# xAI TTS V1

> Audio AI Model by xAI — available on Layer

xAI's text-to-speech model with speech tags for expressive delivery in 20+ languages.

xAI TTS V1 from xAI generates natural speech from text with support for inline speech tags like `[laugh]`, `[pause]`, `[sigh]` and wrapping tags like `<whisper>text</whisper>` and `<slow>text</slow>` for expressive delivery control. Supporting 20+ languages with five distinct voice options (eve, ara, rex, sal, leo), it handles up to 15,000 characters per request. Multiple output formats including MP3, WAV, and PCM at configurable sample rates.

## Specifications

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

## Capabilities

- Text to Speech
- Auto Duration

## Frequently Asked Questions

### How much does xAI TTS V1 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 xAI TTS V1 have?

xAI TTS V1 has an Artificial Analysis Arena Elo of 1152, which places it #8 of the 9 scored audio models on Layer. ElevenLabs TTS V4 Turbo leads that ranking with an Elo of 1336.

---

[Try xAI TTS V1](https://layer.ai/me/session/new?baseModelId=XAI_TTS_V1) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)