Lyria 3 Clip Preview.
- Music Generation
- $0.04 per execution
- ~1 min average
Lyria 3 Clip generates 30-second music clips from text or image prompts, returning MP3 audio with lyrics and song structure for fast creative drafts.
What Lyria 3 Clip Preview is good at.
Best forWhere it fits
Lyria 3 Clip Preview is useful when this specific operation fits between source preparation and delivery. These scenarios show how it can support different…
Limits and tipsUse clean source material where the request accepts audio or video.
For a generative prompt, describe the desired sound, pacing and arrangement clearly. Change one exposed control at a time when comparing a result.
Related modelView modelminimax music 2.5
Run it on the same input to compare output, speed and price.
Model documentation
About this model
Lyria 3 Clip generates 30-second music clips from text or image prompts, returning MP3 audio with lyrics and song structure for fast creative drafts.
Overview
Lyria 3 Clip Preview Overview
Lyria 3 Clip generates 30-second music clips from text or image prompts, returning MP3 audio with lyrics and song structure for fast creative drafts.
This entry generates a 30-second MP3 music clip, optionally guided by image references.
Lyria 3 Clip Preview from Google is available through each::labs in the gemini family. Required fields are prompt.
image_urls: Optional image URLs to guide the music.
Use the Lyria 3 Clip Preview API when you need this transformation or analysis as a repeatable step in an application or creative pipeline. The sections below distinguish the required material, adjustable controls and checks that matter before delivery.
Capabilities
Capabilities
- This entry generates a 30-second MP3 music clip, optionally guided by image references.
- image_urls: Optional image URLs to guide the music.
- Produces a audio result for the next stage of your workflow.
- Runs the requested operation on the supplied input rather than requiring a manual editing session.
- Can be used as a focused processing step in an each::labs application.
Use cases
Use Cases for Lyria 3 Clip Preview
Lyria 3 Clip Preview is useful when this specific operation fits between source preparation and delivery. These scenarios show how it can support different parts of a working pipeline.
Creators
Draft a short soundtrack idea. Use a representative source or a concise brief, then inspect the result before preparing a larger set of assets.
Design and marketing teams
Explore music for a campaign mood. Compare the result with the intended message, composition and destination. Keep reviewable versions of the source and output.
Developers
Generate a compact audio concept from visual references. Inspect the actual returned value before connecting it to another step, and keep the chosen request settings with the result.
Start with a clear definition of the desired result and use the exposed controls to reach it. Keep any additional generation, editing or application logic in separate steps so that the effect of this operation remains easy to review.
Tips & tricks
Tips and Tricks
Use clean source material where the request accepts audio or video. For a generative prompt, describe the desired sound, pacing and arrangement clearly. Change one exposed control at a time when comparing a result.
Choose a representative source for the first pass. Keep the original material and record the request values so that a successful result can be reproduced as part of your wider editing or processing sequence.
- Example direction: “A restrained instrumental bed with soft piano and warm strings, gentle pacing, no sudden changes.”
- Example direction: “A bright acoustic introduction with a clear melody and a simple, uncluttered arrangement.”
Compare one deliberate adjustment at a time. Inspect the part of the result affected by that change, then check the rest of the asset or response for unwanted side effects before reusing the settings.
Technical spec
Technical Specifications
- Result type: audio.
- Required fields: prompt.
- prompt: string.
- image_urls: array or null; default null.
Values must use the types and accepted options listed in the parameter reference. A displayed default does not remove a required-field requirement. Choose a supported output setting for this entry rather than borrowing a preset from a related model.
Things to be aware of
Things to Be Aware Of
Listen to the full result and inspect any returned structured data separately. Pronunciation, timing, unwanted sounds and transitions can require manual review even when a request completes successfully.
Optional settings are not necessarily interchangeable with those on another entry in the same family. Use the accepted names, types and values shown for this operation.
Check the returned content against the original input and your application requirements. A successful request means the operation completed; your application still needs to verify that the response is suitable for the next step.
Key considerations
Key Considerations
Duration is fixed for the Clip entry; describe style, instrumentation and structure rather than sending an unsupported duration field.
Fixed pricing: $0.04 per 30-second music clip.
Prepare prompt before starting. Optional settings include image_urls. Keep these settings aligned with the intended delivery, especially when a later step expects a particular type or format.
Run a representative request before scaling to a larger collection. Judge the result against the source and the brief, and account for all generated outputs or usage-sensitive options when estimating a batch.
Limitations
Limitations
- prompt: minimum characters: 1; maximum characters: 20000.
- image_urls: maximum items: 10; item string; item format: uri.
Unsupported parameters do not establish additional capabilities. A generated result can differ from the intended brief, so review detail and consistency before publication.
Questions about this model
The short answers. For anything specific to your setup, talk to our team.
Lyria 3 Clip Preview is a Google music generation model for creating short audio clips from a prompt. The documented output is a 30-second MP3, with generated lyrics and song structure returned alongside the audio. It is suited for fast musical sketches, loops, and preview tracks.
Lyria 3 Clip Preview can create short music ideas from text prompts, including instrumental directions, genre references, moods, and lyric or structure guidance. Google also documents multimodal input support, so text and images can guide the composition. On each::labs, the model is best treated as a quick audio draft generator.
The model returns MP3 audio for a 30-second music clip. Google documents the response through the Interactions API steps schema, where audio content appears with generated text for lyrics or structure. That output shape lets Lyria 3 Clip Preview expose both the finished audio file and helpful creative context.