Audio to SRT

By the Potok teamUpdated ~2 min read

To create an SRT file from audio, send the recording to the Potok bot on Telegram and export the transcript as SRT. SRT (SubRip) is a plain-text subtitle format, and every cue has a number, a time range such as 00:00:01,000 --> 00:00:03,500 and the text. Files up to 2 GB are accepted.

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

  • Each cue in an SRT file starts with a number, then the time range, then the text, and a blank line ends the cue.
  • The time uses a comma before the milliseconds, which is the main visible difference from WebVTT.
  • Because SRT is plain text, you can open it in any text editor and fix a line by hand.
  • Read about the SRT file format if you plan to edit the cues.

How to do it

  1. Send the audio. Open @potok_now_bot in Telegram and attach the recording or the sound track you extracted from a video.
  2. Wait for the transcript. A short result comes into the chat, a long one as a file.
  3. Export SRT. Choose SRT in the export options. You get a file with the extension .srt.
  4. Name it like the video. Many players load subtitles automatically when the file name matches the video, with .srt at the end.
  5. Check a few cues. Play the video, watch for a cue that appears too early or too late, and fix its time in a text editor.

What the result looks like

Example: the first cues of an SRT file

[00:00] Speaker 1: Welcome to the workshop on bread baking.

[00:03] Speaker 1: Today we make a simple loaf with four ingredients.

[00:08] Speaker 1: Start by warming the water.

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.

What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Renaming a .txt file to .srtThe extension changes but the cues, numbers and times are missing, so players ignore it.Export SRT from the bot instead.
Using a period in the timesA period before the milliseconds is the WebVTT style, and strict SRT readers may reject it.Keep the comma, as in 00:00:01,000.
Editing a cue and breaking the numberingPlayers expect the cues in order, with a blank line between them.Keep each cue as number, time, text, blank line.
Uploading SRT where only VTT is acceptedWeb video players that follow HTML5 conventions ask for WebVTT.Export VTT as well and use that file there.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

What is an SRT file?

SRT (SubRip) is a plain-text subtitle format. Each cue has a number, a time range and the text.

Why do SRT times use a comma?

The format puts a comma before the milliseconds, as in 00:00:01,000. WebVTT uses a period instead.

Can I make an SRT from audio without a video?

Yes. Send the audio and export SRT. You then load the file next to the video it belongs to.

Can I edit the SRT afterwards?

Yes. It is plain text, so any text editor works. Keep the numbering and the blank lines between cues.

Is SRT or VTT better?

SRT works in many desktop players. VTT is the format for HTML5 video on web pages.

Sources

Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.

  1. SubRip and the .srt format (Wikipedia), Wikipedia · checked
  2. 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