Transcribe Spanish audio to text, free
Echo is built for Spanish first: upload an audio or video file and get the text with each speaker and their time. No account: the first 10 minutes of each file, up to 3 files a day.
Drop your audio or video here, or choose a file
MP3, M4A, WAV, OGG and OPUS (WhatsApp voice notes), MP4, MOV, WEBM… Up to 200 MB.
Free, no account needed: the first 10 minutes of each file, 3 a day. The file is deleted when it’s done and the result after 24 hours.
How accurate it is, measured
We measured it in November 2026 with 80 sentences from the public FLEURS dataset in Spanish, recorded by Latin American speakers: it got 97.4% of words right, a word error rate (WER) of 2.63%. The remaining mistakes were mostly unusual proper names and how times were written, not everyday words.
What affects the result most
More than the language, it’s how it was recorded that counts:
- Background noise, room echo and distance from the microphone.
- Several people talking at once.
- Proper names, brands and little-known acronyms: with a free account you can add them to the glossary so they’re spelt correctly.
How to do it
- 1
Upload the audio
Drag it into the tool on this page, which already has Spanish selected: MP3, M4A, WAV, WhatsApp voice notes, MP4…, up to 200 MB.
- 2
Wait a moment
Echo writes down what’s said in Spanish, with punctuation, and separates each speaker.
- 3
Copy or download the text
With times and speakers or just the text, to paste anywhere or save as TXT.
Frequently asked questions
Does it understand Spanish from Spain and Latin America?
The measurement was made with recordings of Latin American Spanish. We don’t have figures by accent, so we won’t give you one for each: try it with your own audio, it’s free.
Does the text come with accents and punctuation?
Yes: with capital letters, accents and punctuation, so you can use it without rewriting it all.
What if Spanish and English are mixed?
Echo transcribes each file in one language. Single English words used at work usually come out fine; long stretches in another language may come out worse. If it’s mostly English, choose English.
By format
Try it with your next meeting.
Create your account in a minute or ask us for a demo for your team.


