# Lyria 3.5

> Audio AI Model by Google — available on Layer

Google DeepMind's latest music model, writing full-length songs with vocals from one prompt.

Lyria 3.5 from Google DeepMind is the latest Lyria music model, generating full-length songs of up to a few minutes with vocals, lyrics, and multi-section structure from a single text prompt. Control genre, mood, instrumentation, tempo, and song length in the prompt, including timestamped section markers for intros, verses, and choruses, or attach an image to set the mood. Lyrics can be sung in English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese. Output is MP3, watermarked with SynthID.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Google |
| Category | Audio |
| Price | 3 / generation |

## Capabilities

- Auto Duration

## Frequently Asked Questions

### How much does Lyria 3.5 cost? Is it free?

Generating assets on Layer requires using Creative Units. This model's current price is 3 / 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 3.5](https://layer.ai/me/session/new?baseModelId=LYRIA_3_5) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)