Podcast to text

By the Potok teamUpdated ~2 min read

To turn a podcast into text, download the episode file and send it to the Potok bot on Telegram. Podcast episodes are usually MP3 files, often an hour or longer, and the file can be downloaded from the podcast host. Files up to 2 GB work, and the transcript 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

  • An episode is usually an MP3, and an hour of speech is a fairly small file compared with an hour of video.
  • Interviews have a host and a guest, so speaker labels make the transcript readable.
  • Timestamps point to a quote, an ad break or a chapter in the original audio.
  • Show notes, blog posts and subtitles can all start from the same transcript.

How to do it

  1. Get the episode file. Open the podcast host's page for the show and download the episode, if the host provides it. Your own episodes come from your editor or hosting account.
  2. Check your rights. Transcribe your own show, or an episode you have permission to use.
  3. Send the file. Open @potok_now_bot in Telegram and attach the MP3 as a document or audio.
  4. Turn on labels and timestamps. For a two-person show, labels split host and guest. Timestamps help you find quotes.
  5. Export for the web. Save DOCX for editing, or SRT and VTT for a video version of the show.

What the result looks like

Example: the start of an interview episode

[00:00] Speaker 1: Welcome to the show, today we talk about small farms.

[00:06] Speaker 2: Thanks for having me, it is a busy season.

[00:12] Speaker 1: Let's start with how you chose the land.

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
Transcribing an episode you do not have rights toThe recording and its words belong to the creators.Use your own episodes or ask permission.
Leaving ad breaks in the notesSponsor reads clutter the text.Cut them out when you edit.
Publishing the raw transcriptFiller words and false starts make it hard to read.Edit before you post.
Skipping guest namesThe bot labels voices with numbers.Add names from the episode page.

More

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

Frequently asked questions

What file is a podcast episode?

Podcast episodes are usually MP3 files, often an hour or longer.

Where do I get the file?

The episode file can be downloaded from the podcast host, when the host offers it.

Will the bot separate host and guest?

It can mark speakers as Speaker 1 and Speaker 2. It does not know their names.

Can I get subtitles for a video version?

Yes. Export SRT or VTT and add the file to your video editor.

How large can the file be?

Up to 2 GB, with the Upload button for the biggest files.

Sources

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

  1. Podcast (Wikipedia), Wikipedia · checked
  2. MP3 (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