lyria-3-pro-preview

ttsproprietary

The Interactions API is now generally available. We recommend using this API for access to all the latest features and models. Home Gemini API Docs Send feedback Lyria 3 Pro Preview Lyria 3 Pro Preview is Google's flagship music generation model. It is optimized for generating full-length songs with complex structural coherence, including multiple verses, choruses, and bridges. It generates high-quality, 48kHz stereo audio from text prompts or image inputs.

Context
131K

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Creator Google AI
Family—
Licenseproprietary
Statusactive
Typetts
Input modalitiestext
Output modalitiesspeech
Open weightNo
Parameters—
Architecture—
Max chars—
Sample rate—
Voices—
Languages—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Generate ContentPOST
Generate text from multimodal inputhttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:generateContent
Stream ContentPOST
Stream text generation responseshttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:streamGenerateContent

API

GET/v1/models/vertex/lyria-3-pro-preview