Speechmatics vs Potok

By the Potok teamUpdated ~2 min read

The choice is between Speechmatics, with 56+ languages, and Potok, with about 30. Speechmatics translates over 30 languages to and from English, exports JSON, TXT and SRT, and takes uploads under 1 GB in the request body; Potok has no translation, takes files up to 2 GB in Telegram and exports six formats.

Get the text of your recording

Your recording goes to @potok_now_bot as a file or a voice message, and the transcript returns to you in Telegram.

Go to @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

Facts that matter here

  • Speechmatics labels speakers; Potok also labels them, as Speaker 1, 2.
  • Speechmatics states no Telegram bot on its public pages.
  • Potok adds MD, DOCX, PDF and VTT beyond what Speechmatics lists.
  • Speechmatics translation runs to and from English only.
  • On largest file, Speechmatics lists Under 1 GB when uploaded in the request body, and Potok lists Up to 2 GB.

Side by side

At a glance
SpeechmaticsPotok
Recognition languages56+ languagesAbout 30
Translation of transcriptsOver 30 languages, to and from EnglishNot available
Speaker labelsYesYes, can be switched on
Export formatsJSON, TXT, SRTTXT, MD, DOCX, PDF, SRT, VTT
Telegram botNot stated on its public pagesYes, @potok_now_bot
Largest fileUnder 1 GB when uploaded in the request bodyUp to 2 GB

Facts about Speechmatics come from its public pages and from third-party reviews. They can change; check the vendor's site before you decide.

What Potok can do
OptionWhat it means
Where to use itThe Telegram bot @potok_now_bot, plus its mini app for big uploads
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech
AcceptedVoice messages, audio and video
ExportTXT, MD, DOCX, PDF, SRT, VTT
SummaryA summary button under the transcript gives a short digest

Mistakes to avoid when you compare

Where things go wrong
What goes wrongEffectWhat to do
Sending a file near 1 GB in a Speechmatics request bodyThe upload may fail at the limitKeep files under 1 GB or use Potok
Expecting translation between any two languagesSpeechmatics translates to and from English onlyPlan an English pivot or use another translator
Expecting DOCX or PDF export from SpeechmaticsOnly JSON, TXT and SRT are namedPick Potok when you need document formats
Choosing Potok for a language outside its 30Coverage is narrower than SpeechmaticsCheck your language on both lists first
Deciding from one line of the table aloneA strong line can hide a weak one that matters for your recordingGo through every row and mark the ones that are deal breakers for you

Next steps

Not sure about a term? Open the glossary. Need to check a language? See the languages page. Helpers are in tools.

Common questions

How many languages does Speechmatics support?

It lists 56+ languages, while Potok covers about 30 languages.

Does Speechmatics translate?

Yes, over 30 languages, to and from English. Potok does not translate text.

What is the Speechmatics upload limit?

Uploads in the request body stay under 1 GB. Potok accepts a file up to 2 GB.

Which formats does Speechmatics export?

JSON, TXT and SRT. Potok exports TXT, MD, DOCX, PDF, SRT and VTT.

How do I try Potok?

Open @potok_now_bot in Telegram and send your audio file.

What does the table say about speaker labels?

For Speechmatics it lists Yes, and for Potok it lists Yes, can be switched on. Test one real file in both tools if this line decides your choice. The wording above follows the vendor page as it was read for this comparison.

Sources

We opened each page below on the date shown. Because pages get updated, confirm important details at the source.

  1. Speechmatics, official page, Speechmatics · checked
  2. Speechmatics, official page (docs.speechmatics.com), Speechmatics · checked
  3. Speechmatics, official page (docs.speechmatics.com), Speechmatics · checked
  4. Whisper speech recognition system (Wikipedia), Wikipedia · checked

See the result on your recording

Drop an audio or video file, or a voice message, into the chat with @potok_now_bot; the recognized text is sent back there.

Open @potok_now_bot in Telegram