QuillHubQuillHub
RU

Spanish transcription: speech to text online

Upload a Spanish recording or paste a YouTube link. QuillHub writes down the speech in Spanish with punctuation, including the opening ¿, splits it by speaker, and adds timestamps. Need it in English? Translate the finished transcript in one click.

20,000+hours transcribed

60 free minutes when you sign up · No card required

  • YouTube
  • TikTok
  • Google Drive
  • Direct file link
  • Files MP3, WAV, M4A, OGG, MP4, MOV, WEBM

Sample transcript

What a 16-minute conversation in Spanish looks like as text

Real QuillHub output with no manual edits: 16 minutes of recording, 2 voices separated automatically, every line with its own timestamp. Above the text: chapters and a summary. Switch the tabs to see each layer.

Entrevista Spanish with Vicente — Consejos para visitar Sevilla00:00 / 15:47 · Vicente, MaríaReady · 4 documents
  • María1:41

    Hola, muy buenas a todos, por cierto. Pues nada, yo soy María, profesora de español. Tengo un canal en YouTube que se llama María Español y enseño también, como Vicente, a estudiantes intermedios-avanzados, más o menos.

  • María2:25

    En Andalucía.

  • María4:48

    A ver, Sevilla, si vienes en verano, es un infierno, pero si vienes en primavera o en otoño, es una maravilla.

  • Vicente5:59

    No me gusta. Yo sí paso calor. Si tengo que pasar calor, solo lo paso si es de camino a la playa.

  • María6:53

    Algo que no es lo típico y que yo siempre recomiendo a mis estudiantes, pero solo si tienen un montón de días en la ciudad. O sea, si tienes 2 días, no, porque obviamente lo típico merece mucho la pena.

  • María10:11

    Hay de todo, absolutamente de todo. Te puedes encontrar bares de tapas, que no significa que las tapas no estén bien. Hay tapas que están muy, muy bien. Que las tapas pueden costar alrededor de 3 euros, algo así. Está súper barato.

71 more turns, each with a speaker label and a timestamp; click a timestamp to jump the audio there

Speech split by person

Free speech-to-text hands back one paragraph for the whole recording. Here the voices are separated and every turn carries its own timestamp, so the text is readable straight away.

  • 2 voices separated automatically, no setup
  • Vicente — 59%, María — 41% of the time
  • Export to TXT, DOCX, SRT, and VTT
  • 0:00Introducción2 min
  • 1:39Presentación de la invitada1 min
  • 2:00Introducción a Sevilla1 min
  • 2:24Rivalidad y orgullo andaluz2 min
  • 4:19Planes de viaje y mejor época2 min
  • 6:36Monumentos imprescindibles y lugares menos conocidos2 min
  • 8:46Dónde salir de fiesta en Sevilla1 min
  • 9:58Precios y presupuesto para salir1 min
  • 10:55Tapas y caña: ¿están incluidas? (comparación con Granada)1 min
  • 11:54Ventajas y contras de las tapas gratuitas1 min
  • 12:33Anécdota: adaptaciones del camarero1 min
  • 13:07Planes y recomendaciones: Itálica, Cartuja y Alameda1 min
  • 13:50Cierre de la entrevista y despedida1 min
  • 14:40Conclusión, enlaces y llamada a la acción1 min

Each chapter has its own timestamp and length

The whole 16 minutes at a glance

Chapters follow the meaning, not the pauses, so you can see what each part of the recording covers and jump to the one you need.

  • 14 chapters across 16 minutes
  • Each chapter links to its place in the recording

Vicente entrevista a María (canal 'María Español') en una conversación informal sobre Sevilla: rivalidad con Málaga, recomendaciones para visitar la ciudad (épocas recomendadas, monumentos típicos y lugares menos turísticos como Itálica e Isla de la Cartuja), zonas para salir (Alameda de Hércules)…

  • La entrevista busca una conversación informal entre dos nativos para mejorar comprensión auditiva.
  • Septiembre-octubre es una época recomendada para visitar Sevilla; el verano puede ser extremadamente caluroso.
  • Los monumentos típicos (Giralda, Torre del Oro, Plaza de España) merecen la visita en estancias cortas.

