← 返回 Skills 市场
2985
总下载
2
收藏
18
当前安装
1
版本数
在 OpenClaw 中安装
/install ace-music
功能描述
Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or...
使用说明 (SKILL.md)
ACE Music - AI Music Generation
Generate music via ACE Music's free hosted API (ACE-Step 1.5 model).
Setup
API Key is stored in env ACE_MUSIC_API_KEY. If not set:
- Open https://acemusic.ai/playground/api-key in the browser for the user
- Ask them to sign up (free) and paste the API key
- Store it:
export ACE_MUSIC_API_KEY=\x3Ckey>or add to TOOLS.md
Quick Generation
Use scripts/generate.sh for one-shot generation:
# Simple prompt (AI decides everything)
scripts/generate.sh "upbeat pop song about summer" --duration 30 --output summer.mp3
# With lyrics
scripts/generate.sh "gentle acoustic ballad, female vocal" \
--lyrics "[Verse 1]\
Sunlight through the window\
\
[Chorus]\
We are the dreamers" \
--duration 60 --output ballad.mp3
# Instrumental only
scripts/generate.sh "lo-fi hip hop beats, chill, rainy day" --instrumental --duration 120 --output lofi.mp3
# Natural language (AI writes everything)
scripts/generate.sh "write me a jazz song about coffee" --sample-mode --output jazz.mp3
# Specific settings
scripts/generate.sh "rock anthem" --bpm 140 --key "E minor" --language en --seed 42 --output rock.mp3
# Multiple variations
scripts/generate.sh "electronic dance track" --batch 3 --output edm.mp3
Script outputs file path(s) to stdout. Send the file to the user.
Advanced Usage (curl/direct API)
For covers, repainting, or audio input — see references/api-docs.md for full API spec.
Key task types:
text2music(default) — generate from text/lyricscover— cover an existing song (requires audio input)repaint— modify a section of existing audio
Parameters Guide
| Want | Use |
|---|---|
| Specific style | Describe in prompt: "jazz, saxophone solo, smoky bar" |
| Custom lyrics | --lyrics "[Verse]...[Chorus]..." |
| AI writes everything | --sample-mode |
| No vocals | --instrumental |
| Longer songs | --duration 120 (seconds) |
| Specific tempo | --bpm 120 |
| Specific key | --key "C major" |
| Multiple outputs | --batch 3 |
| Reproducible | --seed 42 |
| Non-English vocals | --language ja (zh, en, ja, ko, etc.) |
Notes
- API is free forever (confirmed by ACE Music team)
- Base URL:
https://api.acemusic.ai - Audio returned as base64 MP3, decoded automatically by the script
- Duration: if omitted, AI decides based on content
- For best results, use tagged mode (prompt + lyrics separated)
安全使用建议
This skill appears to be a straightforward wrapper around acemusic.ai, but it has three issues you should consider before installing:
1) Metadata mismatch: the skill metadata lists no required environment variables or primary credential, yet the SKILL.md and scripts require ACE_MUSIC_API_KEY (and optionally ACE_MUSIC_BASE_URL). Verify that you are comfortable providing a third-party API key and update any access controls or audit records accordingly.
2) Local dependencies: the helper script uses curl and python3. Ensure those binaries exist and are trusted on the host. Review the script (scripts/generate.sh) yourself — it decodes base64 audio returned by the remote API and writes files to disk.
3) Unknown origin: the skill's source and homepage are unknown. Confirm the legitimacy of acemusic.ai before sharing an API key or using the service. If you need stronger assurance, ask the publisher for a verified homepage, source repository, or a signed release.
If you proceed: set up a dedicated (revocable) API key for this service, test in an isolated environment, and inspect the script and network calls to confirm they only contact api.acemusic.ai and do not send other local data elsewhere.
