Portuguese text to speech, em português.

Two voices, in Portuguese.

• Sophie

  Olá, ligamos da clínica para confirmar a sua consulta de amanhã às dez e meia. Ainda é um bom horário, ou prefere outro?

• Lucas

  O seu pedido saiu do nosso armazém esta manhã e deve chegar na quinta-feira. Se precisar de mudar o endereço de entrega, posso fazer isso agora mesmo.

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

Text in, Portuguese out.

Text to speech turns written Portuguese 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.

Every voice speaks Portuguese, so one brand voice can serve your Spanish, Portuguese and English customers alike.

• VoicesTen built in, and all of them speak Portuguese.
• 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 Portuguese, on the web or the phone.

One request.

curl -X POST "https://api.lokutor.com/tts/synthesize" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Olá, como posso ajudar?","voice":"F2","language":"pt"}' \
  --output speech.wav

import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Olá, como posso ajudar?", "voice": "F2", "language": "pt"},
)
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 · Galician · Basque · English · French · Italian · German