LLM ReferenceLLM Reference

Lyria Models by Google DeepMind

Google DeepMindProprietary
4 models2024–2025

About

Google DeepMind's Lyria family of music and audio generation models. Creates high-quality music tracks, audio clips, and real-time audio from text prompts.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

4 in view

Use when the workload needs audio and multimodal inputs.

2025-01audiomultimodal inputs

Use when the workload needs audio and multimodal inputs.

2025-01audiomultimodal inputs

Use when the workload needs audio.

2024-11audio
Lyria 2Current

Use when the workload needs audio.

2024-06audio

Release Timeline

3 release groups
2025-01
2 current
Lyria 3 Clip
audiomultimodal inputs
Current
Lyria 3 Pro
audiomultimodal inputs
Current
2024-11
1 current
Current
2024-06
1 current
Lyria 2
audio
Current

Specifications(4 models)

Lyria model specifications comparison
ModelReleasedVisionMultimodal
Lyria 3 Pro2025-01YesYes
Lyria 3 Clip2025-01YesYes
Lyria RealTime2024-11NoNo
Lyria 22024-06NoNo

Available From(3 providers)

Frequently Asked Questions

What is Lyria used for?
Lyria is used for audio and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
How does Lyria compare to Gemma 4?
Lyria by Google DeepMind is strongest where you need audio, while Gemma 4 by Google DeepMind is the closest related family to check for vision and multimodal work. Lyria has 4 listed variants, while Gemma 4 reaches up to 256K context, so compare the specs and pricing tables before choosing a production model.
Which Lyria model should I use?
If price is the main constraint, use the pricing table first because Lyria does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Lyria 3 Pro with multimodal inputs.

Models(4)