Decisions the AI pulled out

  • Recomendar visitar Sevilla en otoño (septiembre-octubre) para mejor clima.01
  • Incluir Itálica e Isla de la Cartuja como recomendaciones fuera del centro histórico.02
  • Sugerir la Alameda de Hércules como zona principal para tapear y salir de fiesta.03
  • Publicar y compartir la colaboración en ambos canales (ya grabada y con enlace en la descripción).04

No need to replay 16 minutes

The summary is built from the broadcast itself: key ideas, numbers and the decisions that were actually announced. It can go into a team chat as it is.

  • 4 decisions pulled from the conversation
  • 7 key points in the full summary
One-page digest

Introducción y presentación de María, creadora del canal 'María Español'.

from the recording
Article draft

“Entrevista Spanish with Vicente — Consejos para visitar Sevilla”: Sevilla, viajes, turismo

from the recording
Follow-up email

What was discussed, what was decided, what happens next

template
Task list

Dejar en la descripción y en el vídeo el enlace a la colaboración publicada en el canal de María

from the recording
Ask the recording

“Crear itinerario de 3 días en Sevilla basado en la entrevista”: the chat answers from the text and gives the timestamp

chat
Your own prompt

A CRM note, a post, talking points — or any format you need

anything
  • Itálica
  • Isla de la Cartuja
  • Alameda de Hércules
  • Giralda
  • Plaza de España
  • Tapa/Caña

Every AI action is included in the Unlimited plan — no credits per click.

Finished documents on top of the text

The transcript is only the start. From one recording you can build a digest, an article draft or an email — or describe a format of your own.

  • Ready-made templates and your own prompts
  • Chat over the recording: ask anything about the text
  • 6 terms with definitions
Upload your recordingSee the full example(opens in a new tab)60 free minutes when you sign up · No card required

Example: “Conversación en español entre profesores de español”, Spanish with Vicente, YouTube, license CC BY 4.0. Transcript, chapters, summary and key points by QuillHub.

How it works

How to transcribe Spanish audio to text

Three steps in a browser, on a computer or a phone. Nothing to install.

  1. 1

    Add the recording

    Drag a file into the form or paste a link to a YouTube video, a TikTok, or a file in Google Drive. MP3, WAV, M4A, and video files such as MP4, MOV, and WEBM upload as they are.

  2. 2

    Choose Spanish

    Open Speaker Recognition & More Settings and pick Spanish under Audio Language. Auto Detect works too when Spanish is the main language of the recording. Then press Start transcription.

  3. 3

    Read, edit, download

    The transcript opens in your browser. Fix a word in place, translate it into English if you need to, and download DOCX, TXT, Markdown, or SRT and VTT subtitles. Recordings longer than three minutes also get a summary and chapters in Spanish.

What you get

What a Spanish transcript includes

Readable Spanish text, the voices kept apart, and a way back to the audio for every line.

¿, ñ, and accents

Punctuation is added automatically, including the inverted ¿ at the start of a question. Accented letters and ñ are written as they should be: in the sample on this page, “¿Cuál es tu ciudad?”, “Andalucía”, and “España” come out right.

Paragraphs, not a wall of words

A long conversation or lecture is split into paragraphs by meaning, so you can read it like an article and find the part you need.

Speakers kept apart

In an interview, a class, or a call, lines are split by voice. Rename Speaker A and Speaker B once, and the names carry into the export.

Timestamps on every line

Click a timestamp and the audio plays from that moment. A doubtful word is easy to hear again without scrubbing through the whole file.

Summary in Spanish

Recordings longer than three minutes get a summary, key points, chapters with timestamps, and a list of terms, all in the language of the recording.

Questions in English

The AI chat answers in the language you ask in. Ask a Spanish lecture a question in English and get an English answer with the moment it comes from. The transcript itself stays Spanish.

