# ElevenLabs TTS V3

> Audio AI Model by ElevenLabs — available on Layer

Also known as Eleven v3.

ElevenLabs' most expressive TTS model with inline audio tags for emotion and delivery.

Eleven v3 is ElevenLabs' most advanced text-to-speech model, built from the ground up for emotional expressiveness. Voices can sigh, whisper, laugh, and react using inline audio tags like `[whispers]`, `[laughs]`, and `[excited]`. Supporting 70+ languages with multi-speaker dialogue capabilities via the Text to Dialogue API, it is best suited for audiobooks, film, dramatic voiceovers, and any content requiring nuanced vocal performance.

## Specifications

| Property | Value |
|----------|-------|
| Provider | ElevenLabs |
| Category | Audio |
| Price | 0.03 / character count |

## Capabilities

- Text to Speech
- Auto Duration

## Frequently Asked Questions

### How much does ElevenLabs TTS V3 cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 0.03 / character count.

### How does Layer's pricing work?

There are no seat fees, feature gates, or plans on Layer. Instead, our platform uses a consumption based system with Creative Units (CUs) with a flexible monthly subscription. Every generation on Layer (image, video, 3D, or audio) consumes a Creative Unit, and you only pay for what you create.

### What Elo score does ElevenLabs TTS V3 have?

ElevenLabs TTS V3 has an Artificial Analysis Arena Elo of 1184, which places it #7 of the 9 scored audio models on Layer. ElevenLabs TTS V4 Turbo leads that ranking with an Elo of 1336.

---

[Try ElevenLabs TTS V3](https://layer.ai/me/session/new?baseModelId=ELEVEN_LABS_TTS_V3) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)