Convert Spanish audio to text

By the Potok teamUpdated ~2 min read

You can convert Spanish audio to text by sending the recording to the Potok Telegram bot. Published tests of others on large-v3, not our measurements, give a word error rate of 3.12, one of the best results. Regional 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 3.12 is one of the strongest published results, yet it does not break out Spain, Mexico or Argentina.
  • Written accents separate pairs of words, so a missing accent is a real error.
  • Questions and exclamations begin with an inverted mark, which is easy to lose in some tools.
  • The n with a tilde is its own letter, and a plain n would change the word.
  • Latin American and Iberian speech differ in some everyday words, and the transcript keeps the words the speaker said.

What a transcript looks like

Sample sentence in Spanish
[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

Quality for this language
LanguageVerdictPublished resultNotes
Spanish (Español)Recommendedword 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

  1. Pick the better source. A direct recording beats a voice note forwarded several times.
  2. Open the bot. Open @potok_now_bot in Telegram and send it.
  3. Large file? Use Upload. The mini app takes up to 2 GB.
  4. Test a regional voice. If the speaker has a strong regional accent, read the first minute before trusting the rest.
  5. Check accents and inverted marks. Skim for missing accents and for sentences that lack an opening question mark.
  6. Export. DOCX, PDF or TXT to share, SRT or VTT to caption a video.
What Potok can do
FeatureDetails
Where it worksTelegram bot @potok_now_bot; large files go through the bot's mini app
File sizeUp to 2 GB
ExportTXT, MD, DOCX, PDF, SRT, VTT
Speakers and timeSpeaker labels and timestamps can be switched on
LanguagesAbout 30 languages with good published results; a few more with warnings
TranslationThe transcript is not translated into another language
DictationA separate Potok desktop app lets you dictate text into any program; it recognises Russian speech

Common mistakes

Common mistakes and how to fix them
MistakeWhat happensFix
Assuming one score fits every accentNo separate figure exists for each region.Test a short clip.
Dropping accents in a quick editPairs of words that differ only by an accent change meaning.Search for the pair.
Pasting into a tool that strips the n with a tildeA plain n changes the word.Use a Unicode editor.
Not checking namesMany Spanish names have variants.Verify against a source.

More

See the full list of languages, the tools and the glossary.

Frequently asked questions

Is Spanish really that good?

Its published word error rate is 3.12 on large-v3, among the lowest, though proofreading is still wise.

Does it cover Latin American accents?

The figure does not break accents out, so test a short clip in the accent you need.

What is the limit per file?

The limit is 2 GB per file. For anything too big for a normal chat attachment, use the Upload button in the mini app.

Where does the number come from?

From published tests by other people, not our own measurements.

Does the bot give me an English version?

No. The transcript stays in Spanish, 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.

  1. Word error rate (Wikipedia), Wikipedia · checked
  2. FLEURS speech dataset (Google, Hugging Face), Hugging Face · checked
  3. 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