To create an SRT file from audio, send the recording to the Potok bot on Telegram, switch on timestamps and export SRT. Files up to 2 GB work. SRT is plain text: numbered cues, each with a start time, an end time and a line of words. Any video editor can load it.
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
- SRT is a plain text format, so you can open and fix the file in any text editor.
- Checking by eye means playing the sound with the file loaded and watching each cue appear at the right moment.
- Timestamps are what turn a transcript into subtitles. Without them the export has no cues to show.
How to do it
- Prepare the audio. Use the original recording, not a copy that was compressed twice. Clean speech gives cleaner cue breaks. A noisy file is better trimmed before you send it.
- Open the bot. Open @potok_now_bot in Telegram and start a chat with it.
- Switch on timestamps. Turn them on before you send the file. The SRT export needs a time for each passage.
- Send the file. Attach the audio as a file. For a very large recording, up to 2 GB, use the Upload button of the bot's mini app.
- Export SRT. When the transcript is ready, pick the SRT format. A short result also appears as text in the chat.
- Check by eye. Load the SRT next to the sound in a player or editor. Watch the first minute, a middle section and the end for drift and for cues that are too long.
- Fix in a text editor. Edit wording or merge short cues directly in the file. Keep the numbering and the time lines in their original layout.
What the result looks like
[00:01] Speaker 1: Welcome back to the studio. Today we look at colour grading.
[00:05] Speaker 1: First, a quick word on how to set up your timeline.
[00:09] Speaker 2: And I will keep an eye on the clock.
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 |
|---|---|---|
| Never playing the file with the sound | A cue can sit a second late or hold too many words, and you only notice on screen. | Watch at least three sections of the recording with the SRT loaded. |
| Editing the time lines by hand and breaking the layout | The editor then refuses the file or skips cues. | Change only the words. If you must edit a time, keep the exact format of the line. |
| Saving the file in a different text encoding | Accented letters and quotation marks turn into odd symbols. | Save as UTF-8, which is what most editors expect. |
| Sending a track with music under the voice | The recognised words drift and cues gather around loud passages. | Send a voice-only mix if you have one, and read those cues closely. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Can I make an SRT file from an audio file with no video?
Yes. The cues follow the speech in the audio. You can attach the SRT to a video later in any editor.
Which export option gives the subtitle file?
Choose SRT in the export list. VTT is the other subtitle format the bot offers, for web players.
Do the timestamps have to be switched on?
Yes, switch them on before sending the file. Subtitle cues depend on times, and a plain text export has none.
Is the file ready to publish as it comes out?
Treat it as a draft. Names, numbers and fast speech are where wrong words appear, so read the cues against the sound.
What if the SRT shows labels like Speaker 1?
Those are numbers, not real names. Delete them from the cues or replace them if your subtitles show who speaks.
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
- Subtitle (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