Ukrainian speech to text in Potok is a recommended language. Published tests of the large-v3 model range from a word error rate of 6.51 to 11.5, depending on the data. These are other people's tests, not our measurements. Send voice notes, audio or video to the bot.
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 gap between the best and worst figures shows that results depend on the recordings used, so expect yours to land somewhere in the range.
- Ukrainian is written in the Cyrillic script, and the exported files keep it as spoken.
- Speakers who mix Ukrainian and Russian within a sentence are harder to write down cleanly.
- Some letters have no equivalent in Russian, so check that they appear correctly in the text.
What a transcript looks like
[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
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Ukrainian (Українська) | Recommended | word 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
- Judge your audio. Clean studio speech tends toward the lower figure; noisy calls tend toward the upper end. Decide which kind of audio you have before you read the result.
- Message the bot. Open @potok_now_bot and attach the file, forward a voice message or paste a link.
- Large uploads. The limit is 2 GB; use Upload in the mini app for big files.
- Look at mixed passages. Find sentences where the speaker switches language and compare with the sound.
- Proofread names. Place names and surnames are spelled by sound and need a check.
- Export. Pick TXT, MD, DOCX, PDF, SRT or VTT.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Quoting only the best figure | Another published test gave a much higher error. | Give the range. |
| Ignoring mixed-language speech | Words can be written in the wrong language. | Mark and correct those lines. |
| Recording on a speakerphone | Echo adds mistakes. | Hold the phone near the speaker. |
| Forgetting timestamps for video | You cannot line text up with the picture. | Export SRT or VTT. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What are the published scores?
Large-v3 results range from a word error rate of 6.51 to 11.5 in published tests.
Why such a spread?
The tests used different data, so results change with the recordings.
Are those your own tests?
No. They come from people who published them.
Does mixed Ukrainian and Russian speech work?
Both may appear, but passages that switch should be checked against the audio.
Is the text turned into another language?
No. It stays in Ukrainian, as spoken, and the bot does not make a version in another language.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · checked
- 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