Spanish voice to text on Mac: accents, ñ and usted
Accent marks, the ñ, the opening ¿, and the choice between tú and usted. Here is what a Spanish voice typing app has to get right, and how to check it with one sentence.
Yes, you can turn Spanish speech into text on your computer, and Apple's built-in dictation supports Spanish in several regional settings. But Apple's dictation leaves out the ¿ and ¡, guesses at accent marks, and keeps your "este... o sea" in the text. Lipo is our app. It transcribes Spanish (turns your speech into text), then cleans it up. Cleaning up means it fixes accents and ñ, adds ¿ and ¡, and removes filler words (sounds like "este" that carry no meaning). It keeps your tú or your usted, then pastes the result into any text field (a box where you can type). It can also paste English instead. You will see this called Spanish voice typing and Spanish voice dictation, which are the same thing.
Our European languages roundup covers Spanish briefly. This post is the long version.
Why is Spanish voice typing hard?
Spanish is hard because the details that mark careful Spanish are the details that cheap dictation throws away.
Accent marks come first. "Está" and "esta" are different words, and so are "sí" and "si", "él" and "el", and "cómo" and "como". Many apps handle the common cases and then fail on "qué" and "que" in indirect questions. To get that right, the app must understand the whole sentence.
Next is the ñ. "Año" and "ano" are not the same word, and English-first models often replace ñ with a plain n.
Correct Spanish opens a question with ¿ and an exclamation with ¡. Apple's dictation inserts commas, periods and question marks in Spanish, but Apple does not say whether the opening ¿ and ¡ are included. Test it with one question before you trust it, because a missing ¿ is still wrong in a cover letter or a legal document.
Register (the level of formality) is another problem. Spanish makes you choose tú or usted in every sentence, and the wrong choice is either rude or strangely stiff. Argentina, Uruguay and much of Central America also use vos ("tenés", "querés").
Regional speech adds more. A Mexican says "computadora", and a Spaniard says "ordenador". Caribbean Spanish drops final consonants ("pa'lante", "eh'toy"). A model trained mostly on Castilian news speech hears a fast Cuban sentence and writes words that were never said.
How to voice type in Spanish with Lipo
You do not need to change your keyboard layout.
- Install Lipo from uselipo.com. It needs macOS 15.2 or later. There is a free trial.
- During onboarding, pick Spanish as your dictation language. You can change it later under Dictation, then Language. Lipo can also auto-detect the language (guess which language you are speaking), but choosing Spanish gives better results.
- Grant the microphone and accessibility permissions (settings where you allow the app to use part of your computer). The accessibility permission lets Lipo paste into other apps.
- Click into any text field. Mail, WhatsApp Desktop, Gmail in Safari, Slack, Notion and a code editor all work. The cursor is the blinking line that shows where text will go.
- Hold the hotkey and speak. A hotkey is a key you press to start recording, and the default is the right Option key. When you release the key, Lipo transcribes your speech, cleans it up, and pastes the finished text where your cursor is. Cleaning up means Lipo removes filler words and false starts (words you begin, stop, and then say again), adds punctuation, and fixes small mistakes. Lipo does not type letter by letter, and it does not show text while you speak.
Here is a message with the kind of mess real speech has in it. Six different problems, all in one message.
You say:
"Ehh, oye, mira, la tienda... la tienda en línea la subimos el martes, no, perdón, el miércoles, porque falta el, el tema de los pagos. Ya subí las fotos, son como veinticinco. Y el descuento quedó en quince por ciento, no en veinte. Avísale a Caro que el archivo nuevo se llama catalogo punto pdf, o sea el nuevo, no el viejo, porfa."
Lipo pastes:
Oye, mira, la tienda en línea la subimos el miércoles, no el martes, porque falta el tema de los pagos. Ya subí las fotos, son como 25. El descuento quedó en 15%, no en 20%. Avísale a Caro que el archivo nuevo se llama catalogo.pdf, no el viejo, porfa.
Six things happened there:
- The correction was kept, not the first answer. You said Tuesday, stopped, and said Wednesday. The message says Wednesday.
- The stutter is gone. "la tienda... la tienda" and "el, el tema" are each written once.
- Filler is gone. "Ehh", "perdón" and "o sea" do not appear.
- Numbers are written as digits. "veinticinco" became 25, "quince por ciento" became 15%. Lipo never changes the value of a number, only how it is written.
- A spoken symbol became the symbol. "catalogo punto pdf" became catalogo.pdf, because you were clearly saying a file name.
- Your Spanish stayed yours. "Oye", "mira", "avísale" and "porfa" are all still there. Casual mode fixes the writing, not the way you talk.
For a long email, switch to Toggle mode in settings. Press the hotkey once to start and again to stop.
