Project AURIONAI Use-Cases Research & Innovation
music and audio

Lyria 3

Lyria 3 music model.

Google DeepMindGoogle DeepMindUK / USALyriaFamily
Google DeepMind
Levelmodel
Classmusic and audio
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

independent
Artificial Analysis Music Arena v1.1generative media
Lyria 3 Prosecondary capture of AA post; tied 3-6independent
1,078
8001,0001,200

Score in Elo; the axis starts at 800, as Elo has no zero. Higher is better.

rank 3, AA Music Arena v1.1, InstrumentalOct 2026 alphasignal.ai, digg.com
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

successor
Lyria 2 to Lyria 3: successor, medium confidenceLyria 3 to Lyria 3.5: successor, medium confidenceLyria to Lyria 2: successor, medium confidenceLyriaLyriaGoogle DeepMindLyria 2Lyria 2Google DeepMindLyria 3Lyria 3Google DeepMindLyria 3.5Lyria 3.5Google DeepMind
Google DeepMindLyria 2 is the parent (successor)medium confidencenotes
Google DeepMindLyria 3.5 is a child (successor)medium confidencenotes
Google DeepMindLyria 3 Pro belongs to this modelmusic and audio
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Text-to-music and song generationproduced by

Identity

Developer
Google DeepMind
Family
Lyria
Released
– sources
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
audio
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. Lyria 3.5 , Google DeepMind deepmind.google https://deepmind.google/models/lyria/

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Lyria 3", https://aurion.semai.id/models/google-deepmind-lyria-3/, records of October 2026.