Send a Czech audio file to the Potok bot on Telegram to get it back as text. Published tests of others on large-v3, not our measurements, give a word error rate of 11, with reported results ranging from 11.0 to 11.33. 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
- The narrow spread between tests suggests that independent measurements mostly agree on Czech.
- Czech uses many accented letters, so check them in names and in short function words.
- Spoken Czech in casual talk can differ from the written standard, which may cost a few words.
- Export as TXT, MD, DOCX, PDF, SRT or VTT.
What a transcript looks like
[00:00] Speaker 1: Začněme schůzku. Nejdříve projdeme výsledky z minulého týdne a potom naplánujeme další 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
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Czech (Čeština) | Recommended | word error rate 11% (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 11.0 to 11.33. |
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
- Prepare the file. Trim long silences at the start and end if you can. It makes the result shorter to review and the file lighter to send.
- Open the bot. Open @potok_now_bot in Telegram.
- Send it. A voice note, an audio file, a video or a YouTube link all go through, up to 2 GB. Press Upload in the mini app for large files.
- Mark the unclear places. Where the audio is muffled, expect a wrong word. Note the time so you can listen again and correct it.
- Export and share. Pick the format for the next step, such as DOCX for editing or SRT for subtitles.
| 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 |
|---|---|---|
| Skipping the accented letters | A missing mark can turn one word into another. | Search for the common accented letters and correct them. |
| Sending several speakers without labels | The text runs together and you must sort out who spoke. | Turn on numbered speaker labels before sending. |
| Reading 11 as our own result | The figure comes from published tests of others. | Say where the number comes from when you quote it. |
| Using a clip from a loud street | Traffic noise hides soft consonants. | Record in a quieter place or move closer to the speaker. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How reliable is Czech transcription?
The published word error rate is 11 on large-v3, which counts as good. Your own audio may score differently.
Why is there a range of 11.0 to 11.33?
Different published tests of the same model report slightly different values, so we show the lowest as the headline.
Can I send a video?
Yes. Video files are read like audio, within the 2 GB limit.
Are timestamps available?
Yes. You can switch them on and export SRT or VTT.
Does it write numbers as digits?
That depends on the speech and context, so check dates and amounts 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.
- 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