Dictaphone recording to text

By the Potok teamUpdated ~2 min read

To turn a dictaphone recording into text, copy the file from the recorder and send it to the Potok bot on Telegram. Digital voice recorders save MP3, WAV or WMA files, depending on the model. Files up to 2 GB are accepted, and the text can be exported as TXT, DOCX, PDF, SRT or VTT.

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 digital recorder is a separate device, so its files reach a computer by USB or memory card before anything else happens.
  • WAV recordings are large, MP3 files are small, and WMA sits between the two for most models.
  • Dictaphones often record in rooms with one distant speaker, which makes the first minute a good test of quality.
  • Short dictated notes come back in the chat; a full interview comes back as a file.

How to do it

  1. Copy the file to a computer. Connect the recorder by USB, or take out its memory card and use a card reader. Copy the recordings you need to a folder.
  2. Check the size. A long WAV can be big. The audio file size calculator shows what a given length weighs.
  3. Send it to the bot. Open @potok_now_bot in Telegram on that computer and attach the file as a document or audio.
  4. Turn on timestamps. For a long recording, timestamps let you jump to a passage in the original. Labels help when two people talk.
  5. Export. Choose DOCX or PDF for a report, SRT or VTT if the recording goes with a video.

What the result looks like

Example: a dictated memo from a handheld recorder

[00:00] Speaker 1: Memo for the site visit, the north wall needs a second inspection.

[00:06] Speaker 1: Photograph the crack before the rain, and measure its length.

[00:13] Speaker 1: Send the report to the architect by Friday.

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
Sending only the first file on the cardRecorders split long sessions into several files, so the text stops early.List every file for the session and send them in order.
Putting the recorder in the middle of a tableCups, paper and chairs add noise that the microphone picks up.Place it near the speaker, on a soft surface.
Ignoring the recorder's quality settingA low setting trims detail, and quiet words are lost.Use a higher quality setting for important sessions.
Overwriting the card before the text is checkedYou lose the original and cannot confirm doubtful words.Archive the file, then clear the card.

More

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

Frequently asked questions

Which formats do digital voice recorders save?

Depending on the model, MP3, WAV or WMA. The bot reads audio files of these kinds.

How do I get the file off the recorder?

Copy it to a computer by USB or memory card. Then send it to the bot from Telegram.

Can I send a recording of several hours?

Yes, up to 2 GB. For the biggest files, use the Upload button of the mini app.

What if the recorder split a session into parts?

Each part gives its own transcript. Join the texts in order in one document.

Does it mark who is speaking?

Speaker labels can be switched on. They are numbers, not names.

Sources

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

  1. Dictation machine (Wikipedia), Wikipedia · checked
  2. Windows Media Audio (Wikipedia), Wikipedia · checked
  3. Bit 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