Potok transcribes Russian speech; this site has been translated into English for convenience.
You can transcribe a video into text with the Potok bot [@potok_now_bot](https://t.me/potok_now_bot) or its web version: send a file or give a YouTube, VK Video or RuTube link, and you get the finished text, a short one right in the chat and a long one as a file. 60 minutes per month are free, and files of up to 2 GB are easier to upload in the web version.
A video can be turned into text in two ways: send a file or simply give a link to the video, and then the Potok bot @potok_now_bot or the bot's mini app does everything.
Transcribing a video step by step
- If the video is already a file on your computer or phone, send it to the bot in Telegram (you can send it as a document) or upload it to the Potok bot by dragging and dropping; files of up to 2 GB are accepted.
- If the video is on YouTube, VK Video or RuTube, send the bot or the web version a link to the video: you do not need to download it to a computer.
- Wait for the reply: a short recording comes as text right in the chat, a long one as a separate file (TXT or DOCX); in the web version the finished text opens at once on the recording page.
- If several people speak in the video, turn on timecodes and speaker labels in advance. In
the bot these are the
/settings, in the web version the card of the recording itself.
For long videos, lectures and webinars the web version is more convenient: it accepts a large file by drag and drop and does not break the upload on a poor connection, it resumes from the place where it was interrupted.
How to check and correct the transcript
The bot rereads a long transcript itself: it places punctuation and capital letters, removes obvious recognition errors, but it does not shorten the text or retell it in its own words, so details are not lost in a retelling.
It is easier to check against the original in the bot's mini app: it has a player, and a click on any phrase in the text plays the recording from exactly that place, so you do not need to rewind the video by hand to check a disputed word or name by ear. If the recording has several voices, speaker labels turned on in advance help here too: you can see at once whose line is whose, and it is easier to find the needed moment in a long conversation. The difference between such a transcript and ordinary dictation of text in real time is covered in detail in the article about transcription and voice input.
| Task | Characters | Typing (200 chars/min) | Voice (900 chars/min) |
|---|---|---|---|
| chat reply | 300 | 2 min | 0.5 min |
| 1500 | 8 min | 1.7 min | |
| post or meeting minutes | 4000 | 20 min | 4.4 min |
| article | 10000 | 50 min | 11.1 min |
When the bot does not fit
The Potok bot is a cloud service: recognition runs on servers in Russia, and it does not work without the internet. It will not accept a link to Instagram or TikTok, only Telegram, YouTube, VK Video, RuTube and a whole file.
It also does not fit where the video is not in Russian or where translation of the text into another language is needed: it recognizes only Russian speech, and there is no translation. It tells speakers in a recording apart by the numbers of the lines, not by names, and does not transcribe what is happening during a live broadcast or call, only an already finished recording. Why transcribing a conversation of several people is harder than ordinary dictation of one voice is explained in a separate review.
Frequently asked questions
Yes. Besides YouTube, the bot and the web version accept links to VK Video and RuTube: you do not need to download the file to a computer, a link to the video is enough.
Upload it whole: the bot's mini app accepts files of up to 2 GB, and the finished transcript comes as a separate file, TXT or DOCX, and not as text in the chat.
With Potok you can dictate the minutes live, speaking them during or right after the meeting. Transcribing an already recorded audio file of a meeting (a finished Zoom or Telemost recording) is a separate transcription task: such a file can be sent to Potok's Telegram bot @potok_now_bot.
Voice input is real-time dictation: you speak and immediately get text in the active field. Transcription turns an already finished audio or video recording (for example, a meeting recording) into text after the fact. The Potok app handles the first task, live dictation; finished recordings in Russian are transcribed by its Telegram bot @potok_now_bot.
Yes, several platforms have built-in meeting transcription: Zoom for cloud recordings, Microsoft Teams during the meeting, Google Meet on Google Workspace plans. The alternative is to record the sound and process it with a separate transcription service after the call. The Potok app does not do this kind of transcription, it is for live dictation; a call recording can be sent as a file to Potok's Telegram bot @potok_now_bot.
Voice input is real-time dictation into the active text field. Transcription turns an already finished audio or video recording (a lecture, a call, a podcast) into text after the fact, often with diarization (splitting by speaker).
Transcribe your own recording
Forward a voice message, or send a file or a YouTube, VK Video or RuTube link to Potok's Telegram bot, and the text arrives in the same chat. 60 minutes per month for free.
Open @potok_now_bot in TelegramPrimary sources: yandex.ru · vc.ru · speech2text.ru · audio-2-text.ru
Transcribe a recording in Telegram
Voice messages, video notes, audio and video are transcribed by Potok's Telegram bot @potok_now_bot: forward it a voice message from any chat, or send a file or a YouTube, VK Video or RuTube link. A short recording comes back as text in the chat, a long one as a file; timestamps and speaker labels can be turned on. The buttons give a short summary, tasks and deadlines, an answer to a question about the recording and export to TXT, DOCX, PDF or SRT. Large files, up to 2 GB, are easier to upload in the bot's mini app, via the Upload button next to the input field. The bot recognizes Russian speech; 60 minutes per month are free.