What it can do

Generate Music: Create an AI music generation task on Lacuna. Returns immediately with a `pending` task; poll `get_generation` to retrieve the finished tracks and their audio URLs.

Get Generation: Retrieve the current state of a music generation task by id. Status is `pending`, `ready`, or `failed`; audio URLs appear on `ready`.

List Models: List the music models available through the API, with their credit cost per task, tracks produced per task, and language coverage.

Generate original music from a text description — background beds and soundtrack loops for video, podcast, game and ad workflows, and full vocal songs when you supply lyrics. Every finished task returns hosted MP3 URLs, so an agent can hand the audio straight to the next step.

Tools

generate_music — queue a generation and return the task id immediately
get_generation — read a task's status and, once ready, its audio URLs (free, no credits)
list_models — available models with their credit cost and takes per request

Generation takes a few minutes, so generate_music returns a pending task rather than blocking. Poll get_generation, or subscribe to the job.completed webhook.

Models

Aether — two takes per request, widest style range, accepts vocal register and negative tags
Echo — one take with a complete song structure of up to three minutes

Getting started

Create an API key at lacuna.fm/profile/api. The Music API is available on the Pro plan and above — see plans and credits. Full reference at lacuna.fm/docs/api.

Credits are deducted when a task is queued and refunded automatically if the generation fails.

Lacuna Music

What it can do

What data it sees

Do you need an account

generate_music	Create an AI music generation task on Lacuna. Returns immediately with a `pending` task; poll `get_generation` to retrieve the finished tracks and their audio URLs.
get_generation	Retrieve the current state of a music generation task by id. Status is `pending`, `ready`, or `failed`; audio URLs appear on `ready`.
list_models	List the music models available through the API, with their credit cost per task, tracks produced per task, and language coverage.