To convert Russian audio to text, send the file to the Potok bot on Telegram. Russian is handled by a model built for Russian speech, so figures published for the general model do not apply and none is quoted here. Files up to 2 GB work, and you can export 6 formats.
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
- No error rate is shown because published figures for the general model do not describe the Russian model.
- The 6 export formats are TXT, MD, DOCX, PDF, SRT and VTT.
- Russian is written in the Cyrillic alphabet, so open the file in an editor that supports Unicode.
- The letter yo is often written as plain ye in everyday texts, which affects searching.
- Stress is not written in everyday Russian, so the text will not show which syllable was stressed.
What a transcript looks like
[00:00] Speaker 1: Давайте начнём встречу. Сначала разберём итоги прошлой недели, потом спланируем следующие шаги.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 |
|---|---|---|---|
| Russian (Русский) | Recommended | No published figure | A model built for Russian speech is used for this language, so the published figures for other models do not apply. |
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
- Skip the score hunt. No borrowed percentage applies, so plan to judge quality on your own sample.
- Open the bot. Open @potok_now_bot in Telegram and send audio, video or a forwarded voice message.
- Use Upload for big files. The limit is 2 GB per file. Press Upload in the mini app when the chat attachment fails.
- Read a sample. Listen to a minute and read the same minute. If it is close, send the rest the same way.
- Check proper names. Surnames, firms and abbreviations are where a human check pays off.
- Pick the format. DOCX or PDF to share, SRT or VTT for captions, TXT or MD for notes.
| 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 a percentage that was never measured for this model | A borrowed number would be wrong. | Say that no figure is published. |
| Searching for one spelling of the dotted letter | Texts with and without the dot do not match. | Search both forms. |
| Sending the file through a messenger that squeezes audio | Detail is lost before the bot sees it. | Send the original. |
| Assuming Latin spelling for names | Names appear in Russian letters. | Transliterate by hand if a form needs it. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why no word error rate?
Russian uses its own model, and published results for the general model do not apply to it.
How many export formats are there?
Six: TXT, MD, DOCX, PDF, SRT and VTT.
Is the desktop dictation app the same thing?
No. It is a separate app that dictates into other programs and recognises Russian; this page is about the Telegram bot.
Is there a size limit?
Yes, 2 GB per file, with Upload for large ones.
Is the text translated?
No. The transcript stays in Russian, 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.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · 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