---
type: "raw_signal"
id: "introducing-eleven-realtime-a-simpler-way-to-build-b243c1"
slug: "introducing-eleven-realtime-a-simpler-way-to-build-b243c1"
title: "Introducing Eleven Realtime: a simpler way to build natural voice agents"
description: "ElevenLabs has launched Eleven Realtime v1 Mini and v1 Max, speech-to-speech models positioned for different voice-agent workloads."
retrieval_nugget: "ElevenLabs has launched Eleven Realtime v1 Mini and v1 Max, speech-to-speech models positioned for different voice-agent workloads."
observed_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "observed_at"
why_it_matters: "Source: https://elevenlabs.io/blog/realtime"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "elevenlabs.io"
topics: []
entities: ["ElevenLabs","Eleven Realtime v1 Mini","Eleven Realtime v1 Max","Artificial Analysis","OpenAI Realtime API"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "ElevenLabs has now released separate Realtime v1 Mini and Max speech-to-speech models for low-cost conversation and complex workflows, distinct from the earlier v4 and v4 Turbo launch."
prior_refs: ["memory:1cb3f917-69c1-8669-ae75-d606319beac9","memory:c0b40706-a4cc-833c-aa59-ab7483a9e978"]
source_url: "https://elevenlabs.io/blog/realtime"
source_urls: ["https://elevenlabs.io/blog/realtime"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:introducing-eleven-realtime-a-simpler-way-to-build-b243c1"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/introducing-eleven-realtime-a-simpler-way-to-build-b243c1/","markdown":"https://newruntime.com/signals/introducing-eleven-realtime-a-simpler-way-to-build-b243c1.md","json":"https://newruntime.com/signals/introducing-eleven-realtime-a-simpler-way-to-build-b243c1.json"}
---

# Introducing Eleven Realtime: a simpler way to build natural voice agents

## Retrieval answer

ElevenLabs has launched Eleven Realtime v1 Mini and v1 Max, speech-to-speech models positioned for different voice-agent workloads.

ElevenLabs has launched Eleven Realtime v1 Mini and v1 Max, speech-to-speech models positioned for different voice-agent workloads. The company says both support more than 90 languages and can use its library of over 17,000 voices. They are available through ElevenAgents and a Realtime API compatible with the OpenAI Realtime specification; the API connects over WebSocket.

ElevenLabs reports that Artificial Analysis evaluated the models on Big Bench Audio, Full-Duplex-Bench, and Speech Agent Arena. On Big Bench Audio, v1 Max scored 98.8% and Mini 75.9%; average time to first audio was 0.57 seconds for Max and 0.62 seconds for Mini. On tool-use tasks, Max completed 87.1% and Mini 60.3%. These are the company’s reported results from the evaluation, not evidence of performance in every deployment.

Source: https://elevenlabs.io/blog/realtime

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)