Scenario
← All Models
Audio

ACE-Step 1.5 Text to Music - Quality

Use it ↗

Create a full song from a style prompt and lyrics. Script it with [Verse]/[Chorus] tags, set BPM and key, sing in 50+ languages, and render tracks from 10 seconds to 10 minutes.

ACE-Step 1.5 Quality is the full-size checkpoint with the 4B planner, tuned for fidelity and prompt adherence. Describe the style in one line: genre, mood, instruments, production. Script the song with structure tags ([Verse], [Chorus], [Bridge - whispered]), backing vocals in (parentheses), UPPERCASE for belted lines, or [Instrumental] for vocal-free tracks. BPM, key, and duration are dedicated controls. Vocals in 50+ languages, tracks up to 10 minutes, lossless WAV originals. For drafts at half the cost, use ACE-Step 1.5 Text to Music Turbo.

More models from Academia