How-to guides

How to send audio or video to the bot as a file or document to transcribe it

Mark Vesyoly · founder of Potok · ~5 min

Potok turns speech into text in 33 languages, including English and Russian.

To transcribe a recording, send the bot @potok_now_bot audio or video as a file in private messages: sending as a document will do too. Documents do not work in groups. The bot sends short text to the chat and long text as a TXT or DOCX file. 60 minutes per month are free; for dictation there is the Potok app (potok.now).

The recording is a file, an interview, a lecture or a video from a meeting, and it needs to be turned into text. For this it is sent to the Potok Telegram bot @potok_now_bot in private messages.

How to send the bot audio or video as a document to transcribe

Act in a private chat with the bot, not in a group:

  1. Open the chat with the bot @potok_now_bot.
  2. Send it an audio or video file. Sending as a document will do too: in private messages the bot accepts a file including as a document, if it has sound or video in it.
  3. The bot does not take photos and stickers, so send a file with the recording.
  4. Wait for the reply. Timecodes and speaker markup can be turned on.
  5. Short text arrives as a message in the chat, long text as a file; the file format, TXT or DOCX, is chosen in the bot settings.

The finished transcript stays in the My recordings section, and it can be opened again. Other ways to work with voice and text are collected in the dictation guides. How the bot works overall, see the article about audio to text through a Telegram bot.

If the file is not transcribed

The first thing to check is where you are sending it. Documents do not work in groups: there the bot takes only voice messages, video notes and audio up to 10 minutes, and videos and files as a document must be sent to it in private messages. The bot will not take a photo or a sticker either: as a document it takes a file with sound or video in it. Speech in 100+ languages is recognized (the language is detected automatically), and there is no translation into another language.

When the bot will not suit

The bot transcribes finished recordings, and the Potok app dictates text into a field: they have one subscription, in the bot and in the app. The bot transcribes 60 minutes per month for free. The Potok app is a cloud one: the internet is needed for recognition. The bot transcribes recordings on Potok servers in Russia. For a video call the bot does not join it itself, so the meeting must be recorded by the program itself.

Frequently asked questions

Can I send the bot a video as a document?

Yes, in private messages the bot accepts audio and video as a file, including one sent as a document. Documents are not supported in groups.

Does sending as a document work in a group?

No. Documents do not work in groups: the bot takes only voice messages, video notes and audio up to 10 minutes there, and a file as a document must be sent to it in private messages.

Will the bot take a photo or a sticker?

No, the bot does not take photos and stickers. As a document it takes a file with sound or video in it, and there is nothing to transcribe in a picture or a sticker.

What do I get as the transcript?

A short recording arrives as a message in the chat, a long one as a file. The file format, TXT or DOCX, is chosen in the bot settings.

How to send audio or video to the bot as a file or document to: what to do and what to check?

How to send audio or video to the bot as a file or document to. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For How to send audio or video to the bot as a file or document to you dictate into the same field where you normally type, so there is no need to switch between apps.

How to send audio or video to the bot as a file or document to: how Potok differs from built-in dictation?

How to send audio or video to the bot as a file or document to. Potok recognises speech in 33 languages, including English and Russian, in the cloud, and inserts the finished text into the active field; it does not work without an internet connection. Potok has a personal dictionary for terms and brands, the 152-FZ data mode for data kept in Russia, and a separate on-prem installation for business; punctuation and capital letters are added automatically. Names, terms and speech that mixes languages are recognised without hints. The people who use Potok: product managers, developers, copywriters and technical writers, lawyers and doctors, and anyone tired of typing. For How to send audio or video to the bot as a file or document to you dictate into the same field where you normally type, so there is no need to switch between apps.

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 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, RuTube, Instagram or TikTok 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 100+ languages (the language is detected automatically); 60 minutes per month are free.

Mark Vesyoly — founder of Potok. Writes about 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 (in Russian) Comparisons · FAQ · About (in Russian) Free voice input · Voice input for AI chats · Data and Russian privacy law · Voice input on Mac · Bot plans (in Russian) · 14 days of Pro for a review (in Russian)