Convert Croatian audio to text

By the Potok teamUpdated ~2 min read

To convert Croatian audio to text with Potok, send the recording to the Telegram bot and wait for the reply. Published tests of others on large-v3, not our measurements, report a word error rate of 11.07 for Croatian. Files up to 2 GB are accepted, and the transcript is not translated.

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

  • Word error rate counts the share of words that differ from a correct reference, so lower is better.
  • Croatian is written in the Latin alphabet with a few extra letters carrying diacritics.
  • Regional speech can differ in vocabulary, so test a sample from your speaker.
  • The transcript stays Croatian.

What a transcript looks like

Sample sentence in Croatian
[00:00] Speaker 1: Počnimo sastanak. Prvo ćemo pregledati rezultate prošlog tjedna, a zatim isplanirati sljedeće korake.

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
Croatian (Hrvatski)Recommendedword error rate 11.07% (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 audio quality. Play a minute through headphones. If you can follow it easily, a recogniser usually can too.
  2. Open the bot. Open @potok_now_bot in Telegram.
  3. Send the file. Attach the audio, video or YouTube link. A file can be up to 2 GB; use the Upload button for bigger ones.
  4. Scan for letters with marks. Look at words that should carry a diacritic. Wrong marks are among the commonest small errors.
  5. Export. DOCX or TXT for editing, 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
Ignoring diacritics in the outputA missing mark can change how a word reads.Search the text for the letters that carry marks and correct them.
Sending a lecture full of foreign termsForeign names inside the speech lower accuracy.Proofread those lines against a term list.
Treating the score as exact11.07 is an average from other people's tests.Judge by your own recording.
Recording from far awayDistance adds echo.Place the microphone near the speaker.

More

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

Frequently asked questions

How accurate is Croatian?

Published tests of others report a word error rate of 11.07 on large-v3, which counts as good, but they are not our own measurements.

Will the bot translate the text?

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

Can it handle a phone call recording?

Yes, if the audio is clear. Narrowband call audio usually scores worse than studio sound.

What are the size limits?

Up to 2 GB per file. For a large one use the Upload button of the mini app.

Can I get timestamps?

Yes. Switch them on before sending and export SRT or VTT.

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