ace-step

Name: ace-step
Author: prime-skills

31stars9forks

How to install ace-step?

prime-skills/runcomfy-agent-skills/ace-step

$npx -y skills add prime-skills/runcomfy-agent-skills --skill ace-step

Installs into the current project.

Summary

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the runcomfy CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–

Files · 1

View on GitHub

SKILL.md

1	# ACE Step — Pro Pack on RunComfy
2
3	Tag-driven music generation, inpainting, and outpainting with StepFun-AI's ACE Step open-weights model. Four CLI-reachable endpoints, $0.0002–0.0003 per second of audio, up to 4 minutes per call.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [ACE Step base](https://www.runcomfy.com/models/acestep-ai/ace-step/text-to-audio?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [ACE Step 1.5](https://www.runcomfy.com/models/acestep-ai/ace-step-1.5/text-to-audio?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step)
6
7	## Install this skill
8
9	```bash
10	npx skills add agentspace-so/runcomfy-agent-skills --skill ace-step -g
11	```
12
13	## Powered by the RunComfy CLI
14
15	Step 1 — install (one of, see the `runcomfy-cli` skill for details):
16
17	```bash
18	npm i -g @runcomfy/cli # global install
19	npx -y @runcomfy/cli --version # zero-install
20	```
21
22	Step 2 — sign in (or set `RUNCOMFY_TOKEN` env var in CI / containers):
23
24	```bash
25	runcomfy login
26	```
27
28	Step 3 — generate:
29
30	```bash
31	runcomfy run acestep-ai/ace-step/text-to-audio \
32	--input '{"tags": "..."}' \
33	--output-dir ./out
34	```
35
36	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
37
38	---
39
40	## Pick the right endpoint
41
42	Listed newest first.
43
44	ACE Step 1.5 (text-to-audio) — `acestep-ai/ace-step-1.5/text-to-audio`
45	> Latest ACE Step generation. 50+ language vocal support, refined structured-lyric handling, otherwise same shape as base. Slightly higher cost ($0.0003/s vs $0.0002/s).
46	> Pick for: multilingual lyrics, hero-quality vocal tracks, vocal songs that need clean section structure.
47	> Avoid for: cost-sensitive batches where the base model is good enough.
48
49	ACE Step (text-to-audio) — `acestep-ai/ace-step/text-to-audio` (default — cheap & fast)
50	> Original ACE Step. Tag-driven composition, optional lyrics, 5–240 s stereo. $0.0002/s — ~27× cheaper than ElevenLabs Music.
51	> Pick for: high-volume drafts, background music, jingles, game loops, cost-sensitive iteration.
52	> Avoid for: maximally polished commercial vocal hooks — try ACE Step 1.5 or ElevenLabs Music for those.
53
54	ACE Step (audio-inpaint) — `acestep-ai/ace-step/audio-inpaint`
55	> Regenerate a time range inside an existing track (not mask-based; uses `start_time` / `end_time` in seconds, each anchored to track start or end).
56	> Pick for: fix a bad chorus in the middle, swap the bridge, replace a 20 s section without re-rendering the whole song.
57	> Avoid for: edits that aren't time-bounded — those don't fit the schema.
58
59	ACE Step (audio-outpaint) — `acestep-ai/ace-step/audio-outpaint`
60	> Extend an existing track bidirectionally — add intro before, outro after, or both.
61	> Pick for: lengthening a 30 s draft into a 2 min cut, adding a fade-in, building a longer arrangement around an existing hook.
62	> Avoid for: extending a track past 4 min total — chain calls instead.
63
64	---
65
66	## Route 1: ACE Step text-to-audio (default)
67
68	Model: `acestep-ai/ace-step/text-to-audio` (or `acestep-ai/ace-step-1.5/text-to-audio` for the 1.5 variant)
69
70	### Schema (both variants — same shape)
71
72	\| Field \| Type \| Required \| Default \| Notes \|
73	\|---\|---\|---\|---\|---\|
74	\| `tags` \| string \| yes \| — \| Comma-separated genre / mood / instrument tags. Drives composition \|
75	\| `lyrics` \| string \| no \| — \| Vocal content. Use section markers `[Verse]`, `[Chorus]`, `[Bridge]`. Use `[inst]` or `[instrumental]` for no vocals \|
76	\| `duration` \| int \| no \| `60` \| Audio length in seconds. 5–240 (max 4 min per call) \|
77	\| `seed` \| int \| no \| `-1` \| Reproducibility; `-1` randomizes \|
78
79	Pricing: ACE Step $0.0002/s · ACE Step 1.5 $0.0003/s. 60 s ≈ $0.012 / $0.018; 240 s ≈ $0.048 / $0.072.
80
81	### Invoke
82
83	**Tag-dri

