Lyria 3.5
/v1/runLyria 3.5 is Google's flagship music generation model for full-length songs up to a few minutes, with verses, choruses, bridges, expressive vocals, timed lyrics, and rich instrumental arrangements. It generates high-quality 44.1kHz stereo audio from a text prompt, optionally guided by an image.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to google/lyria-3.5.
Default: google/lyria-3.5
The text prompt describing the music you want to generate. Include genre, mood, instrumentation, tempo, vocals, and structure. Use duration hints (e.g. 'a 2-minute track') or section markers like '[0:00-0:30] Intro: ...' to control length and structure. Supports English, German, Spanish, French, Hindi, Japanese, Korean, and Portuguese.
Optional image used as inspiration; the music will match the mood and theme of the image.
Response Schema
The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.
Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.
Current public run status.
Allowed values: pending, running, completed, failed, timeout
Public SandBase model name used for this run.
Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.
Present only for failed or timeout runs. Contains a public error type and sanitized message.
Stable public error category.
Sanitized error message safe to show to clients.
Usage details when available.
Model capabilities
Capabilities declared by the model registry.
Default: text-to-music
Execution mode declared by the model registry.
Default: async