Portuguese speech to text in Potok is a recommended language. Published tests of the large-v3 model give a word error rate of 3.65 for Portuguese in general, from other people's work, not our measurement. Send voice notes, audio or video to the bot, whichever accent you speak.
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 figure covers Portuguese as a whole; Brazilian and European accents were not reported separately.
- Spelling differs a little between Brazil and Portugal, so the same sentence may be written in either form.
- Vowels in European speech are often reduced, which can make fast talk harder to follow than slow, careful reading.
- Accented letters and the nasal ending marked with a tilde are part of normal output; check they appear in your editor.
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
- Decide which variety you expect. Note whether the speaker is Brazilian or European so you know which spelling to edit toward.
- Send the recording. Open @potok_now_bot and attach the file, forward a voice message, or paste a YouTube link.
- Big files. The limit is 2 GB; the Upload button in the mini app is for the biggest files.
- Compare a minute by ear. Listen to the first minute while reading the transcript. If it matches, the rest is probably close.
- Normalise spelling. Pick one variety and change the few words that follow the other.
- Export. TXT, MD, DOCX, PDF, SRT or VTT; short results are posted in the chat.
| 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 was tested | The published figure does not split Brazilian from European speech. | Run a short clip from your own speaker. |
| Mixing both spelling forms in a final document | Readers notice the inconsistency. | Decide on a variety before editing. |
| Treating 3.65 as proof of a clean file | Real recordings are noisier than test sets. | Proofread names and numbers. |
| Leaving out timestamps for video captions | The text cannot be matched to the picture. | Switch timestamps on and export SRT or VTT. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
Which Portuguese was tested?
The published figure is for Portuguese in general. Brazilian and European accents were not reported separately.
Is 3.65 your own result?
No. It is a published result from other people for the large-v3 model.
Does the bot pick a spelling variety?
It writes what it hears, so check spelling choices that differ between Brazil and Portugal.
Can the transcript be changed into another language?
No. The text is written in Portuguese, the language of the recording, and the bot does not produce another version.
Is a long lecture fine?
Yes, a file up to 2 GB is accepted, and a long result comes back as a file.
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