Documentation

Vocalia's voice API.

REST and WebSocket to synthesize voice in real time. Regional accents, low-latency streaming and formats designed for telephony and voice agents.

Get access →

Quickstart

Your first voice synthesis.

Authenticate with your API key, choose a voice and receive audio over streaming. That simple.

curl

# Synthesize voice (REST)
curl -X POST https://api.vocalia.ai/v1/tts \
  -H "Authorization: Bearer $VOCALIA_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_id": "ar_valentina",
    "text": "Hola, gracias por comunicarte.",
    "format": "mp3"
  }' --output salida.mp3

python

import requests

r = requests.post(
    "https://api.vocalia.ai/v1/tts",
    headers={"Authorization": f"Bearer {KEY}"},
    json={
        "voice_id": "ar_valentina",
        "text": "Hola, ¿en qué te ayudo?",
        "format": "pcm16",
    },
)

Reference

Main endpoints.

Method	Endpoint	Description
POST	/v1/tts	Synthesizes voice from text and returns the audio.
WS	/v1/tts/stream	Real-time audio streaming over WebSocket.
GET	/v1/voices	Lists available voices by language and region.
GET	/v1/usage	Current-period usage for your account.

Formats

Audio

pcm16, mulaw_8000 (telephony), mp3. Choose to fit your pipeline.

SDKs

Python · JS

Official libraries to integrate in minutes, plus plain REST.

Auth

API key

Bearer token per project. Generate and revoke keys from your dashboard.

Let's work together

Ready to integrate voice?

Request API access and we'll give you the credentials to start. If you have technical questions, write to us and we'll help with the integration.

Get access →See products