refactor(skills): move heartmula + audiocraft to optional-skills/creative

Both are heavy-dep, GPU-bound local music-generation skills (8-16GB VRAM,
torch stacks, manual source patches) that were bundled in two different
categories (media/ and mlops/models/). Per the 'when in doubt, optional'
rule they now sit side by side in optional-skills/creative/, and the
bundled songwriting-and-ai-music skill points at them for local generation.

- git mv skills/media/heartmula -> optional-skills/creative/heartmula
- git mv skills/mlops/models/audiocraft -> optional-skills/creative/audiocraft
- cross-link related_skills both ways + songwriting-and-ai-music
- new section 10 in songwriting-and-ai-music with install commands
- docs: bundled pages -> optional pages (en + zh-Hans), catalogs, sidebar

Install via:
  hermes skills install official/creative/heartmula
  hermes skills install official/creative/audiocraft
This commit is contained in:
teknium1 2026-07-23 18:39:58 -07:00 committed by Teknium
parent e3d524b482
commit ba9277cc3e
16 changed files with 75 additions and 20 deletions

View file

@ -9,6 +9,7 @@ platforms: [linux, macos]
metadata:
hermes:
tags: [Multimodal, Audio Generation, Text-to-Music, Text-to-Audio, MusicGen]
related_skills: [heartmula, songwriting-and-ai-music]
---

View file

@ -6,7 +6,7 @@ platforms: [linux, macos, windows]
metadata:
hermes:
tags: [music, audio, generation, ai, heartmula, heartcodec, lyrics, songs]
related_skills: [audiocraft]
related_skills: [audiocraft-audio-generation, songwriting-and-ai-music]
---
# HeartMuLa - Open-Source Music Generation

View file

@ -285,3 +285,21 @@ Style can drift in extensions — restate genre/mood when extending.
- Don't be precious about rules. If a line breaks meter but hits
harder, keep it. The feeling is what matters. Craft serves art,
not the other way around.
---
## 10. Local / Open-Source Music Generation
For local, GPU-based generation instead of Suno, two optional skills
cover this (heavy dependencies, so not installed by default):
- **heartmula** — full songs with vocals from lyrics + tags
(open-source Suno alternative, 8-16GB VRAM):
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta's MusicGen (instrumental text-to-music) and
AudioGen (sound effects):
`hermes skills install official/creative/audiocraft`
The lyric-writing and prompting craft in this skill applies to
heartmula too — its input format is lyrics with bracketed structure
tags plus comma-separated style tags.

View file

@ -55,11 +55,13 @@ hermes skills uninstall <skill-name>
| Skill | Description |
|-------|-------------|
| [**audiocraft-audio-generation**](/docs/user-guide/skills/optional/creative/creative-audiocraft) | AudioCraft: MusicGen text-to-music, AudioGen text-to-sound. |
| [**baoyu-article-illustrator**](/docs/user-guide/skills/optional/creative/creative-baoyu-article-illustrator) | Article illustrations: type × style × palette consistency. |
| [**baoyu-comic**](/docs/user-guide/skills/optional/creative/creative-baoyu-comic) | Knowledge comics (知识漫画): educational, biography, tutorial. |
| [**blender-mcp**](/docs/user-guide/skills/optional/creative/creative-blender-mcp) | Drive Blender via the catalog blender MCP, with bpy recipes. |
| [**concept-diagrams**](/docs/user-guide/skills/optional/creative/creative-concept-diagrams) | Generate flat, minimal light/dark-aware SVG diagrams as standalone HTML files, using a unified educational visual language with 9 semantic color ramps, sentence-case typography, and automatic dark mode. Best suited for educational and no... |
| [**creative-ideation**](/docs/user-guide/skills/optional/creative/creative-creative-ideation) | Generate ideas via named methods from creative practice. |
| [**heartmula**](/docs/user-guide/skills/optional/creative/creative-heartmula) | HeartMuLa: Suno-like song generation from lyrics + tags. |
| [**hyperframes**](/docs/user-guide/skills/optional/creative/creative-hyperframes) | Create HTML-based video compositions, animated title cards, social overlays, captioned talking-head videos, audio-reactive visuals, and shader transitions using HyperFrames. HTML is the source of truth for video. Use when the user wants... |
| [**kanban-video-orchestrator**](/docs/user-guide/skills/optional/creative/creative-kanban-video-orchestrator) | Plan, set up, and monitor a multi-agent video production pipeline backed by Hermes Kanban. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loo... |
| [**meme-generation**](/docs/user-guide/skills/optional/creative/creative-meme-generation) | Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files. |

