Audio to PDF: Turn a Recording into a PDF Transcript

To turn audio into a PDF, send the recording to the Potok bot on Telegram and export the transcript as PDF. PDF keeps the layout fixed, which suits sharing and archiving. Files up to 2 GB are accepted, and a long recording arrives as a file instead of a chat message.

Transcribe a recording

Send your voice message, audio or video to @potok_now_bot on Telegram and the text comes back in the chat.

Open @potok_now_bot in Telegram

Files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT · speaker labels and timestamps · about 30 languages

Key facts

PDF is harder to edit than DOCX, so correct the text first and make the PDF last.
The same recording can be exported as TXT, MD, DOCX, SRT or VTT as well, so you can keep an editable copy.
A PDF is a good fit for minutes or interview records that people will read but not change.
Numbered speaker labels and time marks appear in the PDF if you switched them on.

How to do it

Send the audio. Open @potok_now_bot in Telegram and send the recording. Large files go through the Upload button.
Read the transcript. Check names and figures against the audio before you make anything final.
Export an editable copy. Save DOCX or TXT first, so a later correction does not mean starting again.
Export the PDF. Choose PDF when the text is ready. The layout stays the same on any device.
Share or archive. Send the PDF to the people who need to read it, and file the audio next to it.

What the result looks like

Example: board minutes as a transcript

[00:00] Speaker 1: The meeting is called to order. We have a quorum.
[00:05] Speaker 2: I move to approve the minutes from the last session.
[00:10] Speaker 3: Seconded.

Sample text written by us to show the layout of a transcript. It is not the output of the recognition engine and not a real recording.

What Potok can do
Feature	Details
Where it works	Telegram bot @potok_now_bot; large files go through the bot's mini app
File size	Up to 2 GB
Export	TXT, MD, DOCX, PDF, SRT, VTT
Speakers and time	Speaker labels and timestamps can be switched on
Languages	About 30 languages with good published results; a few more with warnings
Translation	The transcript is not translated into another language
Dictation	A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
Mistake	What happens	Fix
Making the PDF before checking the text	A PDF is awkward to change, so every typo stays until you rebuild it.	Edit in DOCX or TXT, then export the PDF at the end.
Keeping only the PDF	You cannot easily reuse the text in an email or a report.	Keep an editable export beside it.
Sending a PDF with numbered labels to a person who was not in the room	They cannot tell who Speaker 2 is.	Replace labels with names before you create the final file.
Expecting the PDF to carry the sound	It holds the text only.	Store the audio file with the document and mention its name in the file.

See the full list of languages, the tools and the glossary.

Frequently asked questions

Can I get a PDF directly from an audio file?

Yes. Send the audio to the bot and choose PDF when you export the transcript.

Is PDF better than DOCX for a transcript?

PDF keeps the layout fixed, which suits sharing. DOCX is easier to edit, so it suits drafts.

Can I edit the PDF afterwards?

It is harder than editing a Word file. Make corrections in an editable export and create the PDF again.

Does a long recording fit?

Files up to 2 GB are supported. A long transcript arrives as a file instead of a message.

Will the PDF include speaker names?

No. It shows numbered labels such as Speaker 1 if you switched them on.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

PDF (Wikipedia), Wikipedia · checked 2026-10-18
Speaker diarisation (Wikipedia), Wikipedia · checked 2026-10-18
Word error rate (Wikipedia), Wikipedia · checked 2026-10-18

Try it on your own recording