How to make SRT subtitles from a video

Potok transcribes Russian speech; this site has been translated into English for convenience.

SRT is a subtitle file: numbered lines of text with start and end timecodes, which a player shows over the video. You can get it from your video through the Potok bot (potok.now) @potok_now_bot: send a video file or a link to YouTube, VK Video or RuTube, and export the transcript in SRT among other formats. 60 minutes per month are free.

SRT (SubRip Subtitle) is an ordinary text file: numbered blocks, each with a start and end timecode of a phrase and the phrase itself on the line below. Almost all players and video platforms understand such a file, which is why it is asked for instead of subtitles burned into the video.

How to make SRT subtitles from your own video

An SRT file is obtained from a ready recording, not drawn by hand:

Open the Potok Telegram bot @potok_now_bot and press Start (the /start command).
Send a video file (as a document if the video is large) or a link to YouTube, VK Video or RuTube.
Wait for the transcript: a short recording comes as text in the chat, a long one as a file.
Among the export formats choose SRT; TXT, DOCX, Markdown, PDF and VTT are available next to it.
For a video up to 2 GB, the web version of the Potok bot is more convenient: the file is dragged into the browser, and if the connection drops, the upload continues from the point of interruption.

What SRT, VTT and timecode mean

A few more words often appear next to subtitles:

SRT (SubRip Subtitle): a text file with numbered lines, each with its own start and end timecode.
VTT (WebVTT): a similar subtitle format for web players; the bot exports it from the same transcript too.
Timecode: a time mark in the format [mm:ss] that shows at which second of the recording a phrase was spoken; in the bot's transcript it is turned on in the settings.
Speaker: the person talking in the recording. The bot tells them apart only by numbers, "Speaker 1" and "Speaker 2", and does not know real names.

When the bot will not fit for subtitles

The Potok bot will not fit if the video is not in Russian: it recognizes only Russian speech, and there is no translation into another language. Transcription during a live broadcast is also not available: the bot takes an already finished recording and does not connect to a stream itself. It will not accept a link to Instagram or TikTok, only video files and links to YouTube, VK Video and RuTube. The bot gives subtitles as a separate file, not burned into the video: you will have to overlay them in a video editor or on the platform itself. And the bot does not work without the internet: it is cloud-based, and recognition runs on Potok servers in Russia.

The difference between transcribing a ready recording and ordinary voice input of text is covered in the article "transcription and voice input: what is the difference", and the broader comparison of transcription services shows options besides bots.

Frequently asked questions

Can I get subtitles burned into the video and not as a separate file?

No, the Potok bot gives a ready SRT or VTT file separately from the video. Burning subtitles into the video itself has to be done in a video editor or on the platform where the video is uploaded.

Try it on your own texts

Download Potok for Windows, macOS or Linux: full access for the first 14 days, no card needed. After that, 2500 words per week for free or Pro for 690 ₽ per month. Potok is a cloud service: speech is recognized on servers in Russia, and it does not work without the internet.

Download Potok

One subscription, two tools: dictation in any program on your computer and @potok_now_bot in Telegram, which transcribes voice messages, audio and video.

Primary sources: yandex.ru · vc.ru · speech2text.ru · audio-2-text.ru