ElevenLabs
Now in 32 languages

The most realistic voice AI
for every story.

Generate, clone and design voices that sound human. From audiobooks to agents, ElevenLabs gives every product its own way of speaking.

Voice Studio Auto-saved v2.4
Script

The light fell soft on the harbour, and for a moment the city forgot to be a city — it was just water, reflecting itself.

0:14 / 0:22
Voice library
AM
Amelia
British · Narration
RY
Ryker
American · Documentary
NO
Noor
Arabic · Conversational
SH
Shio
Japanese · Audiobook
EL
Elena
Spanish · Warm
The platform

One voice model.
Every surface you ship.

From a single text prompt to studio-grade dialogue, ElevenLabs powers the audio layer of modern products without compromise.

Text to Speech

Convert any prose into emotionally rich voiceover in a single API call. Stream low-latency audio in 32 languages.

Voice Cloning

Clone a voice from 30 seconds of audio. Preserve cadence, accent, and breath patterns across every output.

Conversational Agents

Sub-300ms turn-taking. Handle interruptions, tool calls, and multilingual switching with a single voice identity.

Built for production

From script to release.

Audiobooks

Three hundred pages, six voices, one afternoon.

Multi-character narration with consistent identity across every chapter.

Dubbing

Localize without losing the actor.

Keep the original voice across 32 languages — same warmth, new tongue.

Agents

Phone-grade latency, studio-grade fidelity.

Real-time voice agents that feel less like software and more like presence.

Studio

A single pane for every project.

Browse, design, and version voices alongside the scripts they read.

Pricing

Start free. Scale
when you ship.

Every tier includes commercial rights, 32 languages, and the full voice library.

Starter

For exploring the voice layer.

$0/ month

  • 10,000 characters / month
  • Voice library access
  • API + Studio

Scale

For teams shipping to millions.

$330/ month

  • 2,000,000 characters / month
  • Concurrent streaming
  • Priority rendering
  • Dedicated support

Give every word
a voice.

Design System

The reference.

Tokens, type, and components — the chrome that carries every page.

Color

Brand & Surface
primary
#292524
ink
#0c0a09
canvas
#f5f5f5
canvas-soft
#fafafa
surface-card
#ffffff
surface-strong
#f0efed
Text & Hairlines
body
#4e4e4e
muted
#777169
muted-soft
#a8a29e
hairline-strong
#d6d3d1
hairline
#e7e5e4
Atmospheric Gradient (decoration only)
gradient-mint
#a7e5d3
gradient-peach
#f4c5a8
gradient-lavender
#c8b8e0
gradient-sky
#a8c8e8
gradient-rose
#e8b8c4

Typography

TokenSampleSpec
display-mega The light fell soft. EB Garamond · 64 / 300 · -1.92px
display-xl Give every word a voice. EB Garamond · 48 / 300 · -0.96px
display-lg Built for production EB Garamond · 36 / 300 · -0.36px
title-md Voice Cloning Inter · 20 / 500 · 0
body-md Generate, clone and design voices that sound human. Inter · 16 / 400 · +0.16px
caption-uppercase Now in 32 languages Inter · 12 / 600 · +0.96px
button Try free Inter · 15 / 500 · 0

Radius

none
0px
xs
4px
md
8px
lg
12px
xl · cards
16px
xxl · orb
24px
pill · CTA
9999px

Components

Badges
New Live Beta
Text input
Voice row
AM
Amelia
British · Narration
View DESIGN.md ↗