Skip to main content

Speech-to-speech realtime translation streaming API

Overview​

Palabra’s API enables real-time speech translation using a WebRTC-based or WebSocket-based architecture:

  • WebRTC - best for client applications in browsers, mobile apps, etc. Handled by LiveKit.
  • WebSockets - convenient for serverside integration.

The process begins by creating a secure session and connecting to a Palabra translation server. Once connected, you publish your original audio stream and set your preferred source and target languages.

Palabra then transcribes, translates, and synthesizes your speech into the target language — all in real time. The translated audio is streamed back to you as a track that you can play directly in your application, with minimal latency.

How to start​

Read the following articles to start working with the API:

  1. Streaming Session.
  2. Publishing & Receiving Audio
  3. Translation management API

Quick Start Guide​

You can also check out the Quick Start Guide, which provides step-by-step instructions and code examples for setting up real-time speech translation.

API Clients​

Instead of implementation of the step-by-step low-level API solution from the previos section, you can you Palabra API Clients: