Zoom recording to text

By the Potok teamUpdated ~2 min read

To turn a Zoom recording into text, send the recording file to the Potok bot on Telegram. Zoom saves a local recording as an MP4 video plus a separate M4A audio file, and the audio file is the smaller choice. Files up to 2 GB work, and the transcript exports as TXT, DOCX, PDF, SRT or VTT.

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

  • The M4A file holds only the sound, so it is much smaller than the MP4 video of the same meeting.
  • A cloud recording can be downloaded from the Zoom web portal, and a local one sits in a folder on your computer.
  • Meetings with many voices benefit from numbered speaker labels.
  • The bot reads the sound, not the shared screen or the chat panel.

How to do it

  1. Locate the recording. A local recording sits in a folder on your computer after the meeting. A cloud recording is on the Zoom web portal.
  2. Pick the audio file. If you have the M4A audio file, choose it, because it is smaller than the MP4 video.
  3. Download from the portal if needed. For a cloud recording, use the download option on the web portal.
  4. Send it to the bot. Open @potok_now_bot in Telegram and attach the file. Use Upload when it is close to 2 GB.
  5. Create notes. Turn on labels and timestamps and export DOCX for minutes, or SRT to caption the video.

What the result looks like

Example: the start of a team call

[00:00] Speaker 1: Thanks for joining, we have three topics today.

[00:04] Speaker 2: Can we start with the budget update?

[00:08] Speaker 1: Yes, then hiring, then the launch plan.

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
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Sending the huge MP4 when the M4A is thereIt takes longer and adds nothing for speech.Choose the audio file.
Forgetting to look in the folder after the callThe file may be converting right after the meeting.Wait until the files appear.
Recording participants without telling themThey should know about it.Say so at the start.
Expecting shared slides in the textThe text has only speech.Add slide notes by hand.

More

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

Frequently asked questions

What files does Zoom save?

A local recording is an MP4 video plus a separate M4A audio file.

Which one should I send?

The M4A is smaller and holds the sound you need.

Where is a cloud recording?

It can be downloaded from the Zoom web portal.

Can I send the Zoom link?

No. The bot reads files, not meeting links.

Can the bot label different speakers?

Yes, with numbers like Speaker 1 and Speaker 2.

Sources

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

  1. Zoom (software) (Wikipedia), Wikipedia · checked
  2. MP4 file format, MPEG-4 Part 14 (Wikipedia), Wikipedia · checked
  3. Speaker diarisation (Wikipedia), Wikipedia · checked

Try it on your own 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