Potok transcribes Russian speech; this site has been translated into English for convenience.
You can turn a Telegram voice message into text with the Potok bot [@potok_now_bot](https://t.me/potok_now_bot): forward the recording or send a file, and a short transcript arrives as text in the chat, a long one as a file. 60 minutes per month are free, then by subscription. For large recordings and meetings there is a bot mini app with file uploads up to 2 GB.
A voice message and a video note in Telegram already have their own “Transcribe” button: without Telegram Premium it gives a few transcripts per week, with Premium there is no limit on the number, and the text stays inside the message itself, with no file and no export. The Potok bot @potok_now_bot does not limit the number of messages: it accepts files and links to videos, and adds the “Summary” button and other tools to the text.
How the bot in Telegram transcribes a voice message
The order of actions is the same for a voice message, an audio file or a video.
- Open the bot @potok_now_bot in Telegram and press “Start” (the command
/start). - Forward a voice message to it from any chat, send an audio or video file (it can be as a document), or give a link to YouTube, VK Video or RuTube.
- Wait for the reply: a short recording arrives as text right in the chat, a long one as a separate file. The file format (TXT or DOCX) is set in advance in the bot settings (
/settings). - In the same settings you can turn on timecodes
[mm:ss]and speaker labeling in advance: then the lines in the finished text will be labeled “Speaker 1”, “Speaker 2” and so on.
In groups where the bot was added by an administrator, it takes voice messages, video notes and audio up to 10 minutes long into work; forwarding them to private messages is not required. How to deal with a Telegram video note specifically is covered separately in the article about turning a video note into text. For larger recordings and for files that are inconvenient to upload from a phone there is the bot's mini app: sign in by email or through Telegram, drag a file of up to 2 GB into the browser whole or give a link to a video; the recordings and access there are shared with the bot.
What the bot sends in reply
The bot's reply is not bare text but a ready transcript with several ways to process it further:
- a short recording as text right in the chat, a long one as a separate file in the chosen format;
- with the settings turned on, timecodes
[mm:ss]and speaker labels (“Speaker 1”, “Speaker 2”: the bot does not determine the participants' names, only the numbers of the lines); - under the text, the “Summary” button with the main points of the recording and tasks for each speaker;
- the “Tasks and deadlines” button, a separate list of who has to do what and by when;
- the “Ask” button: you can ask your own question about the content of the recording and get an answer from the text;
- the “Other format” button: export of the finished text to TXT, DOCX, Markdown, PDF, SRT or VTT (the last two are subtitle files).
All transcripts stay in the “My recordings” section and can be opened again at any moment: you do not need to forward the recording again if you need another format or an answer to a new question about the text. How such a bot differs from other transcription services can be seen in the comparison of audio-to-text transcription services.
When the bot will not fit
The Potok bot is a cloud service: recognition runs on servers in Russia, and without the internet it does not work. If you need the recording right during a call and not after it, the bot will not help: it processes a ready file or a forwarded message, not a live conversation.
It will not fit where translation into another language is needed either: the bot recognizes only Russian speech. It tells speakers apart by the numbers of lines, not by names; if the real names of the participants are essential in the text, you will have to add them by hand. The bot will not accept a link to a recording in Instagram or TikTok either, only Telegram, YouTube, VK Video, RuTube and a whole file.
Frequently asked questions
Yes. In private messages you can forward a voice message from any chat to the bot or send a whole file, including as a document. In groups where the bot was added by an administrator, it takes voice messages, video notes and audio up to 10 minutes long.
Speaker labeling can be turned on in the bot settings: the lines are marked “Speaker 1”, “Speaker 2” and so on, by number. The bot does not determine the participants' names.
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).
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.
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.
Recording to text
Send a recording to Potok's Telegram bot or upload a file of up to 2 GB in the bot's mini app. The first 60 minutes of every month are free.
Open @potok_now_bot in TelegramPrimary sources: core.telegram.org · www.ixbt.com · developers.sber.ru · t.me
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.