How-to guides

How to add a voice message transcription bot to a Telegram group

Mark Vesyoly · founder of Potok · ~5 min

Potok transcribes Russian speech; this site has been translated into English for convenience.

To make voice message transcription work in a group, add the Potok Telegram bot @potok_now_bot there and make it an administrator: the bot sees the group messages if it is an administrator. In a group it takes voice messages, video notes and audio up to 10 minutes, and the text arrives at once, without a settings screen.

Voice messages in a group chat are not always convenient to listen to, and text is read at once. For this Potok has a Telegram bot, @potok_now_bot: it is enough to add it to the group and make it an administrator. Other ways to get text from voice are collected separately.

How to add a voice message transcription bot to a Telegram group

  1. Add @potok_now_bot to the group.
  2. Make the bot an administrator of the group: it sees the group messages if it is an administrator.
  3. The bot takes voice messages, video notes and audio up to 10 minutes long in the group: the text arrives at once, without a settings screen.

In private messages the bot works differently: there it transcribes voice messages, video notes, audio and video, accepts files and links, and the file format is chosen in the settings, and timecodes and speaker markup can be turned on. In a group the settings screen is not needed: the text arrives at once. The bot recognizes only Russian speech, and there is no translation. Recognition runs on Potok servers in Russia, and recordings and transcripts are stored there too; all transcripts stay in My recordings, and they can be opened again.

Which recordings the bot transcribes in a group chat

In a group the bot accepts only voice messages, video notes and audio up to 10 minutes. The bot does not accept videos, documents and links in a group. It recognizes only Russian speech, and there is no translation. The bot takes videos, documents and links in private messages: there it accepts voice messages from any chat, and files, including as a document, and links to YouTube, VK Video and RuTube. What else the bot can do in a private chat is described on the page about the transcription bot in Telegram.

Where Potok cannot do this

The Potok app for Windows, macOS and Linux is for dictation: hold the key, speak, release. It does not transcribe finished recordings and voice messages from chats; for them there is the Telegram bot @potok_now_bot. One subscription covers both the dictation app and the bot for recordings. There is no Potok app for Android and iPhone, and no voice commands or offline mode either. Recognition is in the cloud, runs on servers in Russia, and Potok does not work without the internet.

Frequently asked questions

Will the bot transcribe a video or a file sent to the group?

No. In a group the bot accepts only voice messages, video notes and audio up to 10 minutes. It takes videos, documents and links in private messages: forward the recording to the bot in a private chat or send the file there.

Do I need to open the settings screen for the transcription to arrive in the group?

No. In a group the text arrives at once, without a settings screen. The file format is chosen in the bot settings, and timecodes and speaker markup can be turned on.

How many recordings does the bot transcribe for free?

The bot transcribes 60 minutes per month for free, and the limit resets on the first of the month. The Potok subscription removes the limit both in the bot and in the dictation app.

How is transcription different from voice input?

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).

What is the difference between voice input and transcription?

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.

Can a Zoom call be transcribed automatically?

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.

Try it on your own recording

Potok's Telegram bot transcribes a voice message, video note, audio or video, and its buttons make a summary and a task list. 60 minutes per month for free.

Open @potok_now_bot in Telegram

Primary sources: support.microsoft.com · support.apple.com

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.

Mark Vesyoly — founder of Potok. Writes about Russian voice input: how to dictate in work apps, what gets in the way and how to fix it.
© Potok · Vladimir Olegovich Lipatnikov · INN 502915859701 · Public offer Comparisons · FAQ · About Free voice input · Voice input for AI chats · Data and Russian privacy law · Voice input on Mac · Bot plans · 14 days of Pro for a review