Does Lipo get tú, usted and vos right?
Casual mode keeps whatever you spoke, and Formal mode moves the text toward usted. One afternoon includes a WhatsApp message to your sister ("mandame la foto") and an email to a client ("le agradecería que me enviara la factura"). In Casual mode, Lipo fixes accents and punctuation and leaves your tú, your vos and your regional words alone. In Formal mode, Lipo rewrites the text in a professional style, and you can pin a mode to an app. You say: "porfa mandame el reporte de la junta". Lipo writes: Por favor, envíeme el informe de la reunión. Pin Formal to Mail and Casual to WhatsApp Desktop, and the same hotkey produces the right register in each app.
Lipo recognizes standard Spanish and regional accents, including Mexican, Castilian, Rioplatense, Colombian, Chilean and Caribbean speech. Heavy dialect words, such as Chilean "cachai" and "po", may be written in the standard form. If a sentence comes out wrong, tell us.
"Tengo un meeting con el team a las tres, después te hago un call" is normal Spanglish in Miami and San Antonio. Single-language dictation hears "meeting" and either drops it or writes the nearest Spanish sound. Lipo recognizes both languages in the same sentence and writes the English words as English. The two languages at once post explains this.
Speak Spanish, paste English
Many Spanish speakers write English all day, to a manager, a client or a university. You think of the sentence in Spanish, translate it in your head, and then type English. Lipo lets you skip the middle step.
In Lipo's settings, open the Translation tab and set "Lipo pastes" to English. Then choose when translation happens:
- Always translate. Every dictation comes out in English.
- Translate with this hotkey. Your normal hotkey pastes Spanish, and a second hotkey pastes English.
With translation on, Lipo transcribes your Spanish, cleans it up, translates the cleaned text, and then pastes it. If you translate raw speech with the "o sea" still in it, you get English that is fluent but empty.
When you write in a second language, you often say less than you mean, because you are thinking about grammar. In Spanish you know when to write "un abrazo" and when to write "saludos cordiales". When you speak Spanish and Lipo translates it, the meaning and the tone stay.
Here is a whole email, spoken the way people actually speak one.
You say (Spanish, Formal mode, output language set to English):
"Hola Andrea, eh, mira, te escribo por lo del reporte. Este... no vamos a llegar al viernes, o sea, necesitamos hasta el lunes, porque nos falta información de dos áreas. Lo que falta es, primero, los números de septiembre, segundo, las fotos de la bodega, y por último la firma de Legal. En cuanto tenga eso te lo mando el mismo día, ¿va?"
Lipo pastes:
Hi Andrea,
I am writing about the report. We will not make Friday and need until Monday, because we are still missing information from two areas:
1. The September figures
2. The warehouse photos
3. The sign-off from Legal
As soon as I have those, I will send it to you the same day.
Read that against what you said. "Hola Andrea" became a proper greeting, because you spoke one. Lipo will not invent a greeting, a subject line or a sign-off you did not say, which is why the message ends where your speech ended instead of adding "Best regards". "Primero, segundo, y por último" became a numbered list and the marker words themselves disappeared. "Eh", "este", "o sea" and "¿va?" are gone, and "no vamos a llegar" became "we will not make", because Formal mode writes out contractions.
The numbers in that list are ordinary characters, not formatting. Lipo pastes plain text, so the list survives in Slack, WhatsApp and any box that does not understand Markdown.
The translation docs explain every setting. The reverse direction works too. Set "Lipo pastes" to Spanish, speak English, and Lipo pastes Spanish with the accents and the ¿ in place. The dictate and translate guide shows more examples. Translation has a monthly word limit on the smaller plan; see pricing for plans and limits.
For names that keep coming out wrong, use the dictionary. Add a word spelled the way you want, and Lipo uses that spelling in every language and after translation. You can set "Ximena" instead of "Jimena", or "fecha límite" instead of "deadline".
What about Wispr Flow, Willow Voice, Aqua Voice and superwhisper?
Here is how the four compare with Lipo on the things that matter for Spanish.
| Lipo | Wispr Flow | Willow Voice | Aqua Voice | superwhisper | |
|---|---|---|---|---|---|
| Spanish | Yes | Yes | Not sure | Yes | Depends on the model |
| English words inside a sentence in your language, written in your script | Yes | No, one language per recording | Switches mid-sentence, script not stated | Not documented | Not documented |
| Voice typing translation: speak one language, paste another | Yes, any pair | No | No | No | Into English only |
| Tone modes | Casual, Formal, Vibe Coding | Yes | Yes | Yes | Custom modes |
| Screenshot attached to dictated text | Yes | No | No | No | No |
| Video prompt for AI tools (Visual Brief) | Yes | No | No | No | No |
| Clipboard history | Yes | No | No | No | No |
A long language list means the app can recognize those languages. It does not mean it is equally good in all of them.
