Research noteResearched 22 Oct 2026 · published 22 Oct 2026, 19:44 IST

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

How we checked Eleven Realtime and labelled the company’s performance figures.

Research led by Mayank Sahu

Compiled with AI assistance (Claude by Anthropic)

Read the story →

At a glance

1searches run

3sources read

2sources used

5facts labelled

Mixedevidence strength · 2 of 5 facts (40%)

How we rate evidence: Some facts are confirmed, others rest on one report or on the company’s own claims. We count the share of known facts labelled Confirmed or Reported: 70% or more is Strong, 40–69% Mixed, below 40% Limited.

From sources to story

How many sources we read, how many we used, and how many are official or archived.

Read3Every source we opened

Used2Relied on for the story

Cited2Linked in the story

Official0From the company or a public body

Archived2Saved on the Internet Archive

How sure we are, fact by fact

212

Reported · 2 — Two or more independent, named outlets say it.
Company claim · 1 — Only the company says it. Not checked by anyone else yet.
Unconfirmed · 2 — One report only, shown with its source.

Evidence map

Each row is a fact from the story; each column is a source. A filled dot means that source supports the fact.

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

Question

What we set out to check

Which models launched, how fast and accurate ElevenLabs says they are, and how much they cost.

Findings

What we found

Both sources agree on the two models, 0.57-second latency for Max, the 98.8% Big Bench Audio score and OpenAI-format compatibility.
Only ArtRealm AI gives languages, Mini latency and a per-minute price.

Discrepancies

Numbers that differ

The Decoder says exact rates are on ElevenLabs’ pricing page; ArtRealm AI gives $0.08 per minute. We label the price unconfirmed.

Method

Labels we chose and why

Claim for performance figures.
Unconfirmed for price and languages, from one source.

Open questions

What we could not verify

ElevenLabs’ own launch post and pricing page.

Can you help confirm one of these? Send us a source. When we find an answer, we update this note and the story, with the date.

Next steps

How we could improve this

Our second source is a smaller site. We will cite ElevenLabs’ official post and pricing page directly.

Research timeline

Research22 Oct 2026
Research note published22 Oct 2026, 19:44 IST
Story published22 Oct 2026, 19:54 IST

What we searched

ElevenLabs Eleven Realtime speech-to-speech launch

Every source we read

Source	Used?	Why
The Decoder Archived copy	USED	Models, latency, benchmark, availability.
ArtRealm AI Archived copy	USED	Fuller figures from the launch post, pricing.
ElevenLabs on X	NOT USED	Could not open.

Sources cited in the story

Research notes show our working. They are not peer-reviewed papers. Data: facts as JSON · How we report