Audio
Lyria3
Lyria 3 is most recent music model from Google
- Text to audio
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Lyria3. Review your own result before publishing.
A starting point.
Describe a musical idea with a genre, instruments, mood and pace. This endpoint generates audio; its catalog artwork is an illustration, not an audio sample or a quality measurement.
Try a prompt like this
A calm instrumental piece with acoustic guitar, gentle percussion and a warm bass line. Keep the arrangement sparse enough to sit behind spoken narration.
A suggested starting prompt, not the exact prompt behind the sample. Results vary with the input and settings.
Before you publish.
Listen through the entire result, including any vocals. Check transitions and the ending before placing it under a video; review the applicable usage terms for your project.
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.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Start with a prompt describing the arrangement you want. Do not send a speech script expecting a text-to-speech reading.
Check the current schema and quote before submitting. Save your prompt with the result; changing the musical brief can produce a different arrangement.
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 lyria3. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 · Max. characters: 5000 |
image_url | Text | Optional | — |
negative_prompt | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Lyria3 through the API.
Start with this model ID for the endpoint featured on this page:
lyria3
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.