
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 3 lines. Neither model returns per-line timings and there is no forced aligner here, so the highlight follows the playhead approximately.
afrobeats, syncopated log drum and shaker groove, bright plucked guitar riff, warm sub bass, smooth melodic male vocal, major key, 104 BPM
Three short lines, all hook. Twenty seconds has room for a chorus and nothing else; a verse written at the density of a real single gets swallowed or rushed.
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.