# Qwen 3 TTS

> Audio AI Model by Qwen 3 Tts — available on Layer

Multilingual TTS with zero-shot voice cloning and prompt-based voice design.

Qwen 3 TTS (1.7B) is a multilingual text-to-speech model with zero-shot voice cloning. Clone a voice from a single audio sample, or design a new voice from a text prompt; the resulting speaker embedding can then narrate any text. Supports English, Chinese, Spanish, French, German, Italian, Japanese, Korean, Portuguese and Russian.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Qwen 3 Tts |
| Category | Audio |
| Price | 0.03 / character count |

## Capabilities

- Text to Speech
- Auto Duration

## Frequently Asked Questions

### How much does Qwen 3 TTS 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 Qwen 3 TTS have?

Qwen 3 TTS has an Artificial Analysis Arena Elo of 1266, which places it #4 of the 9 scored audio models on Layer. ElevenLabs TTS V4 Turbo leads that ranking with an Elo of 1336.

---

[Try Qwen 3 TTS](https://layer.ai/me/session/new?baseModelId=QWEN_3_TTS) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)