---
title: "ElevenLabs launches Eleven Realtime speech-to-speech models that start replying in about half a second"
url: https://anawords.com/story/elevenlabs-eleven-realtime-speech-to-speech-mini-max
published: 2026-10-22T19:54:16+05:30
updated: 2026-10-22T19:54:16+05:30
section: Tools & Apps
author: Mayank Sahu
checked: sources checked by AI, approved by editor
version: 1
---

# ElevenLabs launches Eleven Realtime speech-to-speech models that start replying in about half a second

Max and Mini models are available in ElevenAgents and an OpenAI-compatible Realtime API. ElevenLabs reports 98.8% on Big Bench Audio for Max; pricing is per minute plus model usage.

**In short:** ElevenLabs launched Eleven Realtime on 20 October 2026, two speech-to-speech models for voice agents. Eleven Realtime v1 Max starts speaking in about 0.57 seconds and scored 98.8% on the Big Bench Audio test, according to ElevenLabs. Both models work through an OpenAI-compatible Realtime API.

## What launched

ElevenLabs released two speech-to-speech models, which listen and reply in speech directly rather than converting to text in between:[^1][^2]

- **Eleven Realtime v1 Max:** for harder tasks such as customer support, reasoning and multi-step tool calls.[^1][^2]
- **Eleven Realtime v1 Mini:** a lower-cost model for natural conversation; it can tell when a speaker has finished or is just saying “mm-hmm”.[^1][^2]

Both are available now in the ElevenAgents platform and through a Realtime API that follows OpenAI’s Realtime format, so developers using that format can switch by changing the endpoint and model name.[^1][^2]

## Speed and accuracy

The Decoder reports Max’s response time at 0.57 seconds; artrealmai, citing ElevenLabs’ launch post, gives Mini at 0.62 seconds.[^1][^2] ElevenLabs reports Max scored 98.8% on Big Bench Audio, a spoken reasoning test, and says no model on the Artificial Analysis speech-to-speech leaderboard is both faster and more accurate.[^1][^2] These are company-reported results.

Artrealmai also lists 90+ languages, more than 17,000 voices, and tool-use success of 87.1% for Max and 60.3% for Mini.[^2]

## Price and limits

Usage is billed per minute plus model costs; artrealmai lists $0.08 per minute for both models plus language-model usage.[^1][^2] It is a hosted service with no open weights, and the Realtime API supports WebSockets only at launch.[^2]

## What it means

Voice agents usually trade speed for accuracy: fast replies feel natural but can get facts wrong, while careful answers create awkward pauses. ElevenLabs says Max narrows that gap. For businesses building phone support or booking agents, OpenAI-format compatibility lowers switching costs, so testing several providers on your own calls is now easier. In India, where many support calls mix languages, testing on real recordings before rollout will matter more than benchmark scores.

## What to watch

- Independent tests on accented and mixed-language speech.
- Whether WebRTC support arrives for browser and mobile apps.

Related: [Mistral’s Voxtral 3 speech models](/story/mistral-voxtral-3-speech-models-voice-agent-sdk-indic-languages) and [xAI’s Grok Voice 3](/story/xai-grok-voice-3-speech-to-speech-model).

## Fact ledger

- [Reported] ElevenLabs launched Eleven Realtime v1 Max and Mini speech-to-speech models on 20 October 2026. (source 1,2)
- [Reported] Both are available in ElevenAgents and an OpenAI-compatible Realtime API. (source 1,2)
- [Company claim] ElevenLabs reports Max at 0.57 seconds and 98.8% on Big Bench Audio. (source 1,2)
- [Unconfirmed] Pricing is $0.08 per minute plus model usage. (source 2)
- [Unconfirmed] Support for 90+ languages. (source 2)

## Sources

1. [The Decoder: ElevenLabs releases two new speech-to-speech models for real-time AI conversations](https://the-decoder.com/elevenlabs-releases-two-new-speech-to-speech-models-designed-for-real-time-ai-conversations/)
2. [ArtRealm AI: ElevenLabs Eleven Realtime, speech-to-speech voice agents](https://artrealmai.com/article/elevenlabs-eleven-realtime-v1-mini-max-speech-to-speech)