People who liked this also viewed

6 picks

Type

ace-step

31stars9forks

View on GitHub

How to install ace-step?

prime-skills/runcomfy-agent-skills/ace-step

$npx -y skills add prime-skills/runcomfy-agent-skills --skill ace-step

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# ACE Step — Pro Pack on RunComfy
2
3	Tag-driven music generation, inpainting, and outpainting with StepFun-AI's ACE Step open-weights model. Four CLI-reachable endpoints, $0.0002–0.0003 per second of audio, up to 4 minutes per call.
4
5	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [ACE Step base](https://www.runcomfy.com/models/acestep-ai/ace-step/text-to-audio?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [ACE Step 1.5](https://www.runcomfy.com/models/acestep-ai/ace-step-1.5/text-to-audio?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=ace-step)
6
7	## Install this skill
8
9	```bash
10	npx skills add agentspace-so/runcomfy-agent-skills --skill ace-step -g
11	```
12
13	## Powered by the RunComfy CLI
14
15	Step 1 — install (one of, see the `runcomfy-cli` skill for details):
16
17	```bash
18	npm i -g @runcomfy/cli # global install
19	npx -y @runcomfy/cli --version # zero-install
20	```
21
22	Step 2 — sign in (or set `RUNCOMFY_TOKEN` env var in CI / containers):
23
24	```bash
25	runcomfy login
26	```
27
28	Step 3 — generate:
29
30	```bash
31	runcomfy run acestep-ai/ace-step/text-to-audio \
32	--input '{"tags": "..."}' \
33	--output-dir ./out
34	```
35
36	CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
37
38	---
39
40	## Pick the right endpoint
41
42	Listed newest first.
43
44	ACE Step 1.5 (text-to-audio) — `acestep-ai/ace-step-1.5/text-to-audio`
45	> Latest ACE Step generation. 50+ language vocal support, refined structured-lyric handling, otherwise same shape as base. Slightly higher cost ($0.0003/s vs $0.0002/s).
46	> Pick for: multilingual lyrics, hero-quality vocal tracks, vocal songs that need clean section structure.
47	> Avoid for: cost-sensitive batches where the base model is good enough.
48
49	ACE Step (text-to-audio) — `acestep-ai/ace-step/text-to-audio` (default — cheap & fast)
50	> Original ACE Step. Tag-driven composition, optional lyrics, 5–240 s stereo. $0.0002/s — ~27× cheaper than ElevenLabs Music.
51	> Pick for: high-volume drafts, background music, jingles, game loops, cost-sensitive iteration.
52	> Avoid for: maximally polished commercial vocal hooks — try ACE Step 1.5 or ElevenLabs Music for those.
53
54	ACE Step (audio-inpaint) — `acestep-ai/ace-step/audio-inpaint`
55	> Regenerate a time range inside an existing track (not mask-based; uses `start_time` / `end_time` in seconds, each anchored to track start or end).
56	> Pick for: fix a bad chorus in the middle, swap the bridge, replace a 20 s section without re-rendering the whole song.
57	> Avoid for: edits that aren't time-bounded — those don't fit the schema.
58
59	ACE Step (audio-outpaint) — `acestep-ai/ace-step/audio-outpaint`
60	> Extend an existing track bidirectionally — add intro before, outro after, or both.
61	> Pick for: lengthening a 30 s draft into a 2 min cut, adding a fade-in, building a longer arrangement around an existing hook.
62	> Avoid for: extending a track past 4 min total — chain calls instead.
63
64	---
65
66	## Route 1: ACE Step text-to-audio (default)
67
68	Model: `acestep-ai/ace-step/text-to-audio` (or `acestep-ai/ace-step-1.5/text-to-audio` for the 1.5 variant)
69
70	### Schema (both variants — same shape)
71
72	\| Field \| Type \| Required \| Default \| Notes \|
73	\|---\|---\|---\|---\|---\|
74	\| `tags` \| string \| yes \| — \| Comma-separated genre / mood / instrument tags. Drives composition \|
75	\| `lyrics` \| string \| no \| — \| Vocal content. Use section markers `[Verse]`, `[Chorus]`, `[Bridge]`. Use `[inst]` or `[instrumental]` for no vocals \|
76	\| `duration` \| int \| no \| `60` \| Audio length in seconds. 5–240 (max 4 min per call) \|
77	\| `seed` \| int \| no \| `-1` \| Reproducibility; `-1` randomizes \|
78
79	Pricing: ACE Step $0.0002/s · ACE Step 1.5 $0.0003/s. 60 s ≈ $0.012 / $0.018; 240 s ≈ $0.048 / $0.072.
80
81	### Invoke
82
83	**Tag-dri

People who liked this also viewed

6 picks

Type