It depends on file size: Whisper supports 98 languages with accuracy that varies by language, but the OpenAI API takes 25 MB per file, while Potok covers about 30 languages and files up to 2 GB in Telegram. Whisper translates into English only; Potok has no text translation.
Send a file, get the text
Open @potok_now_bot in Telegram, attach the recording and wait: the transcript arrives as a message in the same chat.
Open @potok_now_bot in Telegram
About 30 languages · speaker labels and timestamps · files up to 2 GB · export to TXT, MD, DOCX, PDF, SRT and VTT
Key facts
- Whisper itself does not label speakers; a separate OpenAI model adds speaker labels.
- Potok labels speakers as Speaker 1, 2 when the option is switched on.
- Whisper's public pages do not state export formats; Potok offers six.
- Whisper's public pages state no Telegram bot; Potok runs as @potok_now_bot.
- On speaker labels, Whisper lists Not in Whisper itself; a separate OpenAI model adds speaker labels, and Potok lists Yes, can be switched on.
The two compared
| Whisper | Potok | |
|---|---|---|
| Recognition languages | 98 languages, accuracy varies by language | About 30 |
| Translation of transcripts | Into English only | Not available |
| Speaker labels | Not in Whisper itself; a separate OpenAI model adds speaker labels | Yes, can be switched on |
| Export formats | Not stated on its public pages | TXT, MD, DOCX, PDF, SRT, VTT |
| Telegram bot | Not stated on its public pages | Yes, @potok_now_bot |
| Largest file | 25 MB per file in the OpenAI API | Up to 2 GB |
Facts about Whisper come from its public pages and from third-party reviews. They can change; check the vendor's site before you decide.
| Feature | Details |
|---|---|
| Languages | About 30 languages with good published results; a few more with warnings |
| Access | The Telegram bot @potok_now_bot, plus its mini app for big uploads |
| Input | Voice messages, audio and video |
| File size | Files up to 2 GB |
| Other languages | The text keeps the language of the audio and is not translated |
What people get wrong here
| Mistake | What happens | Fix |
|---|---|---|
| Sending a long recording to the Whisper API unchanged | The 25 MB cap rejects the file | Split the audio or use Potok for files up to 2 GB |
| Expecting Whisper to name speakers | Whisper alone returns plain text without labels | Add the separate OpenAI model or use Potok labels |
| Treating 98 languages as equal accuracy | Results vary by language, so some come out weak | Test a short sample in your language first |
| Expecting translation to any language | Whisper translates into English only | Translate the text with another tool afterwards |
| Reading a vendor line on this page as permanent | Lists and limits change, so the line can be out of date by the time you read it | Open the vendor page for the current version before you decide |
Keep going
See the full list of languages, the tools and the glossary.
Frequently asked questions
How many languages does Whisper recognize?
Whisper supports 98 languages, with accuracy that varies by language.
What is the Whisper file limit?
The OpenAI API takes 25 MB per file. Potok accepts a file up to 2 GB.
Does Whisper translate?
Yes, but into English only. Potok does not translate text.
Can Whisper label speakers?
Not by itself; a separate OpenAI model adds speaker labels. Potok offers Speaker 1, 2 labels.
How do I use Potok without code?
Send audio to @potok_now_bot in Telegram and download TXT, MD, DOCX, PDF, SRT or VTT.
What does the table say about translation of transcripts?
For Whisper it lists Into English only, and for Potok it lists Not available. Both entries come from public pages, so check the vendor page before you decide. The wording above follows the vendor page as it was read for this comparison.
Sources
The dates show when each source was opened. Pages are edited over time; read the original before you rely on a detail.
- Whisper, official page, Whisper · checked
- Whisper speech recognition system (Wikipedia), Wikipedia · checked
Try it on your own 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.
Write to @potok_now_bot in Telegram