Czech speech to text with Potok falls in the recommended group. Published large-v3 results for Czech run from 11.0 to 11.33 word error rate, two sources that agree closely. These are other people's tests, not our measurements, so listen to a sample of your own audio.
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
- Two published sources land within a third of a point of each other, which is steadier than most languages.
- The lower end of the range is 11.0 and the upper end is 11.33.
- Czech diacritics such as the caron should appear in the text, and a missing mark is worth correcting.
- A word error rate is the share of words that differ from a reference.
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. Decide whether you need timestamps or speaker labels before sending.
- Send to the bot. Open @potok_now_bot in Telegram and attach the recording.
- Wait. Short results arrive in the chat, long ones as a file.
- Verify. Read one paragraph aloud against the transcript and check the diacritics.
- Export. Pick the format. Files up to 2 GB, with the Upload button for large ones.
- Keep the source audio. Hold on to the original file so any doubtful passage can be replayed against the text.
| 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 |
|---|---|---|
| Reading the range as a promise | It describes published tests, not your audio. | Sample first. |
| Ignoring diacritics | Meaning can change if a mark is missing. | Proofread them. |
| Using only one source for a report | Two figures give a better picture. | Cite both as published by others. |
| Sending bad audio | Poor recording hurts more than language. | Re-record if you can. |
| Cutting the file into many small pieces | Each piece loses the context of the previous one. | Send it whole, since 2 GB is allowed. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What is the published range?
From 11.0 to 11.33 word error rate for the large-v3 model, from two sources.
Whose tests are they?
They belong to others, and we did not run them ourselves.
Can I add timestamps?
Yes, turn them on before you export SRT or VTT.
How long a recording is allowed?
The limit is a file size of 2 GB, not a fixed length of audio.
Is the transcript in Czech?
Yes, and it stays in Czech because the bot does not translate.
Does the transcript keep the hooks and accents?
It should write Czech diacritics, but a missing mark on a name is worth correcting by hand.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · 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