To transcribe a conference talk, send the recording to the Potok bot on Telegram, switch on timestamps and export the format you need. Files up to 2 GB work. Clean text helps readers who missed the room, and SRT or VTT lets the talk video carry captions.
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
- Clean text is made in the edit: the transcript keeps filler words and false starts, and you remove them.
- Timestamps let you link a point in the written talk to the right moment in the video.
- SRT or VTT turns the same transcript into captions for the recording of the talk.
How to do it
- Get the best audio. Ask the organisers for the line feed from the mixing desk. A room microphone picks up echo and the crowd.
- Open the bot. Open @potok_now_bot in Telegram and send the file. Use Upload for a long recording near 2 GB.
- Switch on timestamps. You will want them for captions and for linking to moments in the talk.
- Export DOCX for editing. Save a DOCX version and work on it in a word processor.
- Clean the text. Remove filler words, repeated starts and asides that do not help a reader. Check names of products and people.
- Export SRT or VTT. Generate the captions file for the talk video, using SRT for editors and VTT for web players.
- Publish both. Put the written talk next to the video, with captions loaded in the player.
What the result looks like
[00:00] Speaker 1: Thank you all for coming. Today I want to show how our team moved to a new build system.
[00:08] Speaker 1: Um, so, let me start with the problem we had.
[00:14] Speaker 1: Every release took an entire afternoon.
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 |
|---|---|---|
| Publishing the raw transcript | Spoken language has false starts and filler that read badly on a page. | Edit it into clean text and keep the meaning intact. |
| Misspelling the product or speaker names | The slides show one spelling and the text shows another. | Copy the names from the slide deck. |
| Captions that disagree with the edited text | Viewers see one wording in the captions and another in the article. | Export the captions after you finish editing the words. |
| Recording from the back of the hall | Echo and noise hide quiet words. | Take a feed from the sound desk or place a recorder near the stage. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Why do I need to clean the transcript?
Speech includes filler words and restarts. A page reads better once you trim them.
Can one transcript give me captions and an article?
Yes. Export DOCX to edit as an article, and SRT or VTT for captions from the same recording.
What is the best audio source?
A line feed from the sound desk, when you can get one. Otherwise a recorder close to the speaker.
Do timestamps help with an article?
Yes, they let you link a paragraph to the moment in the video where it was said.
Are the captions in another language too?
No. They stay in the language of the talk.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Closed captioning (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