← 返回 Skills 市场
107
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install acedatacloud-producer-music
功能描述
Generate AI music with Producer via AceDataCloud API. Use when creating songs, generating lyrics, extending tracks, creating covers, swapping vocals/instrume...
使用说明 (SKILL.md)
Producer Music Generation
Generate AI music through AceDataCloud's Producer API.
Authentication
export ACEDATACLOUD_API_TOKEN="your-token-here"
Quick Start
curl -X POST https://api.acedata.cloud/producer/audios \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"action": "generate", "prompt": "upbeat electronic dance track with synth leads"}'
Actions
| Action | Description |
|---|---|
generate |
Create a new song from prompt or custom lyrics |
cover |
Create a cover version of an existing song |
extend |
Continue a song from a specific timestamp |
upload_cover |
Create a cover from an uploaded reference audio |
upload_extend |
Extend from an uploaded reference audio |
replace_section |
Replace a time range in an existing song |
swap_vocals |
Extract and swap vocal tracks |
swap_instrumentals |
Extract and swap instrumental tracks |
variation |
Generate a variation of an existing song |
Workflows
1. Generate from Prompt
POST /producer/audios
{
"action": "generate",
"prompt": "chill lo-fi hip hop with rain sounds and soft piano"
}
2. Custom Lyrics Mode
POST /producer/audios
{
"action": "generate",
"custom": true,
"title": "Midnight City",
"lyric": "[Verse]\
Neon lights reflect on wet streets\
[Chorus]\
Midnight city never sleeps",
"instrumental": false
}
3. Instrumental Only
POST /producer/audios
{
"action": "generate",
"prompt": "epic orchestral soundtrack for a movie trailer",
"instrumental": true
}
4. Extend Song
POST /producer/audios
{
"action": "extend",
"audio_id": "existing-audio-id",
"continue_at": 30
}
5. Replace Section
POST /producer/audios
{
"action": "replace_section",
"audio_id": "existing-audio-id",
"replace_section_start": 15,
"replace_section_end": 30
}
6. Cover from Upload
POST /producer/audios
{
"action": "upload_cover",
"audio_id": "uploaded-reference-id",
"cover_strength": 0.8
}
7. Generate Lyrics
POST /producer/lyrics
{
"prompt": "a love song about stargazing on a summer night"
}
8. Get WAV / Video
POST /producer/wav
{"audio_id": "your-audio-id"}
POST /producer/videos
{"audio_id": "your-audio-id"}
9. Upload Reference Audio
POST /producer/upload
{
"audio_url": "https://example.com/reference.mp3"
}
Parameters
| Parameter | Type | Description |
|---|---|---|
action |
string | See actions table |
prompt |
string | Song description (for non-custom mode) |
model |
string | Model (e.g., "FUZZ-2.0 Pro") |
custom |
boolean | Enable custom lyrics mode |
instrumental |
boolean | Pure instrumental (no vocals) |
title |
string | Song title |
lyric |
string | Custom lyrics with [Verse], [Chorus] tags |
audio_id |
string | Existing audio ID (for edit actions) |
continue_at |
number | Seconds — where to extend from |
replace_section_start |
number | Start time of section to replace |
replace_section_end |
number | End time of section to replace |
lyrics_strength |
0–1 | Lyrics adherence (default: 0.7) |
sound_strength |
0.2–1 | Sound quality weight (default: 0.7) |
cover_strength |
0.2–1 | Cover similarity (default: 1.0) |
weirdness |
0–1 | Creative randomness (default: 0.5) |
seed |
string | Seed for reproducibility |
Task Polling
POST /producer/tasks
{"task_id": "your-task-id"}
Response Structure
{
"data": [
{
"id": "audio-id",
"audio_url": "https://cdn.example.com/song.mp3",
"video_url": "https://cdn.example.com/video.mp4",
"image_url": "https://cdn.example.com/cover.jpg",
"title": "Song Title",
"lyric": "full lyrics...",
"style": "electronic, dance",
"model": "FUZZ-2.0 Pro"
}
]
}
Gotchas
- Use
[Verse],[Chorus],[Bridge],[Outro]tags in custom lyrics continue_atis in seconds — the song extends from that pointreplace_section_start/replace_section_enddefine the time range to regenerateweirdnessat 0 = predictable, at 1 = highly experimental- Upload a reference audio first (
/producer/upload), then use the returned ID forupload_coverorupload_extend - WAV and video downloads are separate endpoints — call them after the main generation completes
安全使用建议
Before installing, confirm the skill's provenance (author/homepage) and that api.acedata.cloud is the intended service. The SKILL.md requires ACEDATACLOUD_API_TOKEN but the registry metadata does not list it—ask the publisher to correct this or refuse until fixed. If you test this skill, use a limited-scope or throwaway API token (do not reuse production credentials). Be aware that uploading reference audio or lyrics will send your content to the third-party service; review their privacy/retention and copyright policies. If possible, verify expected endpoints and responses with a test account and monitor network activity when first using the skill.
能力评估
Purpose & Capability
The SKILL.md describes exactly the actions you would expect for an AI music Producer (generate, cover, extend, upload, fetch WAV/video). Requiring an API token for AceDataCloud is appropriate for this purpose. However, the registry metadata lists no required environment variables or primary credential while the SKILL.md explicitly states it requires ACEDATACLOUD_API_TOKEN—this is an internal inconsistency.
Instruction Scope
Runtime instructions are limited to HTTP calls to api.acedata.cloud endpoints and uploading reference audio. They do not instruct the agent to read local files, other environment variables, or unrelated system paths. One scope-related note: uploading reference audio will transmit user audio to a third-party service; SKILL.md provides no privacy/retention guidance.
Install Mechanism
There is no install spec and no code files; the skill is instruction-only and will not write or execute code on disk as part of installation.
Credentials
The SKILL.md requires ACEDATACLOUD_API_TOKEN (reasonable and expected), but the registry metadata declares no required env vars or primary credential. That mismatch could be an oversight or misconfiguration in the published metadata; it reduces transparency about what secrets the skill will need.
Persistence & Privilege
The skill is not always-enabled and does not request system-wide persistence or to modify other skills. Autonomous invocation is allowed (platform default), which is expected for a functional skill.
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 acedatacloud-producer-music - 安装完成后,直接呼叫该 Skill 的名称或使用
/acedatacloud-producer-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: Generate and edit AI music with multiple creative actions via AceDataCloud Producer API.
- Supports song generation, lyric creation, covers, vocal/instrumental swapping, extending or replacing song sections, uploading reference audio, and variations.
- Custom lyrics, instrumental-only mode, and song section editing fully supported.
- Requires ACEDATACLOUD_API_TOKEN for authentication.
- Includes detailed usage examples, workflows, and API parameter documentation.
元数据
常见问题
Producer Music 是什么?
Generate AI music with Producer via AceDataCloud API. Use when creating songs, generating lyrics, extending tracks, creating covers, swapping vocals/instrume... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 107 次。
如何安装 Producer Music?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install acedatacloud-producer-music」即可一键安装,无需额外配置。
Producer Music 是免费的吗?
是的,Producer Music 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Producer Music 支持哪些平台?
Producer Music 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 Producer Music?
由 Germey(@germey)开发并维护,当前版本 v1.0.0。
推荐 Skills