Riverside alternative: Potok compared

By the Potok teamUpdated ~2 min read

Riverside and Potok differ most in language reach: Riverside states Over 100 languages and dialects, against about 30 for Potok. Riverside exports SRT and TXT and bases speaker labels on separate audio tracks, while Potok exports six formats and runs inside 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

  • Riverside speaker labels rely on separate audio tracks; Potok labels speakers in a single mixed file as Speaker 1, Speaker 2.
  • Riverside's export list is SRT and TXT; Potok adds MD, DOCX, PDF and VTT.
  • Riverside's public pages do not state a largest file; Potok takes one file up to 2 GB.
  • Neither tool offers confirmed translation: Riverside does not state it and Potok has none.
  • Speaker labels: Riverside lists Yes, based on separate audio tracks, and Potok lists Yes, can be switched on.

At a glance

At a glance
RiversidePotok
Recognition languagesOver 100 languages and dialectsAbout 30
Translation of transcriptsNot stated on its public pagesNot available
Speaker labelsYes, based on separate audio tracksYes, can be switched on
Export formatsSRT and TXTTXT, MD, DOCX, PDF, SRT, VTT
Telegram botNot stated on its public pagesYes, @potok_now_bot
Largest fileNot stated on its public pagesUp to 2 GB

Facts about Riverside 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
Expecting track-based speaker labels from a single fileVoices in one mixed file are labelled by sound, not by track.Know which input your speaker labels depend on.
Picking Riverside only for its 100-language listYour actual language may be fine on a shorter list.Check your language on both lists before deciding.
Assuming Riverside exports DOCX or PDFIts list names only SRT and TXT, so documents need conversion.Match the export list to your final deliverable.
Assuming a missing file limit means there is no capA large recording may fail after a long upload.Ask the vendor for the cap or test with a big file.
Reading a vendor line on this page as permanentLists and limits change, so the line can be out of date by the time you read itOpen the vendor page for the current version before you decide

More

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

Frequently asked questions

Do Riverside speaker labels need separate tracks?

Yes, Riverside bases them on separate audio tracks. Potok works from one file and can switch labels on, numbering the speakers.

Which formats can I export from Riverside?

It lists SRT and TXT. Potok exports TXT, MD, DOCX, PDF, SRT and VTT, which covers both documents and subtitles.

Does Riverside state a maximum file size?

Not on its public pages. Potok states one file up to 2 GB, with larger ones sent through the Upload button.

How do I start with Potok in Telegram?

Open @potok_now_bot, send your recording, and wait for the transcript to return in the chat as text or a file.

Why would I pick a tool with fewer languages?

If your language is among about 30 published ones, the format and file limits may matter more than the length of the list.

What does the table say about export formats?

For Riverside it lists SRT and TXT, 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. Riverside, official page, Riverside · checked
  2. 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