AI on top of the transcript

Spanish calls in text, answers in English

A buyer in Texas talks to a supplier in Monterrey every week, in Spanish. Each call becomes Spanish text, and before the next order she asks in English what was agreed.

Supplier call, Monterrey · 2 speakers41:15
What lead time did they promise for the March order?

Six weeks from the deposit, not from the order date. He said tooling for the new lid takes two of those weeks, so the date moves if the artwork changes.

Call 6 · 27:40 — the fragment is lit on the track
Have they raised the price before?

Once, in the second call, by 4% on the 500 ml bottle after a resin price change. In this call he said the March price holds if the order is confirmed by February 15.

6 calls in the archive
call 2 · price change
call 6 · lead time
01

Ask across every call

The chat searches all your transcripts at once: who promised what, when the price changed, what is still open.

02

Summarize, follow-up, tasks

Summarize, Follow-up, Tasks, and Blog post buttons sit in the chat of every recording. For anything else, write your own request.

03

Access for your AI agents

The MCP server lets Claude and other AI agents work with your transcripts directly.

Every AI action is included in the Unlimited plan — no credits per click.

Spanish speech

What trips up Spanish speech recognition and what to do about it

Every example comes from the sample on this page: 16 minutes of two teachers from Málaga and Seville, checked against the video’s hand-made Spanish subtitles.

In the recordingWhy it's hardWhat QuillHub doesWhat you can doWhere to check
Si and sí, tu and túAn accent mark changes the word (si is “if”, sí is “yes”), but both sound the samePicks the spelling from context and sometimes guesses wrong: “Yo, si paso calor…” (“If I’m going to be hot…”) became “Yo sí paso calor”Before you quote a line, reread si/sí, tu/tú, el/él, and mas/másRaw Text, 5:59
Fast, casual speechShort words get swallowed when people talk quicklyWrites what it hears: “uno de los más importantes” became “con otros más importantes”, and “porque no salgo mucho” became “pues no salgo mucho”Check quotes against the audio; a click on the timestamp plays that spotRaw Text, 7:27 and 9:04
Verb tensesIn relaxed speech, “he ido” and “había ido” are only a syllable apartCan pick the neighboring tense: “que he ido un par de veces” became “que había ido un par de veces”If you study tenses from a transcript, listen to the verbs that matterRaw Text, 11:26
Fillers and repeatsPeople repeat words and restart sentencesKeeps repeats (“mis mis dos amigos”) and can glue a pause into a word: “3 cañas, bebes” became “3 cañas de bebes”For a clean quote, remove repeats with Edit textRaw Text, 6:14 and 11:42
Capitals mid-sentenceThe text is assembled from short pieces of speechSometimes starts a piece with a capital letter in the middle of a sentence: “Tampoco”, “Discotecas”, “Limitado”Fix them in place: Edit text, then click the paragraphRaw Text, 8:59, 9:28, 10:52
NumbersSpanish style guides spell out small numbers in running textWrites them as digits (“3 meses”, “2 días”) and prices with a decimal comma, Spanish style: “4,50”For publishing, swap digits for words with Find and replaceRaw Text, 5:13, 6:58, and 10:31
Spain and Latin AmericaMexican, Argentine, Caribbean, and Andalusian Spanish sound different; Andalusians often drop the final sOne Spanish option for every country. The sample on this page is Andalusian; the mistakes above are about fast speech and spelling, not about the accentChoose Spanish whatever the countryRecheck a doubtful word by its timestamp

Which Spanish recordings people transcribe

Spanish speech is easier to work with as text when you need to reread it, quote it, study it, or pass it to a colleague.

Spanish lessons and tutoring

A recorded lesson becomes text with chapters. New words and phrases are on the page, not only in your ear.

Listening practice

Paste a link to a Spanish podcast episode or video and read along while you listen, marking the words you don't know.

Calls with Latin America

Agreements with partners in Mexico, Colombia, or Chile stay in the transcript and the summary. A disputed number is one click away.

Interviews for an article or a thesis

A conversation with a Spanish-speaking source is split by speaker. Find the quote with search instead of listening again.

