Spanish speech to text in Potok is a recommended language with one of the best published results: a word error rate of 3.12 for the large-v3 model. It is a figure from other people's tests, not our measurement. Send voice notes, audio or video, then check names and numbers.
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
- Spain, Mexico, Argentina and other regions were not reported separately, so the one number covers many accents.
- Spanish is spelled very regularly, so most remaining errors sit in names, foreign words and homophones.
- Questions and exclamations begin with an inverted mark in correct writing, which is worth checking in the text.
- A low score on clean test audio says little about a loud room, a bad line or overlapping speakers.
What a transcript looks like
[00:00] Speaker 1: Vamos a empezar la reunión. Primero repasaremos los resultados de la semana pasada y después planificaremos los próximos pasos.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 |
|---|---|---|---|
| Spanish (Español) | Recommended | word error rate 3.12% (large-v3, FLEURS) Canary-1B-v2 paper | Published tests show a low error rate for this language. One of the best published results; regional accents (Spain, Mexico, Argentina and others) 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
- Note the accent. Make a one-line note of where the speaker is from. It helps you judge which errors are accent-related.
- Send it over. Open @potok_now_bot and share the file, a forwarded voice message or a YouTube link.
- Large recording. The limit is 2 GB, and the Upload button handles the heavy ones.
- Check homophones. Words that sound alike, such as ones differing only by a silent letter, need context to get right.
- Check proper nouns. Names of people, streets and companies come last in a read-through.
- Export. TXT, MD, DOCX, PDF, SRT or VTT; short texts also appear 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 |
|---|---|---|
| Trusting a top score for every accent | The tests do not split by region. | Test a clip from your own speaker. |
| Sending a conference-hall recording from the back row | Reverberation hides consonants. | Use a closer recording or a lapel microphone. |
| Ignoring names | Names are the least predictable words. | Make a name list and search for each. |
| Using TXT for caption work | Timing is lost. | Export SRT or VTT instead. |
More
See the full list of languages, the tools and the glossary.
Frequently asked questions
What does 3.12 mean?
It is a published word error rate for the large-v3 model on Spanish, one of the best results we list.
Are those your measurements?
No. They come from published tests of others.
Do all accents score the same?
Published figures do not say. Regional accents were not reported separately.
Does the bot keep the language?
Yes. The transcript stays in Spanish, whatever the accent, and is not turned into another language.
Is there a size limit?
Files up to 2 GB are accepted, and the Upload button in the mini app suits the largest ones.
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
- Whisper speech recognition system (Wikipedia), Wikipedia · 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