Lecture recording to text

By the Potok teamUpdated ~2 min read

To turn a lecture recording into text, send the audio to the Potok bot on Telegram and export the transcript. Lecture recordings are long, often 45 to 90 minutes, so the file can be large. Files up to 2 GB work, and you can save TXT, MD, 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

  • A long lecture is mostly one voice, so speaker labels help only when students or a moderator speak too.
  • Timestamps let you jump from a line in the notes back to the moment in the recording.
  • Seat position decides quality: a recorder at the back of the hall hears the room more than the speaker.
  • Ask permission before you record a class, since many schools have rules.

How to do it

  1. Get the permission. Ask the lecturer or check the school rules before you record or share a lecture.
  2. Pick the audio file. If you recorded video, you can send it as it is, since only the sound is used.
  3. Check the size. A long recording can be large. The audio file size calculator estimates it.
  4. Send it to the bot. Open @potok_now_bot in Telegram. Use the Upload button for a file close to 2 GB.
  5. Add timestamps and export. Turn on timestamps, then save a DOCX for study notes or a PDF to print.

What the result looks like

Example: the start of a lecture

[00:00] Speaker 1: Welcome back, today we cover how enzymes speed up reactions.

[00:07] Speaker 1: Write down the three words on the slide.

[00:13] Speaker 2: Could you repeat the second one?

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
Recording from the back of a large hallThe speaker sounds distant, and words drop out.Sit close, or use a microphone near the speaker.
Expecting equations and slides in the textThe bot hears speech, so formulas and board writing are missing.Add them from your own notes.
Turning on speaker labels for a monologueLabels add little when only one person talks.Use them for Q and A sessions only.
Skipping a check on names and termsTechnical words and names are where errors cluster.Replay those parts and correct the notes.

More

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

Frequently asked questions

How long can a lecture file be?

Lecture recordings are often 45 to 90 minutes. The bot accepts files up to 2 GB.

Do I need labels for a lecture?

Only when more than one person speaks, for example during questions.

Will formulas appear in the text?

No. The bot transcribes spoken words, not slides or the board.

Can I get subtitles for a recorded lecture?

Yes. Export the text as SRT or VTT and use it as subtitles.

How do I check a doubtful term?

Use the timestamp to find the moment in the recording and replay it.

Sources

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

  1. Lecture (Wikipedia), Wikipedia · checked
  2. Bit rate (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