Audio to text

By the Potok teamUpdated ~2 min read

To convert an audio file to text, send it to the Potok bot on Telegram. Transcription turns the speech in a recording into written text, and the result arrives in the chat or as a file. Files up to 2 GB are accepted, and you can export 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

  • Audio files come in many formats, such as MP3, M4A, WAV, OGG and FLAC.
  • You do not have to convert a recording first. Send the file you have, in the format it came in.
  • The text stays in the language of the recording, and is not translated.
  • Speaker labels and timestamps are optional, and they show up as numbered labels, not names.

How to do it

  1. Locate the file. Find the recording on your phone, laptop or recorder. Note its size, since files up to 2 GB are accepted.
  2. Open the bot. Go to @potok_now_bot in Telegram and press Start.
  3. Send the audio. Attach it as an audio file or as a document. A forwarded voice message works as well.
  4. Choose labels and times. Switch speaker labels on for a conversation. Switch timestamps on if you want to find places in the audio later.
  5. Take the result. A short text stays in the chat. Export a long one as a file in the format you need.

What the result looks like

Example: a short voice note as a transcript

[00:00] Speaker 1: Reminder for tomorrow: pick up the keys from the office.

[00:05] Speaker 1: Then call Maria about the delivery.

[00:09] Speaker 1: Do not forget the signed form.

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
Converting the recording before sendingEvery extra conversion of a lossy file loses detail.Send the original file.
Picking a format by size aloneA small file is not always a good one, because low bitrates damage speech.Check the bitrate with the audio file size calculator.
Recording with the phone far from the speakerDistance and room echo hurt recognition more than the file type does.Put the microphone near the voices.
Using the transcript without a checkNames, numbers and overlapping voices are where errors cluster.Play the audio next to the text and fix those places first.

More

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

Frequently asked questions

Which audio formats can I send?

Send the file as it is, whether it is MP3, M4A, WAV, OGG, FLAC or another audio format. Attach it as audio or as a document.

How large can the audio file be?

Files up to 2 GB are supported. Large files go through the Upload button of the bot's mini app.

Does the bot add punctuation and paragraphs?

The text comes back as readable sentences. You can still tidy it in a document editor after export.

Can I transcribe a voice message from a messenger?

Yes. Forward the voice message to the bot, or save it as a file and send that.

Is the text translated?

No. It stays in the language of the recording.

Sources

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

  1. Transcription (linguistics) (Wikipedia), Wikipedia · checked
  2. MP3 (Wikipedia), Wikipedia · checked
  3. MP4 file format, MPEG-4 Part 14 (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