Wispr Flow's own research page sorts its languages into two groups, and Spanish is in the top one: seven languages it says are "trained and tuned to match English-level performance". We would rather tell you that than pretend otherwise. What separates Lipo for Spanish is the rows above this paragraph, not the recognition.
"Not sure" in the table means the company gives a total but does not say in public whether that language is one of them. On totals, Wispr Flow and Willow Voice both say 100+, Aqua Voice publishes a full list of 49, superwhisper depends on the model you choose, and Lipo lists 50+.
Nobody publishes per-language accuracy figures, ourselves included. So speak one real sentence in Spanish, with a person's name and one English word in it, and read what comes back. Ten minutes of that tells you more than any comparison table, including this one. Lipo is built so Spanish gets the same accuracy work as English, rather than a long list where only a few languages work well.
None of the four recognize a language change inside one sentence, so they treat a Spanglish sentence as one language. You cannot predict which words come out right.
Screenshots and Visual Brief, in Spanish
While you are recording, the small floating window (Lipo calls it the pill) has a screenshot button. Click it, capture the screen, and keep speaking. When you release the hotkey, Lipo pastes the text and attaches the screenshot to the same message. So "Mirá este error" arrives with the error in it. The screenshots docs have the details.
Visual Brief goes further. AI tools such as Claude, ChatGPT and Cursor read only text. Visual Brief lets you record your screen while you describe a problem in Spanish. Start it from the Lipo menu bar icon and record your screen or one window for up to 5 minutes. You can say "cuando hago clic acá, la página se recarga pero los datos no aparecen". Lipo transcribes what you said, analyzes the recording, writes a structured prompt in your output language, and pastes it into the AI tool. It needs the Screen Recording permission, and recordings are deleted from your computer after 7 days. Details are in the Visual Brief docs.
What about Apple dictation and the free options?
Apple dictation on macOS 15 offers Spanish for Mexico, Spain, Chile, Colombia and the United States. It runs on-device, which means on your computer, without sending audio to a server. It does not add ¿, ¡ or any other punctuation unless you say the punctuation. It does not remove "este" or false starts. It listens for one language at a time, so it cannot handle English words inside a Spanish sentence. It does not translate.
Tips for better Spanish voice dictation
Speak full sentences. The cleanup step reads the whole sentence for context, and that is how Lipo knows whether "que" needs an accent.
Do not announce punctuation. Say the question with question intonation, and Lipo writes both the ¿ and the ?.
If you correct yourself ("el lunes, no, el martes"), Lipo keeps the correction and removes the mistake.
Choose Spanish as your language instead of auto-detect, especially if you code-switch (change language inside one sentence).
Use the built-in microphone or a wired headset. Wireless earbuds compress the audio, and a soft "s" is the first thing that gets lost.
Frequently asked questions
Can I voice type in Spanish on a Mac?
Yes. Apple's built-in dictation supports Spanish. Apps like Lipo add automatic accents, ¿ and ¡, filler removal, register control and translation.
Does Apple dictation support Spanish?
Yes, with regional settings for Mexico, Spain, Chile, Colombia, the US and others. It inserts commas, periods and question marks, but it does not remove filler words, and it listens for one language at a time.
Does Lipo add accent marks and ñ correctly?
Yes. Lipo writes accents (está, sí, qué, también) and ñ by default, based on the meaning of the whole sentence.
Does it add the inverted question mark?
Yes. Say a question with question intonation, and Lipo writes ¿ at the start and ? at the end.
Can I choose tú or usted?
Casual mode keeps whatever you spoke, including vos. Formal mode rewrites the text toward usted and professional phrasing. You can pin a mode to an app.
Does it work with Mexican, Argentine and Caribbean Spanish?
Yes. Lipo recognizes standard Spanish and regional accents. It keeps Rioplatense voseo instead of correcting it. Heavy dialect words, especially in fast Caribbean speech, may be written in the standard form.
Can I mix Spanish and English (Spanglish)?
Yes. Lipo recognizes both languages in one sentence and writes each word in its own language. "Tengo un meeting a las tres" comes out as spoken.
Can I speak Spanish and get English text, or the reverse?
Both. Set "Lipo pastes" to English or Spanish in the Translation tab. Lipo transcribes, cleans up, translates, and then pastes. Translation has a monthly word limit on the smaller plan; see pricing.
Does it work in WhatsApp, Gmail and Outlook?
Yes. Lipo pastes into any field with a cursor, including WhatsApp Desktop, Gmail in the browser and Outlook.
How much does it cost?
Plans and prices are on the pricing page. There is a free trial.
Keep reading
From the docs: Dictation modes · Your Dictionary