Video to DOCX

By the Potok teamUpdated ~2 min read

To convert a video to DOCX, send the video to the Potok bot on Telegram, wait for the transcript and export it as DOCX. The Word file holds the spoken text of the video. Videos up to 2 GB are accepted, and the picture is not used.

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 video transcript in DOCX can be edited, commented and shared like any Word file, with no extra software.
  • Comments in the margin work well for review: a colleague can flag a wrong name next to the line it belongs to.
  • The document contains the words only. Slides, charts and on-screen text must be added by you.
  • The same transcript can be saved as PDF for a final copy or SRT for subtitles.

How to do it

  1. Get the video ready. Use the file you will publish or archive. Recordings of calls, webinars and lectures all work.
  2. Open the bot. Open @potok_now_bot in Telegram and press Start.
  3. Send the video. Attach it as a file. For a heavy video, up to 2 GB, use the Upload button of the mini app.
  4. Turn on speaker labels. Do it for a panel or a meeting. Add timestamps if reviewers will go back to the video.
  5. Export DOCX. Save the transcript as DOCX and open it in Word, or in any program that reads Word files.
  6. Review with comments. Ask colleagues to leave comments where a name, term or number looks wrong, then correct each one against the video.

What the result looks like

Example: a webinar as a Word transcript

[00:00] Speaker 1: Welcome to the session on planning a small garden.

[00:05] Speaker 2: Thanks. I will start with soil, because everything else depends on it.

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
Handing out the DOCX as a verbatim record without reviewA wrong name or number looks official in a Word file.Check the passages with names and figures against the video first.
Expecting slide text in the documentWords that appear only on screen are not spoken, so they are absent.Paste headings and figures from the slides where they matter.
Editing one copy by email chainsSeveral versions of the file appear, and corrections get lost.Keep one shared file and use comments or tracked changes.
Leaving the labels as Speaker 1 in a published documentReaders cannot tell who is who.Replace the labels with names using find and replace.

More

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

Frequently asked questions

Can I get a Word file from a video?

Yes. The bot transcribes the audio of the video and exports the text as DOCX.

Can several people review the DOCX?

Yes. It is an ordinary Word file, so it can be commented on, edited and shared.

Will the document include the video image?

No. The file holds the spoken text. Add screenshots yourself if you need them.

What other formats can I export?

TXT, MD, PDF, SRT and VTT are available next to DOCX.

How large can the video be?

Up to 2 GB, with the Upload button of the mini app for large files.

Sources

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

  1. Office Open XML (Wikipedia), Wikipedia · checked
  2. MP4 file format, MPEG-4 Part 14 (Wikipedia), Wikipedia · checked
  3. Megabyte (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