Lyria 3

Lyria is a music generation model from Google. This page documents the capabilities and features of Lyria 3.

3 Pro Preview

Model ID	`lyria-3-pro-preview`
Supported inputs & outputs	Inputs: Text, Image Outputs: Audio
Capabilities	Supported Text to music Preview feature Image to music Preview feature Full song generation Preview feature Vocal generation Preview feature Instrumental mode Preview feature Lyrics generation Preview feature User-provided lyrics Preview feature Duration controls Preview feature BPM controls Preview feature Intensity controls Preview feature Audio watermarking Preview feature Input filtering Preview feature Output filtering - recitation Preview feature Output filtering - vocal likeness Preview feature Prompt rewriter Preview feature Not supported Negative prompting Preview feature
Technical specifications
Technical specifications	Audio	Maximum audio clip length: 184 seconds Maximum number of clips per prompt: 1 Supported sample rates: 44.1 kHz Supported bitrate: 192 kbps Supported languages: English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese Supported MIME types: `audio/mp3`
Versions	`lyria-3-clip-preview` Launch stage: Preview Release date: 2026-03-25
Quotas	Regional online prediction requests per minute per base model: 10

3 Clip Preview

Model ID	`lyria-3-clip-preview`
Supported inputs & outputs	Inputs: Text, Image Outputs: Audio
Capabilities	Supported Text to music Preview feature Image to music Preview feature 30s clip generation Preview feature Vocal generation Preview feature Instrumental mode Preview feature Lyrics generation Preview feature User-provided lyrics Preview feature BPM controls Preview feature Intensity controls Preview feature Audio watermarking Preview feature Input filtering Preview feature Output filtering - recitation Preview feature Output filtering - vocal likeness Preview feature Prompt rewriter Preview feature Not supported Negative prompting Preview feature Duration controls
Technical specifications
Technical specifications	Audio	Maximum audio clip length: 30 seconds Maximum number of clips per prompt: 1 Supported sample rates: 44.1 kHz Supported bitrate: 192 kbps Supported languages: English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese Supported MIME types: `audio/mp3`
Versions	`lyria-3-clip-preview` Launch stage: Preview Release date: 2026-03-25
Quotas	Regional online prediction requests per minute per base model: 10

For Lyria pricing information, see the Lyria section of the Cost of building and deploying AI models in Vertex AI page.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-04-03 UTC.