Languages

Transcribir audio a texto en español, online

Sube un audio o un vídeo y recibe en pocos minutos una transcripción en español con marcas de tiempo, lista para editar. El español ya está seleccionado y puedes probarlo sin cuenta.

  • Free, no sign-up
  • No credit card
  • 90+ languages
  • TXT, DOCX, SRT, VTT, PDF

New transcription

Try one file now, no sign-up needed. A free account keeps your transcripts and lets you do more.
Auto-detected by default
Label who said what
A last resort for very noisy recordings; most files are better without it

How it works

Three steps, no setup.

  1. 01Step · 01

    Upload

    Drop an audio or video file. Choose the language and whether to label speakers.

  2. 02Step · 02

    Transcribe

    We extract the audio, transcribe it and identify speakers. Watch progress live.

  3. 03Step · 03

    Use it

    Read along with the player, jump by clicking a line, and share the transcript.

Cómo pasar un audio a texto

Arrastra el archivo a la zona de carga: MP3, M4A, WAV, un audio de WhatsApp o un vídeo MP4, MOV o WebM, del que se extrae el sonido automáticamente. También puedes grabar con el micrófono del navegador o pegar un enlace de YouTube o TikTok. El español ya está elegido en esta página.

En unos minutos aparece el texto en párrafos con marcas de tiempo. El reproductor resalta la línea que suena. Haz clic en una línea para volver a escucharla y corrige la palabra ahí mismo. Después exporta a TXT, DOCX, PDF, SRT, VTT o CSV. Puedes probar sin registrarte, y con una cuenta gratuita la transcripción queda guardada.

Accent marks and homophones that change meaning

Spanish spelling is close to pronunciation, but several pairs of words sound the same and differ only in an accent mark or a letter. The model chooses from context, and these are the spots where a careful reader still finds errors.

  • Diacritical accents: tú and tu, él and el, sí and si, más and mas, sé and se, té and te. In indirect questions the accent stays: no sé qué hacer, dime cómo llegaste.
  • Verb forms that differ by stress: habló and hablo, está and esta, término and terminó. A missing accent changes the tense or the word.
  • Solo and demonstratives. Current academic rules write solo and este without an accent, but many writers still use sólo and éste. Choose one convention and apply it.
  • Silent h and b/v: a and ha, echo and hecho, vaya, valla and baya. With yeísmo, haya, halla and aya also sound alike.
  • Seseo pairs, common in Latin America and southern Spain: casa and caza, coser and cocer. Context usually settles them, but check rare words.
  • Lowercase days, months, languages and titles: lunes, noviembre, el inglés, el señor García. The abbreviation of usted is Ud. or Vd.

Numbers, dates and money by country

There is no single Spanish number format. Spain writes a decimal comma (3,5 %), while Mexico, Central America and parts of the Caribbean usually write a decimal point (3.5 %). Current academic advice prefers a space for thousands (10 000), but a period or comma is common in practice. Decide which country's format your reader expects before you clean up the figures.

Dates go day first: 4 de noviembre de 2026 or 04/11/2026. Ordinals are written 1.º and 2.ª. Years never take a separator: 2026, not 2.026.

Times can appear as las 14:30 or as 2:30 p. m., and amounts as 12,50 € or $1,500 depending on the country. A transcript writes what it hears, so read every amount against the audio when it matters.

Checklist before you share a Spanish transcript

Keep the audio open and run through this list. It takes a few minutes and catches most of what a reader would notice.

  • Search for si, el, tu, mas and que and confirm the accent in each case.
  • Check names, surnames with particles (de la Fuente) and place names.
  • Choose one number format for the whole document.
  • Look for a missing opening ¿ or ¡ in fast exchanges.
  • Decide whether to keep muletillas such as este, o sea and pues for a verbatim record.
  • Read the SRT in your video tool before publishing subtitles.
  • Switch timestamps and speaker names on or off at export.

Spanish recordings that come up most

Students bring interviews for a TFG or TFM in Spain, or for a tesis in Latin America. Others upload recorded classes, WhatsApp audios from family or clients, homilies, neighbourhood association meetings, and podcasts. Speaker labels that show who said what are available on paid plans or with a Minute Pack.

For a TFG appendix, keep timestamps on in the DOCX export so the tribunal can find each quote. For the minutes of an asamblea, switch them off and keep the speaker names. WhatsApp audios can be uploaded as the file the app exports, or as the original from the phone.

FAQ

Español Audio to Text: questions, answered.

¿Es gratis convertir audio a texto?+

Puedes probarlo sin registrarte. Con una cuenta gratuita guardas tus transcripciones. Los límites del plan Free aparecen en la sección de precios de esta página.

¿RocketScribe traduce el audio al inglés?+

No. La transcripción queda en español, el idioma hablado. Puedes abrirla con el enlace de Google Translate o usar la exportación «AI prompt» con ChatGPT, Claude o Gemini.

Why does the transcript write 3.5 when Spain uses 3,5?+

Number style varies across Spanish-speaking countries, and the transcript can mix formats. Pick the format your reader expects and adjust the figures while you review.

Does it write sólo with an accent?+

It may write either form. Current rules prefer solo without an accent, so pick your convention and search the transcript for it.

Can I use it for TFG, TFM or thesis interviews?+

Yes. You get a timestamped draft to correct against the audio and export to Word. Apply your university's transcription conventions while you edit.

Do I need an account?+

No. You can transcribe one file right away without signing up. A free account then gives you 3 files a day (120 minutes a month) and keeps your transcripts: the file you transcribed before signing up moves into the account.

Which formats are supported?+

Any common audio or video file: MP3, WAV, M4A, AAC, FLAC, OGG, MP4, MOV, WEBM, MKV and more. We extract the audio from video automatically.

How accurate is it?+

On clear recordings expect accuracy comparable to leading transcription services. Background noise, crosstalk and heavy accents reduce it, as they do everywhere.

Pricing

Start free. Pay only if you need more.

The Free plan needs no card. Paid plans add longer files, batch uploads and speaker identification.

Free

$0

no card required

For trying it out and the occasional file.

  • 3 files a day
  • 120 minutes a month
  • Timestamps and synced player
  • AI prompt export and translation
  • Transcripts kept for 30 days
Start free
PlusMost popular

$6/ month

billed $72 yearly

For people who transcribe every week.

  • 1,200 minutes of transcription a month
  • Speaker identification included
  • Files up to 300 minutes and 5 GB
  • Upload 20 files at once
  • Up to 5 files processed in parallel
  • Priority processing
Get Plus
Unlimited

$10/ month

billed $120 yearly

For heavy users and small teams.

  • Unlimited transcription*
  • Speaker identification, 2,400 minutes a month
  • Files up to 600 minutes and 5 GB
  • Upload 50 files at once
  • Up to 5 files processed in parallel
  • Priority processing
Get Unlimited

Minute Packs

One-timefrom $1 per 60 minutes
  • Plus limits on Free: longer files, batch uploads
  • Speaker identification
  • No RocketScribe line in your exports
  • Valid 12 months, packs stack

Top up any plan. Stackable and valid for 12 months. A pack's minutes are one shared pool for whatever your plan doesn't cover: transcription on Free and Plus, speaker identification (and transcription past fair use) on Unlimited. On Free, a pack also unlocks Plus limits, with transcription and speaker identification both drawn from it.

* Fair use: 12,000 minutes a month. Beyond that, uploads pause until the next cycle or a Minute Pack. Prices in USD.

Transcribir audio a texto en español, online

Pick a file, choose the language, press Transcribe. No sign-up needed to try.

Transcribe a file