ACE-Step/acestep-v15-xl-sft
ACE-Step v1.5 is a powerful open-source music foundation model that turns a text prompt into a complete song — vocals, lyrics, and instrumentation — at quality that rivals commercial tools. We run the high-quality XL checkpoint with its planning step ("thinking") on by default, so generations favor musical structure and coherence over raw speed.
Try the model with a sample request using the same API shape shown in the reference page.
Lyrics to sing, with optional [verse]/[chorus] structure tags. Empty means the model writes its own lyrics (or, for instrumental requests, none).
Target tempo in beats per minute. Empty means the model chooses. (Default: empty, 30 ≤ bpm ≤ 300)
Let the planning model arrange structure and phrasing before generation. Higher quality but slower; disable it for faster results.
Generate instrumental music with no vocals, regardless of lyrics.
Output audio format. mp3 is small and universally playable; flac and wav are lossless.
Language for auto-written lyrics. Ignored when you supply lyrics or for instrumental tracks.
Length of the track in seconds (30-300). Leave empty to let the model choose. (Default: empty, 30 ≤ duration ≤ 300)
Styles, genres, moods, or instruments to steer the song away from — a compositional nudge, not an audio filter. Ignored when the model writes its own lyrics.. (Default: empty)
Text prompt describing the image
Seed for reproducible output; empty for random. (Default: empty, 0 ≤ seed < 9223372036854776000)
Adjust settings and run the demo to see the model output generated here in real-time.