University lectures and conferences

Open courses and talks in Spanish are transcribed in full, even two-hour ones: a file can be up to 10 hours long.

Your own speaking practice

Record an answer on the Microphone tab before a DELE or SIELE exam and read it back: you'll see where you paused, repeated yourself, or mixed up a tense.

Who it's for

Who uses Spanish transcription

Fast native speech is hard to follow for an hour even with good Spanish. Text reads faster than speech, and you can search it.

Spanish learners

Native speech on the page

Upload a lesson, a podcast, or a show and read the text next to the sound. An unfamiliar word is spelled out, and the terms are collected in a list with explanations.

  • Chapters with timestamps for review
  • A list of terms from the recording
  • Questions about the recording in English

Translators and journalists

The Spanish original, ready to work with

An interview or a speech becomes text split by speaker. A translator starts from the written original instead of taking it down by ear.

  • Lines split by voice
  • Timestamps on lines and chapters
  • DOCX export for editing
QuillHub for media

Sales and sourcing

A Spanish call without manual notes

Negotiations with a supplier in Spain or a client in Mexico stay in writing. Colleagues who missed the call read the summary.

  • A call summary in Spanish
  • A follow-up email with the Follow-up button
  • Calls recorded on your computer with QuillHub Desktop
QuillHub for sales

Researchers

Field interviews in Spanish

Interviews from research in Spanish-speaking countries upload together. The chat answers across all of them: who talked about price, where people complained about service.

  • Several files in one upload
  • Speakers renamed by role
  • Answers across every interview
QuillHub for product research

Tips

How to get an accurate Spanish transcript

Accuracy depends mostly on the sound and on the language you pick. A few habits that help.

  • Pick Spanish yourself

    If the recording opens with music, an intro, or a few words in English, choose Spanish under Audio Language. An explicit choice turns off auto-detection.

  • Split bilingual recordings

    There is one language per recording, chosen by the main speech. If a class goes back and forth between English and Spanish in equal parts, cut it and upload the parts separately.

  • Check names and rare words

    Names, places, rare terms, and words with accent marks are where mistakes cluster. Fix a name once with Find and replace and turn on Save to vocabulary, so new recordings get it right too.

  • Fix the text, then translate

    Correct words in the Spanish transcript first: Edit text, then click a paragraph or use Find and replace. A translation made before the edit is marked “made before the text was edited” and isn’t redone automatically.

  • Upload the original file

    An M4A from iPhone Voice Memos or an MP4 from Zoom uploads as is. Converting it only loses quality, and the form takes files up to 5 GB.

  • Paste videos as a link

    No need to download a YouTube video. QuillHub takes the audio and recognizes it again, so you get text even for a video without captions. The video has to open without signing in.

Without the website

Spanish transcription in Telegram

If you use Telegram, forward a Spanish voice message or audio file to @QuillAI_Bot. It is the same service; once you link Telegram to your account, the transcript also shows up in the web app.

Open @QuillAI_Bot
  • Send a file with Share
  • Minutes and plan shared with the website after linking
  • Transcripts from the bot land in your account after linking

Pricing

The more you record, the cheaper the hour

Start free, pay only when you need more.

Our lowest price
Unlimited

from$6.66per month

Six months of unlimited — $39.99 up front. Minutes are not counted at all.

Get Unlimited

Six months — $39.99, billed once.

What $6.66 a month works out to

10 hours$0.67/hr
20 hours$0.33/hr
50 hours$0.13/hr

The same $6.66 in one-off packs buys about 500 minutes — roughly eight hours. Then they run out; Unlimited doesn’t.

Month by month the same half-year would cost $59.94 — a $19.95 difference.

One-off minute packs
from $2.99
Not a subscription. Minutes never expire and stack with your balance.
150 minutes — $2.99350 minutes — $4.99750 minutes — $9.992,950 minutes — $29.99

The minute gets cheaper with volume: from $0.020 in the smallest pack to $0.010 in the largest.

