To turn audio into a DOCX file, send the recording to the Potok bot on Telegram and choose DOCX when you export the transcript. DOCX is the Microsoft Word document format, so you can correct, comment and format the text right away. The bot accepts files up to 2 GB.
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
- A transcript saved as DOCX can be edited and formatted in Word and other word processors.
- Speaker labels arrive as Speaker 1 and Speaker 2, so a find and replace pass turns them into real names.
- Timestamps, when switched on, stay in the text and can be deleted after you have checked the quotes.
- DOCX suits drafts that other people will review, while a final copy for sharing is often better as PDF.
How to do it
- Send the recording. Open @potok_now_bot in Telegram and send the audio. Use the Upload button of the bot's mini app if the file is large.
- Decide on labels before you start. A meeting or an interview needs speaker labels. A single voice does not.
- Wait for the transcript. A short text comes into the chat and a long one as a file. Either way the export menu offers DOCX.
- Export as DOCX. Choose DOCX and open the file in Word or any program that reads Word documents.
- Replace the labels. Use find and replace to change Speaker 1 into a name, then read the document once against the recording.
What the result looks like
[00:00] Speaker 1: Let us start with the budget for the spring event.
[00:05] Speaker 2: I have two quotes from caterers, and one includes the room.
[00:11] Speaker 1: Send both to me and we will decide on Monday.
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 |
|---|---|---|
| Opening the DOCX and expecting a link to the audio | The document holds text only, so you cannot click a line and hear it. | Keep timestamps on and use them to find a place in the recording. |
| Sending the raw document to a client | Names, figures and overlapping voices are where errors cluster. | Read it against the audio first, then export a clean copy. |
| Choosing DOCX when you need subtitles | A Word file has no cue times in the format a video player reads. | Export SRT or VTT as well. |
| Leaving the labels as numbers in a formal record | Readers cannot tell who said what. | Replace every Speaker label with a name or a role. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Can I get a Word file from an audio recording?
Yes. Send the audio to the bot and export the transcript as DOCX.
Does the DOCX keep speaker labels and times?
It keeps them if you switched them on before the transcript was made. They appear as numbered labels and time marks in the text.
Can I edit the DOCX in Google Docs or another editor?
Yes. DOCX opens in Word and in other word processors, though layout details can shift slightly.
What if my audio is longer than the chat limit allows?
Files up to 2 GB are supported, and larger ones go through the Upload button of the mini app.
Is DOCX or TXT better for a transcript?
DOCX lets you format and comment, while TXT is the smallest output and opens everywhere.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Office Open XML (Wikipedia), Wikipedia · checked
- Speaker diarisation (Wikipedia), Wikipedia · checked
- Word error rate (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