Eleven Realtime: Eleven Realtime is a new family of models for ElevenAgents voice agents
By Steven Van ·
Two models, Mini and Max, bundle the LLM, speech-to-text and text-to-speech settings for ElevenAgents, with an OpenAI Realtime-compatible API.
Eleven Realtime is a new family of models for ElevenLabs ElevenAgents voice agents, rolling out gradually across workspaces. Each model is a complete voice agent configuration: you pick one, and ElevenLabs handles the LLM, Speech to Text and Text to Speech settings behind it.
Two models to choose from
- Eleven Realtime v1 Mini (eleven_realtime_v1_mini) is the default, and the fastest and cheapest.
- Eleven Realtime v1 Max (eleven_realtime_v1_max) reasons before it answers. ElevenLabs recommends it for agents with complex instructions or multi-step tool calls.
An agent's system prompt, voice, tools and knowledge base work the same as before.
Connecting from a browser
Developers who already build on OpenAI's Realtime API do not need to rewrite their client. The events and the WebSocket transport are the same, so the changes are the endpoint and the session configuration. The backend calls the Create realtime client secret endpoint to get a short-lived secret, and the browser uses it to connect directly.
