ACE-Step
Songs with vocals, or instrumentals, made on your own GPU by ACE-Step 1.5, from a style and lyrics.
ACE-Step 1.5 (MIT) makes whole songs, with vocals or instrumental, in a few seconds per song on a recent GPU. It sings in 50+ languages, and can repaint part of a track, extend it, or remix it.
Experimental and admin-only.
Setup
Add the service
Add Modules → Services → ACE-Step → Install, then follow the install steps. Voxta installs ACE-Step into its Python and downloads the turbo model with its VAE and text encoder (~6 GB). It writes 320 kbps mp3 with FFmpeg. On Windows the install downloads it, and on Linux it uses the system's (see FFmpeg). Watch the Terminal for progress.
Pick a preset
| Preset | Music model | Planner |
|---|---|---|
| Balanced | Turbo | 0.6B |
| Light | Turbo | None |
| Best | Turbo | 1.7B |
| Detailed | SFT | 1.7B |
A planner or the SFT model is downloaded the first time a preset that uses it loads.
The model starts on the first track, not with the service, so reading its options or opening a chat takes no video memory.
Models
Music Model:
| Model | Notes |
|---|---|
| Turbo (fast) | 8 steps. The default. |
| SFT (detailed) | 50 steps with prompt guidance. Follows the style more closely, with more detail: a few seconds more per track, about the same video memory. |
Song Planner, ACE-Step's language model that plans the melody and arrangement before the track is rendered. Bigger plans better.
| Planner | Video memory, in all |
|---|---|
| None (lightest) | ~5 GB |
| 0.6B (balanced) | ~7 GB |
| 1.7B (best) | ~13 GB |
| 4B (most knowledge) | ~17 GB |
Avoid (a negative style) reaches the planner only, so the playground shows it only when a planner is set.
Settings
Module settings:
| Setting | Notes |
|---|---|
| Models Directory | ACE-Step's checkpoints folder, default Music/ACEStep under your models folder. An existing ACE-Step checkpoints folder can be used as it is. |
| LoRAs Directory | Where presets pick their LoRA from. Default Music/ACEStep-LoRAs. |
Preset settings:
| Setting | Notes |
|---|---|
| Music Model | Turbo or SFT. |
| Song Planner | None, 0.6B, 1.7B or 4B. |
| Let the Planner Rewrite the Style | Off by default. On, the planner rewrites the style from the lyrics: a woman's song can come out a man's, and "no drums" can grow drums. |
| Quality Steps | 1–100. Empty uses the model's own: 8 for turbo, 50 for SFT. More is a little cleaner and slower. |
| Style Adherence (CFG) | SFT only. 1–15, default 7. Higher follows the style more strictly. |
| Writing Instructions | How the language model writes the style and lyrics for ACE-Step. The default comes from ACE-Step's own guide. |
| LoRA | A LoRA from the LoRAs directory, or none. |
| LoRA Strength | 0–1, default 1. |
What it takes
| Length | 10–600 s, default 120 s. Empty lets the model choose. |
| Style | Up to 512 characters. |
| Lyrics | Up to 4096 characters. |
| Vocal language | 50+ languages, or auto. |
| BPM, key, beats per bar | Optional. |
| Takes | Up to 4 per request, made in one pass. |
| Repaint and extend | 3–90 s at a time. A range past the end extends the track. |
| Remix | Makes the take again in a new style and lyrics, at a strength. |
ACE-Step has no stems.
LoRAs
A preset can load a LoRA, a style or voice ACE-Step was fine-tuned on. It is swapped in per track, so presets with different LoRAs share one loaded model.
Put LoRAs in the LoRAs Directory, each as ACE-Step's trainer or Side-Step saves it:
- a PEFT folder (
adapter_config.jsonbeside its weights), or - a LyCORIS LoKr (
lokr_weights.safetensors, or a.safetensorsfile carrying its LoKr config).
Single-file LoRAs converted for ComfyUI do not load.
Writing for ACE-Step
- Style: one genre, at most one influence. Name the texture of the sound and the voice. Give the tempo in words. BPM and key go in their own fields.
- Lyrics: section tags (
[Verse],[Chorus],[Bridge]...) on their own lines, a blank line between sections. A tag can say how to sing it:[Chorus - anthemic].
See ACE-Step's tutorial and musician's guide.
For a version without Python, in one GGUF file, see audio.cpp.