Speechmatics alternative: Potok compared

By the Potok teamUpdated ~2 min read

Choosing Speechmatics or Potok starts with scope: Speechmatics states 56+ languages and translation over 30 languages to and from English, while Potok covers about 30 languages and has none. Speechmatics exports JSON, TXT and SRT and takes under 1 GB in the request body; Potok takes 2 GB in Telegram.

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

  • Speechmatics states speaker labels; Potok can switch them on and numbers speakers as Speaker 1, Speaker 2.
  • Speechmatics' size limit applies to uploads in the request body, which concerns developers sending files by code.
  • Speechmatics exports JSON, TXT and SRT; Potok adds MD, DOCX, PDF and VTT.
  • Speechmatics' public pages do not mention a Telegram bot; Potok runs as @potok_now_bot in Telegram.
  • Speaker labels: Speechmatics lists Yes, and Potok lists Yes, can be switched on.

At a glance

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
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 when choosing

Common mistakes and how to fix them
MistakeWhat happensFix
Choosing Speechmatics for translation into any languageIts translation works to and from English only.Check that your language pair involves English.
Sending a file near 1 GB in the request bodyThe upload can fail because the stated limit is below 1 GB.Keep the file under the limit or split it.
Needing JSON from a chat botA data pipeline expects JSON and gets documents instead.Choose the tool whose export list names JSON.
Counting 56+ languages without testing yoursQuality in your language may differ from the headline.Run a short sample in your own language.
Skipping a test with one real file of your ownPublished lists say little about how your voices and noise are handledRun the same five-minute clip through both tools and compare the text

More

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

Frequently asked questions

Which tool translates transcripts, Speechmatics or Potok?

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

How large a file can Speechmatics take?

It states under 1 GB when the file goes in the request body. Potok accepts one file up to 2 GB.

What formats does Speechmatics export?

JSON, TXT and SRT. Potok gives TXT, MD, DOCX, PDF, SRT and VTT, without JSON.

Do I need to write code to use Potok?

No. Open @potok_now_bot in Telegram, send the file, and the transcript comes back in the chat.

Does Speechmatics identify speakers?

Yes, it states speaker labels. Potok can switch them on and keeps them as numbers, never real names.

What does the table say about export formats?

For Speechmatics it lists JSON, TXT, SRT, and for Potok it lists TXT, MD, DOCX, PDF, SRT, VTT. Check the vendor page for the current wording before you decide.

Sources

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

  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

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