actions-marketplace-validations/Ace-Step Audio Generation

Generate audio using Ace-Step 1.5 via acestep.cpp — pre-bundled models, no wait

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
captionText description for music generationnochiptune
lyricsLyrics (leave empty for LLM auto-generation)no""
durationDuration of the generated audio in secondsno20
seedRandom seed for reproducible generation (optional)no""
inference_stepsNumber of DiT inference stepsno8
shiftFlow matching shift parameterno3
vocal_languageVocal language code (en, fr, es, …)noen
output_pathOutput path for the generated MP3 file (relative to workspace or absolute)nooutput.mp3
understandLocal file path or URL (http/https) to an MP3 or WAV audio file to analyze with ace-understand (activates understand mode — skips audio generation)no""
namedescription
audio_filePath to the generated MP3 audio file
generation_timeTime taken to generate the audio in seconds
understand_resultJSON output from ace-understand containing caption, lyrics, bpm, key, duration, and language analysis of the provided audio