# Lyria 3

> Audio AI Model by Google — available on Layer

Google DeepMind's next-generation music model with enhanced composition and vocal quality.

Lyria 3 from Google DeepMind is the successor to Lyria 2, delivering improved composition quality, richer vocal performance, and broader genre coverage. The model generates high-fidelity stereo music from text prompts with fine-grained control over key, BPM, and stylistic elements. All output is watermarked with SynthID for responsible AI identification.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Google |
| Category | Audio |
| Price | 1.2 / generation |

## Capabilities

- Auto Duration

## Frequently Asked Questions

### How much does Lyria 3 cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 1.2 / generation.

### 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.

---

[Try Lyria 3](https://layer.ai/me/session/new?baseModelId=LYRIA_3) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)