Narrators and voice agent builders wanting more emotional reads; the launch discount ends 12 October, after which it's $0.08 per 1,000 characters.

Kenning's take

What it does

Eleven v4 is an ElevenLabs text-to-speech model on a new architecture that reads scripts with more emotion and context, follows audio tags more reliably than v3, and supports Professional Voice Clones again. Eleven v4 Turbo is a low-latency version for real-time agents, with about 100ms median latency. Both cover 90+ languages and are available in the ElevenLabs apps, API and ElevenAgents.

• New architecture with stronger emotional range
• Audio tags for direction and sound effects
• Professional Voice Clone support
• Turbo version with about 100ms latency
• 90+ languages

Who it suits. Creators making narration and dialogue, and developers building voice agents.

Key facts

Category

AI models

Part of

ElevenLabs (ElevenReader and ElevenLabs app)

Made by

ElevenLabs

Released

28 September 2026

How to get it

in the ElevenLabs apps, API and ElevenAgents; Turbo through the API and ElevenAgents

Works on

Web, iOS, Android, API

In the UK

Yes

Free plan

10k credits a month on the Free plan

API price

v4 $0.08 per 1,000 characters, v4 Turbo $0.04 per 1,000 characters; launch discount of 72% (to $0.022 and $0.011) until 12 October 2026

Pricing

Plan	Price	Billed
Starter	$6	month
Creator	$22	month
Pro	$99	month
Scale	$299	month
Business	$990	month

source

FAQ

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.