Lyria 3
Lyria 3 is a music generation model from Google that produces audio from text prompts with a 5000 token context window.
Text-to-music generation from Google DeepMind
Lyria 3 is a music generation model developed by Google DeepMind, available through Google Cloud's Vertex AI platform. It accepts text-based prompts and generates musical audio output, operating with a context window of 5000 tokens. The model is identified internally as lyria-3-clip-preview, indicating it is in a preview stage of availability.
Lyria 3 is designed for use cases that require programmatic music creation from natural language descriptions, such as generating background music, soundscapes, or musical clips for creative and production workflows. It is accessible through Vertex AI's generative AI infrastructure, making it suitable for developers building applications that need music generation capabilities without managing audio synthesis pipelines directly. The model falls under Google's first-party model offerings on the platform.
What Lyria 3 supports
Text-to-Music Generation
Generates musical audio clips from natural language text prompts. Accepts descriptive text input and returns audio output suitable for creative and production use cases.
Prompt-Based Control
Allows users to specify genre, mood, instrumentation, and style through text descriptions. This gives developers direct control over musical output without audio engineering expertise.
5000 Token Context
Supports a context window of up to 5000 tokens, allowing for detailed and nuanced text prompts describing the desired musical output.
Vertex AI Integration
Deployed natively on Google Cloud's Vertex AI platform, enabling access through standard Google Cloud APIs and authentication without third-party infrastructure.
Latest Model Release
Tagged as the latest Lyria model in Google's music generation lineup, reflecting the most recent iteration available through the Vertex AI generative AI catalog.
Ready to build with Lyria 3?
Get Started FreeCommon questions about Lyria 3
What is the context window for Lyria 3?
Lyria 3 supports a context window of 5000 tokens, which governs the length and detail of text prompts that can be submitted to the model.
What does Lyria 3 take as input?
Lyria 3 accepts text-based prompts describing the desired music. The model then generates audio output based on those descriptions.
Is Lyria 3 generally available or still in preview?
Based on the model's full name, lyria-3-clip-preview, the model is currently in a preview stage of availability on Vertex AI.
What is the pricing for Lyria 3?
Pricing information for Lyria 3 is not published in the available metadata. You should consult Google Cloud's Vertex AI pricing documentation for current rates.
Who publishes Lyria 3 and where is it hosted?
Lyria 3 is published by Google and is hosted as a first-party model on Google Cloud's Vertex AI generative AI platform.
Explore similar models
GoogleLyria 3 Pro
Lyria 3 Pro is a music generation model from Google designed to produce full audio tracks from text prompts.
GoogleGemini 3.7 Flash
Gemini 3.7 Flash is a text generation model from Google with a 1,048,576-token context window and configurable thinking levels.
GoogleGemini Omni Flash
Gemini Omni Flash is a video generation model from Google that supports image and video inputs with multimodal editing capabilities.
MiniMaxMiniMax Music 3.0
MiniMax Music 3.0 is a music generation model from MiniMax that creates songs from lyrics or as instrumentals at $0.15 per song.
ElevenLabsElevenLabs Music
ElevenLabs Music is a music generation model that produces audio tracks from text prompts with a 2000 token context window.
ByteDanceSeedance 2.5 Turbo
Seedance 2.5 Turbo is a video generation model from ByteDance that supports text-to-video, image-to-video, and video editing modes.
Start building with Lyria 3
No API keys required. Create AI-powered workflows with Lyria 3 in minutes — free.