Skip to main content
Version: 2.0.0

Overview

Our WebSocket API offers real-time audio streaming capabilities for text-to-speech (TTS) synthesis. This document provides detailed guidelines on how to establish a WebSocket connection and send requests to synthesize speech effectively.

Features​

  • Real-time audio streaming: Utilizes WebSockets for low-latency, real-time streaming.
  • Flexible output formats: Supports both binary and JSON frame outputs for audio data.
  • Robust error handling: Categorizes errors as recoverable and unrecoverable, ensuring the stability of the WebSocket connection.
note

Websockets API is only available for Business plan users. If you're running into trouble, upgrade to a Business plan or higher on the billing page.