To convert a video to text, send the file to the Potok bot on Telegram and read the transcript in the chat. Common video types such as MP4, MOV, AVI and MKV work. 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
- A video file carries an audio track; transcription works on that track and ignores the picture.
- Common video formats include MP4, MOV, AVI and MKV, and the same steps apply to all of them.
- A link to a YouTube video can be sent to the bot instead of a file.
- A forwarded video from a chat can be sent on without saving it first.
How to do it
- Choose how to hand over the video. Use the file on your device, a video forwarded in Telegram, or a YouTube link.
- Open the bot. Open @potok_now_bot in Telegram.
- Send the video. Attach it as a file, forward it or paste the link. For a file up to 2 GB, use the Upload button.
- Switch on what you need. Speaker labels help for talks and meetings. Timestamps help when you want to find a moment later.
- Read and export. Short results come into the chat, long ones as a file. Save as TXT, MD, DOCX, PDF, SRT or VTT.
What the result looks like
[00:00] Speaker 1: Good morning. Today's topic is how rivers shape a valley.
[00:06] Speaker 1: Please take out the handout with the diagram on the first page.
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 |
|---|---|---|
| Sending a video without checking that it has sound | A silent screen capture gives an empty transcript. | Play a few seconds with the volume on before sending. |
| Expecting the text to describe the picture | Only spoken words are written down, so a silent demo produces no text. | Add your own notes for what happens on screen. |
| Sending a link to a private or removed video | The bot cannot open it and nothing comes back. | Check that the link opens in a private browser window, or send the file. |
| Choosing the output format last-minute | You re-export several times, and edits made to one copy do not carry over. | Decide at the start: DOCX for editing, SRT for subtitles, TXT for plain copies. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Which video formats work?
Common ones such as MP4, MOV, AVI and MKV. The bot takes the audio track from the file.
Can I use a YouTube link?
Yes. A link to a YouTube video can be sent to the bot instead of a file.
How big can the video be?
Up to 2 GB. Larger files go through the Upload button of the mini app.
Does the text include on-screen words?
No. Only speech is transcribed, not text shown in the image.
Can I get timestamps?
Yes. They are optional and can be switched on before sending.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Video file format (Wikipedia), Wikipedia · checked
- 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