SoundCloud audio to text

By the Potok teamUpdated ~2 min read

To turn a SoundCloud track into text, you need it available as a file and you must have the right to use it. Send that file to the Potok bot on Telegram, since the bot does not take SoundCloud links. Files up to 2 GB work, 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

  • A SoundCloud track needs to be available as a file before it is transcribed.
  • Your own uploads are the easiest case, because you already hold the source file.
  • Tracks by other people belong to their creators, so respect their rights.
  • Mixes with loud music under the speech give poor text, while talk and podcast uploads do well.

How to do it

  1. Check who owns the track. Use your own upload, or get permission from the creator.
  2. Get the audio file. For your own track, use the original file from your computer. For someone else's, ask for the file.
  3. Send it to the bot. Open @potok_now_bot in Telegram and attach the audio.
  4. Pick the extras. Turn on timestamps for a long talk. Labels help if there are guests.
  5. Export the text. Save TXT for editing, or SRT and VTT if the track becomes a video.

What the result looks like

Example: the intro of a talk uploaded as a track

[00:00] Speaker 1: This is the second episode of the series on field recording.

[00:06] Speaker 1: Today we test three microphones in the woods.

[00:12] Speaker 1: Let's hear the first sample.

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
Pasting a SoundCloud linkThe bot reads files, so a link gives it nothing.Send the audio file.
Using someone else's track without askingThe creator owns the recording.Ask for the file or skip it.
Transcribing a music mixLyrics under loud beats are hard to catch.Use clean spoken audio.
Skipping a final readNames and titles are easy to mishear.Check them against the audio.

More

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

Frequently asked questions

Can I paste a SoundCloud link?

No. The bot does not take SoundCloud links. Send an audio file you may use.

How do I get my own track as a file?

Use the original file you uploaded from your computer or the app you recorded in.

Can I transcribe music lyrics?

The bot is built for speech, and lyrics over loud music give poor results.

Is there a size limit?

Each file can be up to 2 GB.

Are speakers named?

No. The labels are plain numbers like Speaker 1.

Sources

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

  1. SoundCloud (Wikipedia), Wikipedia · checked
  2. Podcast (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