Free Slovak transcription: test a tool with a clip

By the Potok teamUpdated ~2 min read

Free Slovak transcription can be put to the test with one short clip. Published tests of others report a large-v3 word error rate of 8.4 for Slovak, the model Potok uses. Pick speech with long words and diacritics, and watch for Czech-looking spellings creeping into 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

  • The score is a benchmark result from other people's recordings, so your own audio decides the real outcome.
  • Slovak and Czech are close, and a tool can slide into a Czech form of a word.
  • Soft consonants and long vowels carry marks that change the word.
  • A tidy result on a read-aloud sample can still hide errors on spontaneous talk.

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. Select a clip with Slovak-only words. Pick words that differ between Slovak and Czech, since they show whether the text drifts.
  2. Open the bot. Open @potok_now_bot in Telegram and send the clip as a voice message, an audio file or a video.
  3. Check each mark. Go through accents and soft signs, and tick the ones that match the audio.
  4. Look for Czech spellings. Mark any word that reads as Czech and decide whether it matters to you.
  5. Go long if it works. For longer material send files up to 2 GB and export TXT, DOCX, PDF, SRT or VTT.
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
Letting a Czech spelling passIt reads as a minor oddity but is wrong for a Slovak reader.List such words and fix them in one pass.
Testing with a news announcerThis is the easiest voice type there is.Add a clip of everyday conversation.
Ignoring long vowelsThe mark changes the word.Check long vowels in every sentence.
Skipping numbersSpoken numbers have several written forms.Compare each number to the audio.

More

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

Frequently asked questions

How close is Slovak to Czech for the tool?

They are similar enough that you should check for Czech spellings in your sample.

Is 8.4 your own number?

No. It is a published test result from others.

Which model does it relate to?

The figure is for large-v3, the same model that Potok uses.

Can I switch the language of the text?

No. The transcript stays in the language of the recording.

How large a file is allowed?

Files up to 2 GB are accepted, and the Upload button helps with big ones.

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