Samples
Spanish speech to text: a real sample transcript
What the free preview returns for a short Spanish recording (Español), with the audio, the sources and the mistakes left in.
Updated
Spanish (Español), 27 seconds, taken 2026-10-27. A narrator reading a book, with no aligned reference text, so no error rate. Output of the free preview with the language set to Spanish, not corrected.
The transcript, as the engine returned it
- No temas, le dijo Júpiter, tantas son tus quejas, que quiero convencerte de su falta
- de fundamento.
- No olvides mis palabras, verás realizados tus tres primeros deseos, sea lo que fuere
- lo que desee es. Elige lo que pueda hacerte dichoso
Download this transcript as SRT (written by the same exporter the app uses; the other formats are TXT, timestamped TXT, VTT, Markdown, JSON and CSV).
Where the recording comes from
- Source: LibriVox recording of Cuentos de Hadas by Charles Perrault (translated by Teodoro Baró), read in Spanish by Victor Villarraza, chapter 3, 64 kbps mp3 from https://archive.org/details/cuentosdehadas_1701_librivox.
- Licence: Public domain (LibriVox recordings are dedicated to the public domain; the archive.org item carries the Public Domain Mark) (creativecommons.org/publicdomain/mark/1.0/).
- Which recording: 62.197 s to 88.847 s, the first pauses of 0.4 s or more at or after 1:02 and after 25 s of audio
How every sample was made, step by step, is on the samples page. To try your own Spanish recording, use the Spanish transcription page.
Questions
What did the engine get wrong in this Spanish clip?
There is no reference text for this recording, so we cannot count its mistakes. Read the transcript against the audio.
Can I use the Spanish recording?
Public domain (LibriVox recordings are dedicated to the public domain; the archive.org item carries the Public Domain Mark). The source is named above.
Try it with your own file
Upload a recording and read the transcript.