View file

@ -79,7 +79,6 @@ If a skill is missing from this list but present in the repo, the catalog is reg
| Skill | Description | Path |
|-------|-------------|------|
| [`gif-search`](/docs/user-guide/skills/bundled/media/media-gif-search) | Search/download GIFs from Tenor via curl + jq. | `media/gif-search` |
| [`heartmula`](/docs/user-guide/skills/bundled/media/media-heartmula) | HeartMuLa: Suno-like song generation from lyrics + tags. | `media/heartmula` |
| [`songsee`](/docs/user-guide/skills/bundled/media/media-songsee) | Audio spectrograms/features (mel, chroma, MFCC) via CLI. | `media/songsee` |
| [`youtube-content`](/docs/user-guide/skills/bundled/media/media-youtube-content) | YouTube transcripts to summaries, threads, blogs. | `media/youtube-content` |
@ -87,7 +86,6 @@ If a skill is missing from this list but present in the repo, the catalog is reg
| Skill | Description | Path |
|-------|-------------|------|
| [`audiocraft-audio-generation`](/docs/user-guide/skills/bundled/mlops/mlops-models-audiocraft) | AudioCraft: MusicGen text-to-music, AudioGen text-to-sound. | `mlops/models/audiocraft` |
| [`huggingface-hub`](/docs/user-guide/skills/bundled/mlops/mlops-huggingface-hub) | HuggingFace hf CLI: search/download/upload models, datasets. | `mlops/huggingface-hub` |
| [`llama-cpp`](/docs/user-guide/skills/bundled/mlops/mlops-inference-llama-cpp) | llama.cpp local GGUF inference + HF Hub model discovery. | `mlops/inference/llama-cpp` |
| [`evaluating-llms-harness`](/docs/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness) | lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.). | `mlops/evaluation/lm-evaluation-harness` |

View file

@ -296,3 +296,21 @@ Style can drift in extensions — restate genre/mood when extending.
- Don't be precious about rules. If a line breaks meter but hits
harder, keep it. The feeling is what matters. Craft serves art,
not the other way around.
---
## 10. Local / Open-Source Music Generation
For local, GPU-based generation instead of Suno, two optional skills
cover this (heavy dependencies, so not installed by default):
- **heartmula** — full songs with vocals from lyrics + tags
(open-source Suno alternative, 8-16GB VRAM):
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta's MusicGen (instrumental text-to-music) and
AudioGen (sound effects):
`hermes skills install official/creative/audiocraft`
The lyric-writing and prompting craft in this skill applies to
heartmula too — its input format is lyrics with bracketed structure
tags plus comma-separated style tags.

View file

@ -14,14 +14,15 @@ AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
| | |
|---|---|
| Source | Bundled (installed by default) |
| Path | `skills/mlops/models/audiocraft` |
| Source | Optional — install with `hermes skills install official/creative/audiocraft` |
| Path | `optional-skills/creative/audiocraft` |
| Version | `1.0.0` |
| Author | Orchestra Research |
| License | MIT |
| Dependencies | `audiocraft`, `torch>=2.0.0`, `transformers>=4.30.0` |
| Platforms | linux, macos |
| Tags | `Multimodal`, `Audio Generation`, `Text-to-Music`, `Text-to-Audio`, `MusicGen` |
| Related skills | [`heartmula`](/docs/user-guide/skills/optional/creative/creative-heartmula), [`songwriting-and-ai-music`](/docs/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## Reference: full SKILL.md
@ -575,8 +576,8 @@ for desc in descriptions:
## References
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/models/audiocraft/references/advanced-usage.md)** - Training, fine-tuning, deployment
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/skills/mlops/models/audiocraft/references/troubleshooting.md)** - Common issues and solutions
- **[Advanced Usage](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft/references/advanced-usage.md)** - Training, fine-tuning, deployment
- **[Troubleshooting](https://github.com/NousResearch/hermes-agent/blob/main/optional-skills/creative/audiocraft/references/troubleshooting.md)** - Common issues and solutions
## Resources

View file

@ -14,12 +14,12 @@ HeartMuLa: Suno-like song generation from lyrics + tags.
| | |
|---|---|
| Source | Bundled (installed by default) |
| Path | `skills/media/heartmula` |
| Source | Optional — install with `hermes skills install official/creative/heartmula` |
| Path | `optional-skills/creative/heartmula` |
| Version | `1.0.0` |
| Platforms | linux, macos, windows |
| Tags | `music`, `audio`, `generation`, `ai`, `heartmula`, `heartcodec`, `lyrics`, `songs` |
| Related skills | `audiocraft` |
| Related skills | [`audiocraft-audio-generation`](/docs/user-guide/skills/optional/creative/creative-audiocraft), [`songwriting-and-ai-music`](/docs/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## Reference: full SKILL.md

