Potok gives you Portuguese transcription with accents and the cedilla in place. Published tests of large-v3 give a word error rate of 3.65, one of the lowest on our list, though the figure covers Portuguese in general. Files up to 2 GB are accepted through the Telegram bot.
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
- The 3.65 is a published word error rate from others' tests, not our own measurement.
- The published figure does not separate Brazilian and European speech, so your accent may behave differently.
- Written Portuguese depends on accents and the cedilla, and the tilde on vowels such as a and o.
- Speaker labels are numbered and timestamps are optional.
What a transcript looks like
[00:00] Speaker 1: Vamos começar a reunião. Primeiro, vamos revisar os resultados da semana passada e depois planejar os próximos passos.Meaning in English: Let's start the meeting. First, we'll review last week's results, then plan the next steps.
Written by us to show the script and the layout of a transcript. It is not the output of the recognition engine.
Published quality
| Language | Verdict | Published result | Notes |
|---|---|---|---|
| Portuguese (Português) | Recommended | word error rate 3.65% (large-v3, FLEURS) Canary-1B-v2 paper | Published tests show a low error rate for this language. The published figure is for Portuguese in general; Brazilian and European accents were not reported separately. |
These numbers come from published tests by other people, not from tests by Potok. Your own audio, with its noise, accents and microphone, will differ.
How to do it
- Open the chat. Go to @potok_now_bot in Telegram.
- Send the file or link. Voice messages, audio, video and YouTube links are accepted.
- Use Upload for 2 GB cases. A very long interview fits if it is under 2 GB; the Upload button in the mini app deals with it.
- Turn on the extras you need. Labels help a conversation and timestamps help a research log.
- Check the endings of verbs and names. Read a stretch where people give figures, names or places.
- Export. Use MD or TXT for notes and DOCX for shared edits.
| Feature | Details |
|---|---|
| Where it works | Telegram bot @potok_now_bot; large files go through the bot's mini app |
| File size | Up to 2 GB |
| Export | TXT, MD, DOCX, PDF, SRT, VTT |
| Speakers and time | Speaker labels and timestamps can be switched on |
| Languages | About 30 languages with good published results; a few more with warnings |
| Translation | The transcript is not translated into another language |
| Dictation | A separate Potok desktop app lets you dictate text into any program; it recognises Russian speech |
Common mistakes
| Mistake | What happens | Fix |
|---|---|---|
| Quoting 3.65 for every accent | Brazilian and European speech were not reported separately. | Try a clip from the speaker you actually have. |
| Dropping accents in search terms | Words with and without the mark are different strings, so searches miss matches. | Search both spellings. |
| Adjusting spelling to one variety silently | A reader from the other country sees the changes as errors. | Decide on a variety before editing. |
| Skipping names of people and places | Proper names are the usual weak spot in any language. | Compare them with a reliable source. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Does the transcript include accents?
Yes. It is ordinary written Portuguese, with accents, the tilde and the cedilla.
Is Brazilian Portuguese different from European?
Speech and some spellings differ, and the published figure does not split them, so test a sample.
What is the published error rate?
A word error rate of 3.65 for large-v3, from tests by others.
Can I get a PDF?
Yes. PDF is one of the six export formats.
Will it write the text in English?
No. Portuguese stays Portuguese, and the bot does not translate.
Sources
Each source was opened by hand on the date shown. Pages change, so open the source if a detail matters to you.
- Word error rate (Wikipedia), Wikipedia · checked
- FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
- Canary-1B-v2 paper, Table 11 (Whisper large-v3 on FLEURS) · 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