
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.
upbeat indie pop duet, jangly electric guitars, handclaps, warm synth pads, cheerful male and female vocals trading lines, major key, 124 BPM
'Trading lines' asks for two voices that alternate. It is the only reliable way to get call-and-response from a model with no per-voice controls.
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.