Conversational AI client

ElevenLabs provides customized, conversational voice agents, that can be easily integrated into your Voxipmlant applications via the WebSocket protocol. It offers a custom TTS and ASR modules, several LLMs, such as Google Gemini, Claude, OpenAI and more, and a turn talking model, which can scale to thousands of calls per day.

In this article, you will learn how to integrate ElevenLabs realtime client into your application.

1. Require the Modules.ElevenLabs module in your VoxEngine scenario.
2. Create an ElevenLabs.ConversationalAIClient instance and provide your parameters.
3. Send media between a Call and ElevenLabs.ConversationalAIClient via the *.sendMedia or VoxEngine.sendMediaBetween methods.
4. Listen to the ElevenLabs.ConversationalAIClient events and implement you application business logic.

Here is the complete scenario example for your reference:

If you want to use the ElevenLabs.conversationInitiationClientData method, you should allow the override functionality: