actions-marketplace-validations/Ace-Step Audio Generation
Generate audio using Ace-Step 1.5 via acestep.cpp — pre-bundled models, no wait
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| caption | Text description for music generation | no | chiptune |
| lyrics | Lyrics (leave empty for LLM auto-generation) | no | "" |
| duration | Duration of the generated audio in seconds | no | 20 |
| seed | Random seed for reproducible generation (optional) | no | "" |
| inference_steps | Number of DiT inference steps | no | 8 |
| shift | Flow matching shift parameter | no | 3 |
| vocal_language | Vocal language code (en, fr, es, …) | no | en |
| output_path | Output path for the generated MP3 file (relative to workspace or absolute) | no | output.mp3 |
| understand | Local 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 | "" |
Outputs
| name | description |
|---|---|
| audio_file | Path to the generated MP3 audio file |
| generation_time | Time taken to generate the audio in seconds |
| understand_result | JSON output from ace-understand containing caption, lyrics, bpm, key, duration, and language analysis of the provided audio |