View file

@ -52,8 +52,10 @@ hermes skills uninstall <skill-name>
| 技能 | 描述 |
|-------|-------------|
| [**audiocraft-audio-generation**](/user-guide/skills/optional/creative/creative-audiocraft) | AudioCraftMusicGen 文本转音乐、AudioGen 文本转音效。 |
| [**blender-mcp**](/user-guide/skills/optional/creative/creative-blender-mcp) | 通过 socket 连接 blender-mcp 插件,直接从 Hermes 控制 Blender。创建 3D 对象、材质、动画,并运行任意 Blender Pythonbpy代码。适用于用户希望在 Blender 中创建或修改任何内容的场景。 |
| [**concept-diagrams**](/user-guide/skills/optional/creative/creative-concept-diagrams) | 生成扁平、极简、支持亮色/暗色模式的 SVG 图表,输出为独立 HTML 文件,采用统一的教育视觉语言,包含 9 种语义色阶、句首大写排版及自动暗色模式。最适合教育和说明类内容。 |
| [**heartmula**](/user-guide/skills/optional/creative/creative-heartmula) | HeartMuLa根据歌词 + 标签生成类 Suno 风格的歌曲。 |
| [**hyperframes**](/user-guide/skills/optional/creative/creative-hyperframes) | 使用 HyperFrames 创建基于 HTML 的视频合成、动态标题卡、社交叠层、字幕访谈视频、音频响应视觉效果及着色器转场。HTML 是视频的唯一来源。适用于用户希望制作任何视频内容的场景。 |
| [**kanban-video-orchestrator**](/user-guide/skills/optional/creative/creative-kanban-video-orchestrator) | 规划、搭建并监控由 Hermes Kanban 支撑的多 agent 视频制作流水线。适用于用户希望制作任何类型视频的场景 — 叙事影片、产品/营销视频、MV、解说视频、ASCII/终端艺术、抽象/生成式循环等。 |
| [**meme-generation**](/user-guide/skills/optional/creative/creative-meme-generation) | 通过选取模板并使用 Pillow 叠加文字来生成真实的 meme 图片,输出实际的 .png 文件。 |

View file

@ -90,7 +90,6 @@ Hermes 在执行 `hermes update` 时也会同步内置技能,但同步清单
| 技能 | 描述 | 路径 |
|-------|-------------|------|
| [`gif-search`](/user-guide/skills/bundled/media/media-gif-search) | 通过 curl + jq 从 Tenor 搜索/下载 GIF。 | `media/gif-search` |
| [`heartmula`](/user-guide/skills/bundled/media/media-heartmula) | HeartMuLa根据歌词 + 标签生成类 Suno 风格的歌曲。 | `media/heartmula` |
| [`songsee`](/user-guide/skills/bundled/media/media-songsee) | 通过 CLI 生成音频频谱图/特征mel、chroma、MFCC。 | `media/songsee` |
| [`youtube-content`](/user-guide/skills/bundled/media/media-youtube-content) | 将 YouTube 字幕转换为摘要、推文串、博客文章。 | `media/youtube-content` |
@ -98,7 +97,6 @@ Hermes 在执行 `hermes update` 时也会同步内置技能,但同步清单
| 技能 | 描述 | 路径 |
|-------|-------------|------|
| [`audiocraft-audio-generation`](/user-guide/skills/bundled/mlops/mlops-models-audiocraft) | AudioCraftMusicGen 文本转音乐、AudioGen 文本转音效。 | `mlops/models/audiocraft` |
| [`huggingface-hub`](/user-guide/skills/bundled/mlops/mlops-huggingface-hub) | HuggingFace hf CLI搜索/下载/上传模型、数据集。 | `mlops/huggingface-hub` |
| [`llama-cpp`](/user-guide/skills/bundled/mlops/mlops-inference-llama-cpp) | llama.cpp 本地 GGUF 推理 + HF Hub 模型发现。 | `mlops/inference/llama-cpp` |
| [`evaluating-llms-harness`](/user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness) | lm-eval-harness对 LLM 进行基准测试MMLU、GSM8K 等)。 | `mlops/evaluation/lm-evaluation-harness` |

