Spanish text to speech, en español.

Natural Spanish speech for support lines, appointment reminders, narration and voice agents. Built in Madrid, by a team that speaks it.

Try it free → API reference

Listen

Two voices, in Spanish.

Sophie
Hola, te llamo de la clínica para confirmar tu cita de mañana a las diez y media. ¿Te sigue viniendo bien, o prefieres otra hora?
Noah
Tu pedido salió esta mañana de nuestro almacén y llegará el jueves. Si necesitas cambiar la dirección de entrega, puedo hacerlo ahora mismo.

Versa 2.0’s output for exactly the text shown, through the public API, unedited.

How it works

Text in, Spanish out.

Text to speech turns written Spanish into spoken audio. Ours is Versa, a speech model we train ourselves: it generates each chunk of sound in parallel instead of one token at a time, so the first audio arrives in about 65 ms and the rest streams behind it.

Spanish is our home market, and Spanish phone numbers are on the price list, so an agent can answer calls on a number in Spain.

VoicesTen built in, and all of them speak Spanish.
Your voiceA new voice from 3 to 30 seconds of speech, no training.
Price$4.10 per million characters, prepaid, no plan.
Voice agentsAgents listen and answer in Spanish, on the web or the phone.

The API

One request.

terminal

curl -X POST "https://api.lokutor.com/tts/synthesize" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hola, ¿en qué puedo ayudarte?","voice":"F2","language":"es"}' \
  --output speech.wav

speak.py

import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Hola, ¿en qué puedo ayudarte?", "voice": "F2", "language": "es"},
)
open("speech.wav", "wb").write(r.content)

Returns a WAV file. For streaming, use the WebSocket API or the JavaScript and Python SDKs.

FAQ

Common questions.

How much does Spanish text to speech cost?

$4.10 per million characters, the same in every language, billed per character from a prepaid balance. New accounts get $5 of credit with no card, about 1.2 million characters.

Which voices speak Spanish?

All ten. Versa is zero-shot, so a voice is a timbre rather than a language: every voice speaks every one of our nine languages, Spanish included.

Can I clone a voice in Spanish?

Yes. Record or upload 3 to 30 seconds of speech in the dashboard and the new voice speaks Spanish and the other eight languages. Only clone a voice you own or have permission to use.

Can a voice agent hold a conversation in Spanish?

Yes. A Lokutor voice agent listens and answers in Spanish, on the web or on the phone, for about 5¢ a minute with the language model included.

Other languages

Catalan · Galician · Basque · English · Portuguese · French · Italian · German

Hear your own text.

$5 of credit to start, no card. Type it in the speech studio and press play.

Start free → Talk to us