Compare AIUse AILatest in AICommunity
Our VisionTermsPrivacyContact

Lyria 3 Pro is Google's music generation model available through the Gemini API, capable of producing high-quality, 48kHz stereo audio from text prompts or images. It generates full-length songs with complete musical structure — verses, choruses, bridges — including vocals, timed lyrics, and full instrumental arrangements. The model delivers structural coherence across entire compositions, making it suitable for creative music production, soundtrack prototyping, and audio content creation.

Author
GoogleGoogle
Release Date
2026-03-30
Knowledge Cutoff
2026-03-01
License
Proprietary
I/O Format
Context Length
1.0M / 66K
API I/O (1M)
$0.08~$0.08/song
How to Use
Google AI Ultra or above / API Access
Output Speed
113 tok/s
Arena Overall
—
Intelligence Index
—
Coding Index
—
Math Index
—
LiveBench
—
ForecastBench
—
GPQA Diamond
—
HLE
—
MMLU-Pro
—
AIME 2025
—
MATH-500
—
LB Reasoning
—
LB Math
—
LB Data Analysis
—
LiveCodeBench
—
LB Coding
—
LB Agentic
—
TAU2
—
TerminalBench
—
SciCode
—
IFBench
—
AA-LCR
—
Hallucination (HHEM)
—
Factual Consistency (HHEM)
—
LB Language
—
LB Instruction Following
—
Calculate CostView Model Details
1 / 3
Swipe to compare

Lyria 3 Pro is Google's music generation model available through the Gemini API, capable of producing high-quality, 48kHz stereo audio from text prompts or images. It generates full-length songs with complete musical structure — verses, choruses, bridges — including vocals, timed lyrics, and full instrumental arrangements. The model delivers structural coherence across entire compositions, making it suitable for creative music production, soundtrack prototyping, and audio content creation.

Author
GoogleGoogle
Release Date
2026-03-30
Knowledge Cutoff
2026-03-01
License
Proprietary
I/O Format
Context Length
1.0M / 66K
API I/O (1M)
$0.08~$0.08/song
How to Use
Google AI Ultra or above / API Access
Output Speed
113 tok/s
Arena Overall
—
Intelligence Index
—
Coding Index
—
Math Index
—
LiveBench
—
ForecastBench
—
GPQA Diamond
—
HLE
—
MMLU-Pro
—
AIME 2025
—
MATH-500
—
LB Reasoning
—
LB Math
—
LB Data Analysis
—
LiveCodeBench
—
LB Coding
—
LB Agentic
—
TAU2
—
TerminalBench
—
SciCode
—
IFBench
—
AA-LCR
—
Hallucination (HHEM)
—
Factual Consistency (HHEM)
—
LB Language
—
LB Instruction Following
—
Calculate CostView Model Details