Kilo Gateway
30 second duration clips are priced at $0.
Model details
Lyria 3 Clip Preview belongs to Google's Lyria 3 family of music generation models, which is made available through the Gemini API and positions the system as a text- and image-to-audio generator aimed at creative production tasks. Rather than producing long tracks end-to-end, the Clip Preview variant is scoped to short-form output, explicitly intended for short clips, loops, and previews. That orientation makes it well suited to sketching musical ideas, prototyping hooks or beds, and supplying previews that can later be expanded or arranged in a fuller production workflow. Creators approaching it as a rapid ideation tool, rather than a full-length composer, will find the use case closest to what the model is described to do.
In qualitative terms, Lyria 3 Clip Preview targets high-fidelity stereo output at 48kHz, giving creators broadcast-grade audio even at the preview stage, and supports generation directly from descriptive text prompts or from reference images. The model emphasizes structural coherence, handling vocals, timed lyrics, and full instrumental arrangements within the same short generation, so a single clip can carry melody, harmony, and lyrical content without needing separate passes. Within the broader Lyria 3 family, the Clip Preview variant trades extended length for lower-latency, controllable short output, which fits social media, advertising, game audio, and prototyping scenarios where quick iteration matters more than minute-scale compositions.
A provider subscription or plan supersedes token-based pricing for this model.
Kilo Gateway
30 second duration clips are priced at $0.
Kilo Gateway
30 second duration clips are priced at $0.04 per clip. $0 per million input tokens, $0 per million output tokens. 1,048,576 token context window, maximum output of 65,536 tokens.
Kilo Gateway
Compare lyria-3-clip-preview availability, pricing, regions, and deployment types across GCP Vertex AI.