Galician text to speech, en galego.

Two voices, in Galician.

• Sophie

  Ola, chámote da clínica para confirmar a túa cita de mañá ás dez e media. Aínda che vén ben, ou prefires outra hora?

• Noah

  O teu pedido saíu esta mañá do noso almacén e chegará o xoves. Se precisas cambiar o enderezo de entrega, podo facelo agora mesmo.

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

Text in, Galician out.

Text to speech turns written Galician 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.

Galician is co-official in Galicia, where public bodies serve people in it. Versa speaks it with every one of its ten voices, and with any voice you clone.

• VoicesTen built in, and all of them speak Galician.
• 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 Galician, though Versa speaks it.

One request.

curl -X POST "https://api.lokutor.com/tts/synthesize" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Ola, en que te podo axudar?","voice":"F2","language":"gl"}' \
  --output speech.wav

import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Ola, en que te podo axudar?", "voice": "F2", "language": "gl"},
)
open("speech.wav", "wb").write(r.content)

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

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