since they separate real words.
  5. Scan for Czech-looking forms. If a word looks Czech, check how your readers spell it in Slovak.
  6. Export. Use DOCX or TXT to edit and SRT or VTT for captions.
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
Ignoring accent marksA missing mark gives a different or non-existent word.Spot-check them.
Letting Czech spellings stayThe languages are close but not the same.Replace them.
Taking 8.4 as a promiseIt is an average from others' tests.Proofread.
Forgetting that names inflectEndings change in speech.Restore the nominative form where needed.

More

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

Frequently asked questions

How accurate is Slovak?

The published word error rate is 8.4 on large-v3. It is an average over test speech, not a promise.

Can Slovak and Czech be confused?

They are close, so check the output for spellings that belong to the other language.

What is the largest file?

2 GB, with the Upload button for big ones.

Can I label speakers?

Yes, with numbers such as Speaker 1. Real names are not known.

Is the text translated?

No. The transcript stays in Slovak, 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