Skip to main content
Everything our SDKs do goes over the public HTTP + WebSocket API — you can use it directly from any language. This page covers the connection basics; each endpoint’s full message reference lives on its own page.

​
Base URL

​
Authentication

Include your API key in requests:
See Authentication for key management.

​
Sending text safely

Encode JSON as UTF-8. For predictable normalization of short or ambiguous text, set language explicitly. Unicode NFC normalization can also make equivalent composed and decomposed input consistent before it reaches the API.

​
Tooling for WebSockets

The streaming endpoints are plain JSON-over-WebSocket. For interactive exploration use wscat (npm install -g wscat) or websocat:
Every streaming endpoint page includes complete raw-WebSocket examples in Python and JavaScript alongside the wire-format tables.

​
Endpoints

Generate Speech

REST one-shot — also the canonical request parameter reference

Stream Speech

One request, audio chunks streamed over a WebSocket

Stream Input

Token-by-token text input, turn-based sessions for LLM agents

Multi-Context

Up to 20 independent audio streams over one connection

Audio Formats

PCM, G.711 telephony codecs, chunk fields, AI-generated audio marking

Voices

List, inspect, and clone voices

Models

Inspect accepted model IDs and per-model input limits

Dictionaries

Manage project pronunciation dictionaries and entries