View file

@ -286,4 +286,20 @@ AI 歌手不是在阅读——它们是在发音。帮助它们:
- Style 字段中强有力的人声人设描述比任何单个 metatag
都能产生更大的差异。
- 不要对规则过于执着。如果一行打破了韵律但冲击力更强,
就保留它。感受才是关键。技艺服务于艺术,而不是反过来。
就保留它。感受才是关键。技艺服务于艺术,而不是反过来。
---
## 10. 本地 / 开源音乐生成
如果想在本地用 GPU 生成音乐而不是使用 Suno有两个可选 skill
覆盖此场景(依赖较重,默认不安装):
- **heartmula** — 从歌词 + 标签生成带人声的完整歌曲
(开源 Suno 替代品,需 8-16GB 显存):
`hermes skills install official/creative/heartmula`
- **audiocraft** — Meta 的 MusicGen文本转纯音乐
AudioGen音效生成
`hermes skills install official/creative/audiocraft`
本 skill 中的歌词写作与提示词技巧同样适用于 heartmula —
它的输入格式是带方括号结构标签的歌词,加上逗号分隔的风格标签。

View file

@ -14,14 +14,15 @@ AudioCraftMusicGen 文本转音乐AudioGen 文本转声音。
| | |
|---|---|
| 来源 | 内置(默认安装) |
| 路径 | `skills/mlops/models/audiocraft` |
| 来源 | 可选 — 通过 `hermes skills install official/creative/audiocraft` 安装 |
| 路径 | `optional-skills/creative/audiocraft` |
| 版本 | `1.0.0` |
| 作者 | Orchestra Research |
| 许可证 | MIT |
| 依赖 | `audiocraft`, `torch>=2.0.0`, `transformers>=4.30.0` |
| 平台 | linux, macos |
| 标签 | `Multimodal`, `Audio Generation`, `Text-to-Music`, `Text-to-Audio`, `MusicGen` |
| 相关 skill | [`heartmula`](/user-guide/skills/optional/creative/creative-heartmula), [`songwriting-and-ai-music`](/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## 参考:完整 SKILL.md

View file

@ -14,12 +14,12 @@ HeartMuLa基于歌词与标签的类 Suno 歌曲生成。
| | |
|---|---|
| 来源 | 内置(默认安装) |
| 路径 | `skills/media/heartmula` |
| 来源 | 可选 — 通过 `hermes skills install official/creative/heartmula` 安装 |
| 路径 | `optional-skills/creative/heartmula` |
| 版本 | `1.0.0` |
| 平台 | linux, macos, windows |
| 标签 | `music`, `audio`, `generation`, `ai`, `heartmula`, `heartcodec`, `lyrics`, `songs` |
| 相关 skill | `audiocraft` |
| 相关 skill | [`audiocraft-audio-generation`](/user-guide/skills/optional/creative/creative-audiocraft), [`songwriting-and-ai-music`](/user-guide/skills/bundled/creative/creative-songwriting-and-ai-music) |
## 参考:完整 SKILL.md

View file

@ -221,7 +221,6 @@ const sidebars: SidebarsConfig = {
collapsed: true,
items: [
'user-guide/skills/bundled/media/media-gif-search',
'user-guide/skills/bundled/media/media-heartmula',
'user-guide/skills/bundled/media/media-songsee',
'user-guide/skills/bundled/media/media-youtube-content',
],
@ -232,7 +231,6 @@ const sidebars: SidebarsConfig = {
key: 'skills-bundled-mlops',
collapsed: true,
items: [
'user-guide/skills/bundled/mlops/mlops-models-audiocraft',
'user-guide/skills/bundled/mlops/mlops-huggingface-hub',
'user-guide/skills/bundled/mlops/mlops-inference-llama-cpp',
'user-guide/skills/bundled/mlops/mlops-evaluation-lm-evaluation-harness',
@ -373,11 +371,13 @@ const sidebars: SidebarsConfig = {
key: 'skills-optional-creative',
collapsed: true,
items: [
'user-guide/skills/optional/creative/creative-audiocraft',
'user-guide/skills/optional/creative/creative-baoyu-article-illustrator',
'user-guide/skills/optional/creative/creative-baoyu-comic',
'user-guide/skills/optional/creative/creative-blender-mcp',
'user-guide/skills/optional/creative/creative-concept-diagrams',
'user-guide/skills/optional/creative/creative-creative-ideation',
'user-guide/skills/optional/creative/creative-heartmula',
'user-guide/skills/optional/creative/creative-hyperframes',
'user-guide/skills/optional/creative/creative-kanban-video-orchestrator',
'user-guide/skills/optional/creative/creative-meme-generation',