To convert an MP4 to text, send the video to the Potok bot on Telegram and read the transcript in the chat. Only the audio track is used, so a large video is fine. Files up to 2 GB are accepted, and you can export 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
- MP4 is a container that usually holds H.264 video and AAC audio. The speech lives in the AAC part.
- Transcription only needs the audio track, so large video files are fine and the picture adds nothing to the result.
- Screen recordings and phone videos are both MP4 in most cases, and both are sent the same way.
- A result of any length can be saved as a transcript with timestamps.
How to do it
- Take the file from where it lives. A phone video sits in the gallery, a screen recording in a folder, a camera clip on the memory card. Copy it to the device with Telegram.
- Open the bot. Open @potok_now_bot in Telegram.
- Send the MP4. Attach it as a video or as a document. For a heavy file, up to 2 GB, use the Upload button of the mini app.
- Switch on labels for several voices. A meeting recording is easier to read with speaker labels and timestamps.
- Read and export. Short text appears in the chat, long text as a file. Save it as TXT, MD, DOCX, PDF, SRT or VTT.
What the result looks like
[00:00] Speaker 1: I am sharing my screen so we can walk through the sign-up form.
[00:08] Speaker 2: Please open the second tab and scroll to the address fields.
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.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Shrinking the video before sending to save space | Heavy re-encoding can damage the audio, and the speech suffers more than the picture. | Send the original MP4 if it is under 2 GB. |
| Sending a video whose sound was muted | There is no speech to recognise, so the transcript comes out empty. | Play the file first and make sure the voice is audible. |
| Recording a screen share with the wrong audio source | Only system sounds are captured and the voices of the participants are missing. | Enable the microphone or the call audio before you record. |
| Quoting the transcript without checking the video | Names on slides and numbers on screen are not in the audio, so the text cannot supply them. | Add on-screen names and figures from the video yourself. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Does the bot read the video image?
No. It works from the audio track, so only spoken words appear in the text.
Is a large MP4 a problem?
Not as long as it stays under 2 GB. Large files go through the Upload button of the bot's mini app.
Which formats can I export?
TXT, MD, DOCX, PDF, SRT and VTT. SRT and VTT give subtitle files with times.
Can I send an MP4 as a document?
Yes. Sending it as a document keeps the file as it is, and it works just as well as sending it as a video.
Can the bot show who is speaking?
It can mark speakers as Speaker 1, Speaker 2 and so on. It does not know their real names.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- MP4 file format, MPEG-4 Part 14 (Wikipedia), Wikipedia · checked
- 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