Generate music and sound effects with EmpirioLabs AI from a text description, with optional lyrics on models that sing, wait for the result, and save the audio file. Use when the user asks to compose a song, a backing track, a jingle, or a film score, to create a sound effect or ambience, or to check on an audio job that is still running. Runs a bundled Python script that picks a model from the live catalog (or the one you name) and saves the file to the path you choose.