Slovak transcription: the text you receive

By the Potok teamUpdated ~2 min read

Slovak recordings sent to Potok come back as Slovak text, with the accents and carons that the language needs. Published large-v3 tests report a word error rate of 8.4. Send voice notes, audio, video or links in Telegram, with files up to 2 GB.

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 8.4 is a word error rate from published tests of others, not one we measured.
  • Slovak marks vowel length with an acute accent, and many consonants carry a caron, so one missing mark changes the word.
  • The bot writes the text only in Slovak and gives no version in another language.
  • Long results arrive as a file, short ones directly in the chat.

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. Open the bot and add a file. Choose @potok_now_bot and attach your Slovak clip.
  2. Pick extras. Speaker labels are useful for debates; timestamps help when you transcribe a town-hall recording.
  3. Wait for the file. Longer jobs return a document rather than a chat message.
  4. Check vowel length marks. Read a few passages for accents, as these are easy to lose.
  5. Review the consonant marks. Look at words with a caron, such as those in names of towns.
  6. Save it. TXT, MD, DOCX, PDF, SRT or VTT. Use Upload in the mini app if the file is near 2 GB.
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
Treating a missing accent as a typo to ignoreThe word may become a different word.Check meaning against context.
Assuming Czech and Slovak are interchangeableWords and spellings differ, so a Czech-style correction changes the text.Edit with a Slovak spell-checker.
Treating the 8.4 as a promiseNoisy audio can do worse.Present it as a published reference.

More

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

Frequently asked questions

Does the transcript keep Slovak accents?

Yes, the output is normal Slovak writing, though it is worth checking marks in names.

Where does 8.4 come from?

From published tests of large-v3 by others; we did not run them.

How do I get a timestamped transcript?

Turn on timestamps before sending, and each paragraph gets a time.

Can I use the text for captions?

Yes. SRT and VTT exports work for subtitles.

Does it work for Czech too?

Czech has its own page; this page is only about Slovak speech.

Are numbers and dates written in digits?

They usually appear as digits or words according to context, so check figures against the recording.

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