# ElevenLabs Realtime

> Realtime voice agent models with 570ms to first audio

Source: https://tools.launchllama.co/products/elevenlabs-realtime
Markdown: https://tools.launchllama.co/products/elevenlabs-realtime.md
Generated: 2026-11-01T14:21:23.827Z

## Facts

- **Name:** ElevenLabs Realtime
- **Tagline:** Realtime voice agent models with 570ms to first audio
- **Short description:** Realtime voice agent models with 570ms to first audio
- **Website:** https://elevenlabs.io/realtime
- **Categories:** Artificial Intelligence
- **Listing type:** product_hunt
- **Upvotes on Launch Llama:** 194
- **Listed since:** 2026-11-01
- **Featured (paid) listing:** no

## Full description

Eleven Realtime is ElevenLabs’ new family of speech-to-speech models for voice agents. Speech recognition, turn-taking, the LLM and the voice are tuned end-to-end. v1 Mini is built for natural conversation, v1 Max for complex tasks, with 620ms and 570ms to first audio. It supports 90+ languages and works in ElevenAgents or through an OpenAI-compatible Realtime API, so you only change the endpoint and model name.

## Notes for agents

- Generated on request from live Launch Llama data, so it is always current.
- Human page: https://tools.launchllama.co/products/elevenlabs-realtime
- Site overview: https://tools.launchllama.co/llms.txt (long form: https://tools.launchllama.co/llms-full.txt)
- Every listing as markdown: https://tools.launchllama.co/catalog.md
- Search the catalog over MCP (https://tools.launchllama.co/mcp) or REST: https://tools.launchllama.co/developers