Audio to Markdown

By the Potok teamUpdated ~2 min read

To turn audio into Markdown, send the recording to the Potok bot on Telegram and export the transcript as MD. Markdown is plain text with light markup for headings and lists, so the file opens in any editor. The bot takes files up to 2 GB, and the same transcript also exports 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

  • Notes apps and static sites read Markdown directly, so the exported file can be dropped into a folder as it is.
  • Because Markdown is plain text, it works well with version control and with search tools.
  • The bot gives you the transcript, so headings and lists are yours to add after reading.
  • A single line break inside a paragraph is usually ignored when Markdown is rendered.

How to do it

  1. Send the recording. Start with @potok_now_bot in Telegram and attach the audio.
  2. Pick labels if you need them. For a conversation, switch speaker labels on. They arrive as numbered names.
  3. Export MD. Choose the MD option. You get a text file with the extension .md.
  4. Open it in a notes app. Put the file in your notes folder or paste it into a page. Check how line breaks look once it is rendered.
  5. Add structure. Mark topic changes with headings and turn action points into a list. Keep the original audio with the note.

What the result looks like

Example: a voice note as a transcript ready for notes

[00:00] Speaker 1: Idea for the newsletter: a short list of three reading tips.

[00:06] Speaker 1: First tip is to read one chapter before bed.

[00:11] Speaker 1: Add a link to the library at the end.

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
Expecting headings and summaries to appear on their ownThe export is the transcript, so the file is one long text.Add the headings yourself where the topic changes.
Pasting the text into a page and losing the line breaksMarkdown joins single lines into one paragraph when it is shown.Leave a blank line between paragraphs.
Saving the file as .txt and wondering why nothing rendersPrograms only treat a file as Markdown if the extension says so.Keep the .md extension.
Leaving the Speaker labels in a published pageReaders see numbers instead of names.Replace them with names or roles before publishing.

More

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

Frequently asked questions

Can I get Markdown from an audio file?

Yes. Send the file to the bot and choose MD when you export the transcript.

What is Markdown?

It is plain text with light markup for headings and lists. Notes apps and static sites read it directly.

Does the MD file contain formatting?

It holds the transcript text, with labels and times if you switched them on. You add headings and lists yourself.

Why does my Markdown page run all lines together?

Rendered Markdown joins lines that are not separated by a blank line. Add an empty line between paragraphs.

Can I turn the same recording into MD and SRT?

Yes. Export the transcript in each format you need from the same result.

Sources

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

  1. Markdown (Wikipedia), Wikipedia · checked
  2. Speaker diarisation (Wikipedia), Wikipedia · checked
  3. Telegram (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