Potok offers Ukrainian transcription in Telegram and returns Ukrainian text. Published large-v3 results range from 6.51 to 11.5 word error rate, depending on the test set. Files up to 2 GB are accepted, and both labels and timestamps are optional.
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 range of 6.51 to 11.5 is a word error rate from tests by others, not our measurement.
- The spread shows that results depend on the data, so your recording may land anywhere in it.
- Ukrainian uses the Cyrillic alphabet with letters of its own, including the apostrophe in some words.
- Short results arrive in the chat, long ones as a file.
- Names of places and people are the usual weak spot, so check them against a reliable source.
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
- Start in the chat. Open @potok_now_bot and send the clip.
- Send a link or a file. A YouTube link, a forwarded voice message, audio or video all work, up to 2 GB.
- Choose labels. They split a conversation into numbered turns.
- Read the result against a sample of audio. Check a few minutes with the recording playing.
- Check the apostrophe. See that words which need it are written with it.
- Export. 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 number | 6.51 flatters the average. | Quote the whole range of published results. |
| Assuming the text is Russian-like | Spelling rules differ, so copying edits from Russian text corrupts the result. | Edit with a Ukrainian spell-checker. |
| Losing the apostrophe in a copy | A word is written wrongly. | Search for the words that need it. |
| Using speaker numbers as names | Quotes cannot be attributed. | Add names by hand. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the published error rate for Ukrainian?
Large-v3 results range from 6.51 to 11.5 word error rate in tests by others.
Why such a wide range?
Different test sets and conditions give different results, so yours may differ.
Does the bot separate speakers?
It can mark turns as Speaker 1, Speaker 2 and so on.
Can I download subtitles?
Yes, SRT and VTT are among the exports.
Is the text translated from Ukrainian?
No. It stays in Ukrainian, written as it was spoken in the recording.
Does the bot add real names for the speakers?
No. It knows only numbered labels, so you add names yourself after export.
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