MP3 to DOCX

By the Potok teamUpdated ~2 min read

To convert an MP3 to DOCX, send the recording to the Potok bot on Telegram and choose DOCX when you export the transcript. You get a Word file you can correct, comment on and share. Files up to 2 GB are accepted, and a long transcript 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

  • An MP3 recording can be turned into an editable Word document, so corrections happen in the editor you already use.
  • The DOCX is made from the finished transcript. You pick the format at the export step, after the text is ready.
  • TXT, MD, PDF, SRT and VTT come from the same transcript, so a plain-text copy costs nothing extra.
  • Speaker labels and timestamps are optional and appear as numbers, such as Speaker 1, never as real names.

How to do it

  1. Check the MP3. Play the first seconds. A voicemail, a lecture download or a podcast episode all work, as long as the voice is audible.
  2. Open the bot. Open @potok_now_bot in Telegram and press Start.
  3. Send the file. Attach the MP3 as an audio file or as a document. For a large file, up to 2 GB, use the Upload button of the bot's mini app.
  4. Decide on labels. Switch on speaker labels if people take turns, and timestamps if you want to jump back to the audio later.
  5. Wait for the text. A short transcript appears in the chat. A long one arrives as a file.
  6. Export as DOCX. Choose DOCX, open the file in Word and replace Speaker 1 and Speaker 2 with real names.

What the result looks like

Example: a dictated memo as a document

[00:00] Speaker 1: Memo for the training handbook, section four, onboarding.

[00:06] Speaker 1: New staff should receive the building pass on day one, not after the first week.

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
Exporting TXT and pasting it into Word by handYou rebuild the paragraphs yourself and spend time on layout, not on checking the words.Pick DOCX at the export step and start editing at once.
Sending the document on before listening to the recordingNames, numbers and overlapping voices are where errors cluster, and a Word file looks more final than it is.Play the MP3 next to the document and fix those places first.
Expecting the labels to carry namesThe bot does not know who the people are, so the document says Speaker 1 and Speaker 2.Use find and replace in Word to put real names in.
Keeping only the DOCXOnce the audio is gone you cannot check a doubtful passage.Keep the MP3 beside the document until the text is final.

More

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

Frequently asked questions

Can I get a Word file straight from an MP3?

Yes. Send the MP3 to the bot, wait for the transcript and choose DOCX as the export format.

Is the DOCX editable?

Yes. It is an ordinary document, so you can correct words, add comments and share it like any Word file.

Can I get the same transcript as PDF or SRT?

Yes. TXT, MD, DOCX, PDF, SRT and VTT are all available for the same transcript.

Does the document keep the speaker names?

No. The bot marks speakers with numbers only. Add the names yourself after the export.

How large can the MP3 be?

Files up to 2 GB are supported, and a large file goes through the Upload button of the mini app.

Sources

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

  1. Office Open XML (Wikipedia), Wikipedia · checked
  2. MP3 (Wikipedia), Wikipedia · checked
  3. Megabyte (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