ElevenLabs Realtime

ElevenLabs Realtime is a family of speech-to-speech models for building voice agents. Speech recognition, turn-taking, the LLM, and the voice are tuned end-to-end. V1 Mini is designed for natural conversation (620ms to first audio) and V1 Max for complex tasks (570ms to first audio). It supports 90+ languages and can be used in ElevenAgents or via an OpenAI-compatible Realtime API by changing only the endpoint and model name.