Transcription

How to transcribe a large audio file

Mark Vesyoly · founder of Potok · ~5 min

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

A large audio file is easier to transcribe in the bot's mini app: a file up to 2 GB is uploaded by drag and drop, and if the connection drops, the upload resumes from where it broke. A short recording from the same file can also be sent straight to the Telegram bot @potok_now_bot, and the principle is the same. 60 minutes of transcription per month are free.

A large audio file is the case where sending the recording to Telegram in pieces is inconvenient, while the web version accepts it whole in one upload.

How to transcribe a large audio file, step by step

For a file of several hundred megabytes or more, it is easier to go through the browser:

  1. Open the web version of the Potok bot and sign in by email or through Telegram.
  2. Drag the audio file into the browser window, up to 2 GB; for video, a link to YouTube, VK Video or RuTube also works.
  3. If the connection drops in the middle of the upload, the upload resumes from where it broke, not from the beginning.
  4. Wait for the transcription and choose the text format: TXT, DOCX, Markdown, PDF, SRT or VTT.
  5. The same file, if it is shorter, can also be sent straight to the Potok Telegram bot @potok_now_bot. The principle of transcription is the same, and the account and recordings are shared.

What you get back for a large recording

The transcript of a large file does not come as a solid text without structure:

When the bot will not fit a large file

If the audio file is in English, German or any language other than Russian, the bot will not transcribe it: it works only with Russian speech, and translation is not provided. While a conversation or meeting is still going on, the bot is also powerless: it takes a finished recording and does not join a live call. You cannot paste an Instagram or TikTok link into it: it accepts only a file or an address on YouTube, VK Video and RuTube. And without the internet the bot does not work: it is a cloud service, and recognition runs on Potok's servers in Russia, not on the device itself.

If the file, on the contrary, is short and is just a voice message, the whole list of options is collected in the article the best bots for transcribing voice messages, and the broader comparison of transcription services adds apps to the bots.

Calculated from average typing and speaking speeds, not measured.
TaskCharactersTyping (200 chars/min)Voice (900 chars/min)
chat reply3002 min0.5 min
email15008 min1.7 min
post or meeting minutes400020 min4.4 min
article1000050 min11.1 min

Frequently asked questions

What if the upload of a large file broke off halfway?

In the bot's mini app you do not have to redo anything: if the connection drops, the file upload continues from where it stopped, not from the beginning.

How does transcription differ from voice input?

Voice input is real-time dictation into the active text field. Transcription is turning an already finished audio or video recording (a lecture, a call, a podcast) into text after the fact, often with diarization (splitting by speaker).

Can I transcribe meeting minutes through voice input?

With Potok you can dictate the minutes live, saying them during or right after the meeting. Transcribing an already recorded meeting audio file (a finished Zoom or Telemost recording) is a separate transcription task: you can send such a file to the Potok Telegram bot @potok_now_bot.

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 is turning an already finished audio or video recording (for example, a meeting recording) into text after the fact. The Potok app does the first job, live dictation; finished recordings in Russian are transcribed by its Telegram bot @potok_now_bot.

Can a Zoom call be transcribed automatically?

Yes, a number of platforms have built-in meeting transcription: in Zoom for cloud recordings, in Microsoft Teams during the meeting, in 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; you can send a call recording as a file to the Potok 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: 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.

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