To convert an MP3 to SRT, send the audio to the Potok bot on Telegram and export the transcript as SRT. Each cue has a time range and a short line of text, matching the speech in the file. The bot accepts files up to 2 GB.
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
- An SRT file made from an MP3 has the same cues as the audio, with time ranges.
- SRT is plain text, so any text editor can fix wrong words. No special subtitle program is needed.
- An MP3 has no picture, so the SRT only becomes useful when you pair it with a video that uses the same audio.
- VTT is the web variant of the same idea and comes from the same transcript.
How to do it
- Start from the audio you will use. If the subtitles belong to a video, send the MP3 cut from that exact video, so the times line up.
- Open the bot. Open @potok_now_bot in Telegram and press Start.
- Send the MP3. Attach it as an audio file or a document. Up to 2 GB works, with the Upload button for large files.
- Wait for the transcript. A short transcript shows in the chat. A long one arrives as a file.
- Export SRT. Save the transcript as SRT. Open it in a text editor to read how cues are numbered and timed.
- Load it next to the video. Most players and editors accept an SRT file placed next to the video or imported as a subtitle track.
What the result looks like
[00:00] Speaker 1: Welcome back to the second lesson.
[00:03] Speaker 1: Today we will look at how to read a simple map.
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 |
|---|---|---|
| Using an MP3 that was trimmed after the video was cut | Every cue appears too early or too late, because the times follow the audio you sent. | Create the MP3 from the final video, with no edits afterwards. |
| Fixing wrong words in a word processor | Rich formatting can break the numbering and time lines that players expect. | Use a plain text editor and keep the cue structure intact. |
| Making cues too long to read | Viewers cannot finish a long line before it disappears. | Split long cues in the editor into short lines of one or two sentences. |
| Expecting speaker names in the cues | Labels, when switched on, are numbers such as Speaker 1. | Replace them by hand where the viewer needs a name. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Can an MP3 become an SRT file?
Yes. The bot transcribes the audio and can export the transcript as SRT, with a time range for every cue.
Do I need a video to get SRT?
No. You can export SRT from audio alone. You need a video only when you want to show the subtitles.
Can I correct the SRT myself?
Yes. It is plain text, so a simple text editor is enough to change words and split lines.
What if the subtitles drift out of time?
Check that the MP3 comes from the final video. Different edits shift the times, so the cues no longer match.
Is a WebVTT file also available?
Yes. VTT is one of the export formats, next to TXT, MD, DOCX, PDF and SRT.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- SubRip and the .srt format (Wikipedia), Wikipedia · checked
- MP3 (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