# 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 per character_count |

## Capabilities

- Text to Speech
- Auto Duration

---

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