Catalan text to speech, en català.

Text to speech in Catalan for public services, media, education and customer service in Catalonia, Valencia, the Balearic Islands and Andorra.

Try it free → API reference

Listen

Two voices, in Catalan.

Maria
Hola, et truco de la clínica per confirmar la teva cita de demà a les deu i mitja. Encara et va bé, o prefereixes una altra hora?
Oliver
La teva comanda ha sortit aquest matí del nostre magatzem i arribarà dijous. Si has de canviar l'adreça d'entrega, ho puc fer ara mateix.

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

How it works

Text in, Catalan out.

Text to speech turns written Catalan 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.

Catalan is co-official in Catalonia, Valencia and the Balearic Islands and the official language of Andorra. Versa speaks it with every one of its ten voices, and with any voice you clone.

VoicesTen built in, and all of them speak Catalan.
Your voiceA new voice from 3 to 30 seconds of speech, no training.
Price$4.10 per million characters, prepaid, no plan.
Voice agentsNot yet: agents can’t listen in Catalan, though Versa speaks it.

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 què et puc ajudar?","voice":"F4","language":"ca"}' \
  --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 què et puc ajudar?", "voice": "F4", "language": "ca"},
)
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 Catalan 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 Catalan?

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, Catalan included.

Can I clone a voice in Catalan?

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

Can a voice agent hold a conversation in Catalan?

Not yet. Versa speaks Catalan, but our speech recognition doesn’t understand it yet, so a voice agent can’t listen in Catalan. Text to speech in Catalan works today.

Other languages

Spanish · 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