To convert Portuguese audio to text, send the file to the Potok bot on Telegram. Published tests of others on large-v3, not our measurements, give a word error rate of 3.65. That figure covers Portuguese in general; Brazilian and European accents were not reported separately. Files up to 2 GB work.
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 figure 3.65 is for Portuguese as a whole, so there is no separate number for Brazil or Portugal.
- Spelling differs between the two main varieties for some words, so the output may not match your house style.
- Tildes and cedillas matter, as in the nasal endings that mark many common words.
- Speaker labels are numbers, and the bot never learns real names.
- Formal and casual address differ in spoken Portuguese, and the transcript keeps the form the speaker used.
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
- Know your target spelling. Decide whether your readers expect Brazilian or European forms, because the transcript follows the sound and may not.
- Open the bot. Open @potok_now_bot in Telegram and send the recording.
- Handle large uploads. Up to 2 GB; use the Upload button in the mini app for long files.
- Check nasal endings and cedillas. Skim for words where a tilde or cedilla might be missing.
- Fix variety-specific words. Search for a few words you know differ between the two varieties and align them.
- Export. TXT, MD, DOCX, PDF, SRT or VTT, depending on use.
| 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 |
|---|---|---|
| Assuming one accent score covers both varieties | The published number is not split. | Test a short clip in your own accent. |
| Leaving mixed spelling | Forms from both varieties appear in one text. | Unify at the end. |
| Dropping tildes in a rush | Words change meaning without the mark. | Spot-check nasal endings. |
| Sending a clip full of English terms | Foreign words get anglicised or garbled. | Review them separately. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Is Brazilian Portuguese covered?
The 3.65 figure is for Portuguese in general. Brazilian and European accents were not reported apart.
Why does my transcript use the other spelling?
The text follows the sound, and some words are written differently in the two varieties. Edit afterwards.
Is there a size limit?
Yes, 2 GB per file, with Upload for large ones.
Where does 3.65 come from?
From published tests by other people on large-v3, not from our own measurements.
Is the output translated into English?
No. The transcript stays in Portuguese , the same language as the recording you send, and it is never converted into another one.
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