
A sung track: the prompt below set the arrangement and the script is what the model was given to sing. Copy the prompt, change a word and render your own.
What ACE-Step was given to sing, verbatim. Press play and it follows along.
Line positions are the rendered length divided by 2 lines. Neither model returns per-line timings and there is no forced aligner here, so the highlight follows the playhead approximately.
contemporary R&B slow jam, sparse finger-snap percussion, deep warm bass, muted Rhodes chords, breathy layered female vocal with runs, minor key, 74 BPM
'With runs' is the phrase that gets melisma from the model. Without it ACE-Step sings the line straight and the take sounds like pop.
Listed as Apache 2.0 in the catalogue and flagged unverified there. Read the model card before shipping output commercially. Soundbox itself is MIT and imposes no terms of its own on what you generate.