Skip to content
Reduced motion is on. Play a preview to watch it.
Explore models

Audio

Lyria 3.5

Compose music from a written brief with Lyria 3.5.

  • Text to audio
Create with Lyria 3.5
Preview for Lyria 3.5

Catalog preview for Lyria 3.5. Review your own result before publishing.

A starting point.

Specify genre, instruments, tempo, vocal character and song sections.

Before you publish.

Listen for distorted vocals, abrupt transitions and an ending that fits your edit.

Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.

How credits work · Use the API · Content guidelines

Settings and model questionsCheck the available settings and guidance when preparing your input.

Inputs and settings

Use prompt for the music brief. image_url can provide visual inspiration.

Describe desired length or section timings in the prompt; there is no dedicated duration field.

Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.

Supported inputs

These fields come from the current studio form for google/lyria-3.5. Other modes may require different inputs.

Input types, requirements and limits for google/lyria-3.5
InputTypeRequirementOptions and limits
promptTextRequiredMin. characters: 1 · Max. characters: 5000
image_urlTextOptional—
negative_promptTextOptional—

Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.

Use Lyria 3.5 through the API.

Start with this model ID for the endpoint featured on this page:

google/lyria-3.5

Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.

Check the current model schema for supported inputs and options. Other tasks may use different model IDs.

From quote to result.

Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.

Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.