MKV to text

By the Potok teamUpdated ~2 min read

To convert an MKV video to text, send the file to the Potok bot on Telegram and read the transcript in the chat. MKV (Matroska) is an open container that can hold many video, audio and subtitle tracks, so check which track carries the speech. Files up to 2 GB are accepted. Export 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

  • Screen recorders such as OBS often save MKV by default, and so do many downloaded talks.
  • A recording with several audio tracks may keep the microphone and the computer sound apart.
  • Long streams and gameplay captures easily pass 2 GB, so they often need their audio saved on its own.
  • Subtitle tracks inside the file are not the transcript, as the bot works from the speech.

How to do it

  1. List the audio tracks. Open the file in a media player and look at the audio menu. Note which track holds the voice you need.
  2. Check the size. If the file is larger than 2 GB, save the audio track alone with a media tool, or cut the video into parts.
  3. Open the chat. Go to @potok_now_bot in Telegram.
  4. Send the MKV. Use the Upload button of the mini app for big files, or attach a smaller one as a document.
  5. Choose output. Turn speaker labels on for a call recording, then export SRT if the text goes back onto the video.

What the result looks like

Example: a screen recording with a voice-over as a transcript

[00:00] Speaker 1: In this recording I will show how to set up the report.

[00:05] Speaker 1: First, open the settings panel on the left.

[00:10] Speaker 1: Then choose the date range.

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 a recording where the microphone was offThe only sound is the computer's, so your own voice is missing from the text.Test-record ten seconds and play them back.
Assuming the first audio track is the right oneA film may have a commentary or another language first.Pick the track by listening, and save that one.
Uploading a multi-hour stream capture wholeIt exceeds the size limit.Save the audio only, or cut the video into parts.
Expecting embedded subtitles to be copied outThey are separate from the speech.Let the bot make a new transcript.

More

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

Frequently asked questions

What is an MKV file?

MKV (Matroska) is an open container that can hold many video, audio and subtitle tracks.

Which audio track is used if the file has several?

Do not rely on a default. Check by listening, and save the track you need as its own audio file if in doubt.

Can I send a long MKV?

Files up to 2 GB are supported. Above that, save the audio alone or cut the video.

Do I need to convert MKV to MP4?

No. The bot reads video files directly, and conversion is only a way to reduce size.

Can I get subtitles from my MKV?

Yes. Export the transcript as SRT or VTT and load it next to the video.

Sources

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

  1. Matroska (Wikipedia), Wikipedia · checked
  2. MP4 file format, MPEG-4 Part 14 (Wikipedia), Wikipedia · checked
  3. Bit rate (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