功能分析
Type: OpenClaw Skill
Name: ace-music
Version: 1.0.0
The `scripts/generate.sh` file contains two significant vulnerabilities. Firstly, it is susceptible to JSON injection, as parameters like `--duration`, `--bpm`, and `--key` are directly inserted into the JSON request body without proper escaping, allowing an attacker to inject arbitrary JSON fields (e.g., `--duration '10,"malicious_field":"value"'`). Secondly, it has a path traversal vulnerability via the `--output` parameter, which allows an attacker to specify an output filename with directory traversal sequences (e.g., `../../evil.mp3`), potentially leading to arbitrary file writes on the system where the agent is running.
能力评估
Purpose & Capability
The skill's name, SKILL.md, API reference, and generate.sh all consistently implement an AI music-generation workflow against https://api.acemusic.ai using an API key. Requiring an API key and posting JSON to a music API is proportional to the stated purpose. However, the SKILL metadata claims no required env vars/credentials while the runtime docs and script clearly expect ACE_MUSIC_API_KEY (and optionally ACE_MUSIC_BASE_URL). This mismatch is a coherence issue.
Instruction Scope
SKILL.md instructs the agent/user to obtain and store an API key and to run scripts that perform network requests to api.acemusic.ai and write decoded audio files to disk — all expected for the stated task. But the instructions also tell the agent to open a browser to an external signup page and to store the key in an env var or TOOLS.md. More importantly, the runtime instructions and included script reference environment variables (ACE_MUSIC_API_KEY, ACE_MUSIC_BASE_URL) and call out use of python3 and curl, yet the skill's declared requirements list none. The instructions do not ask to read unrelated files or exfiltrate data, but the agent will transmit the API key to the external API host, which is expected but should be explicit in metadata.
Install Mechanism
No install spec is provided (instruction-only + a helper script), which is the lower-risk option. The included script will run curl and python3 at runtime — these are not installed by the skill and must exist on the host. Because there is no download/extract of third-party code, there is no high-risk install operation; still, the script will execute network calls and write files to disk when run.
Credentials
The skill requires an API key (ACE_MUSIC_API_KEY) to function, and may use ACE_MUSIC_BASE_URL, but the registry metadata declares no required env vars or primary credential. Declaring no credentials while the runtime requires a bearer token is an inconsistency that could confuse permission reviews or automated secrets audits. The number and scope of env vars requested (one API key) is appropriate for the task, but the missing declaration and the fact the skill will transmit that key to a third-party service are important to surface.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide changes. It simply contains an instruction and a helper script that runs ad-hoc API calls and writes audio files; this is normal for a user-invocable skill and does not grant elevated platform privileges.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install ace-music - 安装完成后，直接呼叫该 Skill 的名称或使用
/ace-music触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of ace-music – generate AI music using ACE-Step 1.5 via ACE Music's free API.
- Supports generating music, songs, beats, instrumentals, covers, and repainting using text, style prompts, and lyrics.
- Easy setup: guides users to obtain and store a free API key.
- Provides a script for quick one-shot music generation with customizable parameters (lyrics, style, genre, key, tempo, language, etc.).
- Supports advanced API usage for covers and audio editing tasks.
- No cost: utilizes ACE Music's confirmed free API.
元数据
常见问题
ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API. 是什么？
Generate AI music using ACE-Step 1.5 via ACE Music's free API. Use when the user asks to create, generate, or compose music, songs, beats, instrumentals, or... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2985 次。
如何安装 ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API.？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ace-music」即可一键安装，无需额外配置。
ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API. 是免费的吗？
是的，ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API. 完全免费（开源免费），可自由下载、安装和使用。
ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API. 支持哪些平台？
ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API. 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 ACE Music - Free Suno Alternative Generate unlimited AI music for free using ACE-Step 1.5. Full songs with vocals, lyrics, any genre, any language. No subscription, no credits, no limits. The open-source Suno alternative, powered by ACE Music's free API.？
由 fspecii（@fspecii）开发并维护，当前版本 v1.0.0。
推荐 Skills