To make subtitles from audio, send the recording to the Potok bot on Telegram and export the transcript as SRT or VTT. Subtitle files keep text and timing separate from the video, so you can load them next to any copy of the clip. Files up to 2 GB are accepted, and a long result arrives as a file.
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
- The two common text formats are SRT and WebVTT, and the choice depends on where the video will play.
- A subtitle file can be replaced or corrected without touching the video itself.
- Subtitles show the words spoken, in the language of the recording, and the bot does not translate them.
- Timestamps matter more here than for notes, because every cue needs a start and an end.
How to do it
- Pick the format first. Desktop players and many editors read SRT. Web pages with HTML5 video ask for VTT. If unsure, export both.
- Send the recording. Open @potok_now_bot in Telegram and attach the audio or video.
- Export the file. Choose SRT or VTT from the export options.
- Load it with the video. Give the subtitle file the same base name as the video, or attach it in your player or editor.
- Read the clip with the subtitles on. Watch for cues that appear late or are too long, and correct the text in an editor.
What the result looks like
[00:00] Speaker 1: Good morning, and thank you for coming.
[00:03] Speaker 1: Today I will show three ways to read a chart.
[00:08] Speaker 1: The first one starts with the axis.
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 |
|---|---|---|
| Burning in subtitles before checking them | A typo that is drawn into the picture cannot be changed later. | Keep subtitles as a separate file until the text is final. |
| Choosing the format by guess | A player that expects VTT may ignore an SRT file, and the other way round. | Check what the target accepts, or keep both exports. |
| Expecting subtitles in a different language | The bot writes what is said, in the language of the recording. | Prepare other languages outside the bot, from the exported text. |
| Keeping very long cues | Viewers cannot read two long lines in the time they are on screen. | Split a long cue into two at a natural pause. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
How do I get subtitles from an audio file?
Send the audio to the bot and export the transcript as SRT or VTT. Each cue carries a time range.
What is the difference between SRT and VTT?
SRT is a plain-text subtitle format with a comma before the milliseconds. WebVTT is the format for HTML5 video and uses a period.
Do subtitles change the video file?
No. The text and timing stay in a separate file, so you can fix them without touching the video.
Can I get subtitles in another language?
No. The text stays in the language of the recording.
Can I use the file on a video site?
Many sites accept an uploaded subtitle file, but each has its own rules. Check which format the site asks for.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Subtitle (Wikipedia), Wikipedia · checked
- SubRip and the .srt format (Wikipedia), Wikipedia · checked
- WebVTT (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