Convert Ukrainian audio to text

By the Potok teamUpdated ~2 min read

Send a Ukrainian recording to the Potok bot on Telegram to convert Ukrainian audio to text. Published tests of others on large-v3, not our measurements, give a word error rate of 6.51, though other results range up to 11.5. 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

  • Published large-v3 results range from 6.51 to 11.5, so the real figure depends on the test data.
  • Ukrainian has letters that Russian lacks, so a plain Russian-style letter in the text is a sign of an error.
  • Speech that mixes Ukrainian and Russian is hard for any system, and the text may switch spelling.
  • Writing is in the Cyrillic alphabet, so use an editor that supports Unicode.
  • Several place names have a Ukrainian and a Russian form, so confirm which spelling your document uses.

What a transcript looks like

Sample sentence in Ukrainian
[00:00] Speaker 1: Почнімо нараду. Спочатку розглянемо результати минулого тижня, а потім сплануємо наступні кроки.

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
Ukrainian (Українська)Recommendedword error rate 6.51% (large-v3, FLEURS)
Canary-1B-v2 paper, Whale paper
Published tests show a low error rate for this language.
Published large-v3 results range from 6.51 to 11.5.

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 speech first. Note whether the recording stays in one language. Mixed speech needs more attention later.
  2. Open the bot. Open @potok_now_bot in Telegram and send the file.
  3. Send a long recording. Up to 2 GB goes through. Use Upload in the mini app if the chat refuses it.
  4. Look for Ukrainian-only letters. Search for places where a letter from the neighbouring alphabet appears by mistake.
  5. Check proper names. Place names and surnames vary in spelling.
  6. Export. DOCX or TXT to edit, 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
Quoting only the best resultThe range goes up to 11.5.Quote both ends.
Ignoring mixed-language passagesThe text may switch spelling.Review them separately.
Not checking apostrophesUkrainian uses an apostrophe inside some words.Search for the marks.
Skipping speaker labels in a meetingVoices blend together.Switch the numbered labels on.

More

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

Frequently asked questions

Which number should I trust?

The lowest published large-v3 result is 6.51 and others reach 11.5. Treat the range as the honest answer.

Are Ukrainian letters kept?

Yes. The text is written in Ukrainian, so open it with Unicode support.

What is the file limit?

2 GB per file, with Upload for large ones.

Did you measure the 6.51?

No. It comes from published tests by other people.

Is the text translated?

No. The transcript stays in Ukrainian, 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
  4. Whale paper, Table 5 (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