Start
$0
60 minutes when you sign up
  • 60 minutes to try, they don't expire
  • All languages and speaker recognition
  • Export to a document
  • No card required
Get started
Team

A shared workspace, projects and roles. Invoice billing and paperwork for companies.

$14.99per seat, per month
Start a team

Questions

Spanish transcription FAQ

If your question isn't here, write to support.

It is turning Spanish speech from an audio or video recording into written Spanish text. Automatic transcription does it with a speech recognition model and adds punctuation, speaker labels, and timestamps. The text stays in the original language.

A speech recognition model turns the sound into Spanish words, adds punctuation including the inverted ¿, tells the voices apart, and marks the time of each line. For recordings longer than three minutes, a second model reads the finished text and writes a summary, chapters, key points, and terms in Spanish. Shorter recordings get plain text only, without speakers or timestamps.

Yes, in two steps. QuillHub first transcribes the Spanish speech into Spanish text, then the Translate button in the transcript window makes an English translation. Translating doesn't use your minutes, but it needs minutes left on your balance or an active plan. You can download the translation as DOCX, TXT, or SRT subtitles. The summary and chapters stay in Spanish. There is no voice-over: you get text, not English audio.

Yes. You get 60 free minutes when you sign up, no card required. That covers a lesson or a few short recordings. After that, minute packs start at $2.99, or Unlimited costs $9.99 a month.

Everyday speech comes out well; mistakes cluster in fast casual phrases, accent marks that change meaning, and names. In the 16-minute sample on this page, compared with the video’s hand-made subtitles, the errors we found were a few swallowed words, one tense, one si written as sí, and some capital letters in the middle of sentences. QuillHub doesn’t claim an accuracy percentage: check the lines you quote by their timestamps.

Yes. There is no separate setting per country: Mexican, Argentine, Colombian, Caribbean, and European Spanish all use the same Spanish option. The sample on this page is Andalusian Spanish from Málaga and Seville. Noise, echo, and people talking over each other affect accuracy more than an accent does.

One language is chosen for the whole recording, by the main speech. If a conversation is mostly Spanish with English words thrown in, the text is Spanish and the English bits are written as best the model can. When both languages take about half the time, cut the recording and upload the parts separately, each with its own language.

Not always. The default is Auto Detect, which picks one language for the whole recording by its main speech. If the recording starts with music or English, open Speaker Recognition & More Settings and choose Spanish under Audio Language.

Spanish. The summary, chapters, key points, and terms are written in the language of the recording. For an English recap, ask for one in the AI chat of the recording.

No. QuillHub is automatic: a recording is transcribed in minutes, and you check and correct the text yourself in the transcript window. For transcripts that must be certified word for word, such as court records or medical files, use a human transcription service.

Yes, by link. Paste the video address on the Paste Link tab. QuillHub downloads the audio and recognizes it again, so you get text even for a video without captions. The video has to open without signing in.

No. Phonetic transcription shows how a word is pronounced, in IPA symbols, and that is a job for dictionaries and pronunciation tools. Here transcription means writing down speech from a recording as ordinary Spanish text. By the way, the Spanish word for transcript is «transcripción».

Audio such as MP3, WAV, M4A, OGG, OPUS, AAC, and WMA, and video such as MP4, MOV, AVI, MKV, and WEBM. Files can be up to 10 hours and 5 GB, several at a time. Download the text as DOCX, TXT, or Markdown, and subtitles as SRT or VTT.

Your data

What happens to your recordings

Doctor's appointments, legal consultations and therapy sessions go through QuillHub. That is why we say this plainly instead of burying it in the terms.

Who processes your data

Encryption — files and transcripts are encrypted in transit and at rest, and only you and the people you share a link with have access.

Never used for training — recordings are not used to train models and are not passed to third parties.

Delete anytime — a recording can be deleted at any moment, together with its transcript and everything derived from it.

Transparent subprocessors — the list of services involved in processing is published on its own page.

Transcribe Spanish audio for free

60 minutes when you sign up, no card required. Add a recording or a video link, and the Spanish text is ready in a few minutes.