# ElevenLabs Text to Dialogue

> Audio AI Model by ElevenLabs — available on Layer

Generate multi-speaker dialogue audio from structured text with per-speaker voice control.

ElevenLabs Text to Dialogue generates cohesive multi-speaker audio from a structured list of dialogue turns, each with its own voice assignment. Built on the Eleven v3 engine, it produces natural conversational audio with overlapping speech patterns and consistent per-speaker characteristics. Supports stability control, speaker boost, and pronunciation dictionaries for domain-specific content.

## Specifications

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

## Capabilities

- Auto Duration

---

[Try ElevenLabs Text to Dialogue](https://layer.ai/me/session/new?baseModelId=ELEVEN_LABS_TEXT_TO_DIALOGUE) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)