MPEG to text

By the Potok teamUpdated ~2 min read

To convert an MPEG to text, send the .mpg or .mpeg file to the Potok bot on Telegram. The speech is read from the audio track and the transcript comes back in the chat. Files up to 2 GB are accepted, which covers most old home videos.

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

  • MPEG-1 and MPEG-2 files use the .mpg or .mpeg extension; DVDs use MPEG-2.
  • Old camcorders, TV recorders and digital cameras often wrote .mpg clips, so family archives contain many of them.
  • A ripped DVD folder holds .VOB files. They are MPEG-2 too, but you may need to join the parts first.
  • The transcript is the speech only. Subtitles or menus stored on the disc are not part of it.

How to do it

  1. Identify what you have. A single .mpg or .mpeg file is ready to send. A DVD copy with several .VOB parts is better joined or sent part by part.
  2. Open the bot. Open @potok_now_bot in Telegram and press Start.
  3. Send the file. Attach it as a document. If it is large, up to 2 GB, use the Upload button of the bot's mini app.
  4. Add labels if there is a conversation. Interviews and family gatherings read better with speaker labels and timestamps.
  5. Wait and export. Short text appears in the chat and a long transcript arrives as a file. Save it as TXT, MD, DOCX, PDF, SRT or VTT.

What the result looks like

Example: an old family video as a transcript

[00:00] Speaker 1: Say hello to the camera, we are recording the garden party.

[00:05] Speaker 2: Hello, everyone. Happy birthday, grandma.

[00:10] Speaker 3: Thank you, now who is going to cut the cake?

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 whole DVD as one huge fileA disc image can pass the 2 GB limit and fail to upload.Send the chapters or the .VOB parts one by one, or join only the ones you need.
Assuming old footage has clear soundHiss, hum and a distant microphone make quiet words hard to recognise.Listen to a minute of the file first and expect extra checking of names.
Looking for the dialogue on a DVD menuMenu screens have music but no speech, so the first minutes give no text.Pick the file of the main title, not the menu part.
Converting the clip to a tiny file before sendingSqueezing an old, noisy recording further removes the little detail left in the voice.Send the original .mpg as it is.

More

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

Frequently asked questions

Is MPEG the same as MP4?

No. MPEG-1 and MPEG-2 are older formats with the .mpg or .mpeg extension. MP4 is a newer container.

Can I send a file copied from a DVD?

Yes, if it is a video file. Files from the disc usually come as .VOB parts, which you may send one at a time.

Will menus and subtitles from the disc appear?

No. The transcript contains the speech from the audio track only.

How big can the file be?

Up to 2 GB. For larger files, use the Upload button of the bot's mini app, or split the file.

Can I get subtitles from an MPEG clip?

Yes. Export the transcript as SRT or VTT to get lines with time ranges.

Sources

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

  1. MPEG-2 (Wikipedia), Wikipedia · checked
  2. Bit rate (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