Skip to content
Back to search

vocaloid-style-mv-pipeline

Production pipeline and Claude Code skill for Vocaloid-style hand-drawn (手書き) lyric music videos: deterministic Canvas2D/WebGL2 animation engine, JIZURA lyric motion, AI illustration, Blender toon 3D, headless rendering to 16:9 and 9:16.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/egsecda--vocaloid-style-mv-pipeline/badge.svg)](/listings/egsecda--vocaloid-style-mv-pipeline)

HTML

<a href="/listings/egsecda--vocaloid-style-mv-pipeline"><img src="/api/listings/egsecda--vocaloid-style-mv-pipeline/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**1. Check the machine.**

python skills/vocaloid-style-mv/scripts/check_env.py

**2a. Install the skill (recommended).** Copy it to your Claude Code skills folder:

# macOS / Linux / Git Bash
mkdir -p ~/.claude/skills && cp -r skills/vocaloid-style-mv ~/.claude/skills/
# Windows PowerShell
New-Item -ItemType Directory -Force "$env:USERPROFILE\.claude\skills" | Out-Null
Copy-Item -Recurse -Force skills\vocaloid-style-mv "$env:USERPROFILE\.claude\skills\"

Then put your song and lyrics in a folder, open Claude Code there and ask:

> make a V家手書き MV for this song (song.wav, lyrics.txt)

The skill scaffolds a project, analyses the song, proposes a concept for you to check, generates the art, builds and renders the film, and reviews it. It stops at a few checkpoints along the way: the concept, the character master, the first stills and the first full render.

**2b. Or use the template directly.**

python skills/vocaloid-style-mv/scripts/new_project.py ../my-mv --song path/to/song.wav --lyrics path/to/lyrics.lrc --setup
cd ../my-mv

`--setup` installs Playwright and the Python packages, downloads the fonts, and clones and builds JIZURA. `--title`, `--title-sub`, `--artist` and `--credit` set the film's title, Latin subtitle, artist name and credit line in `engine/timeline.js`. Open your agent in `../my-mv` and ask for the MV as above. Agents without skill support can be pointed at `skills/vocaloid-style-mv/SKILL.md`.

No song yet? Leave out `--song` / `--lyrics` and use a throwaway folder (the demo writes its own song and lyrics into the project). The new project then prints the commands for the procedural demo film 「蛍火」 (24 s; about 30 s to render on an RTX 3080), a smoke test that the machine renders end to end. Expected result: [16:9 clip](docs/images/demo_16x9.mp4) · [contact sheet](docs/images/demo_sheet.jpg) · [9:16 sheet](docs/images/demo_vertical_sheet.jpg).

<details> <summary>The main commands the agent runs (all from the project root)</summary>

python tools/analyze_audio.py                                   # audio/song.wav → analysis/audio.json (+ overview.png)
python tools/imagegen.py assets/char/jobs_core.jsonl --out-dir assets/char --concurrency 8
node tools/stills.mjs --times 12.5,62.6,130.8 --sheet check     # stills + contact sheet → render/stills/
node tools/render_final.mjs --name mv                           # full render + audio mux → render/mv.mp4
python tools/review_sheets.py render/mv.mp4 --step 1.8 --out render/review1

The skill's [`references/01-workflow.md`](skills/vocaloid-style-mv/references/01-workflow.md) has the full sequence, acceptance criteria and time budget. A procedural demo song in `template/demo/` is a smoke test that proves a new machine renders end to end. Its film, 「蛍火」: [16:9 clip](docs/images/demo_16x9.mp4) · [contact sheet](docs/images/demo_sheet.jpg) · [9:16 sheet](docs/images/demo_vertical_sheet.jpg).

</details>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 306 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="docs/images/hero.jpg" alt="Frames from 「残光」, a Vocaloid-style tegaki lyric MV made with vocaloid-style-mv-pipeline" width="100%">
  3. </p>
  4. <h1 align="center">Vocaloid-Style MV Pipeline</h1>
  5. <p align="center"><code>vocaloid-style-mv-pipeline</code></p>
  6. <p align="center">
  7. <b>A Claude Code skill and project template for Vocaloid-style 手書き (tegaki) lyric MVs and motion-graphics showreels.<br>
  8. A deterministic front-end animation engine renders every frame.</b>
  9. </p>
  10. <p align="center">
  11. English · <a href="README.zh-CN.md">简体中文</a> · <a href="README.ja.md">日本語</a>
  12. </p>
  13. <p align="center">
  14. Author: <b>NikusonP</b> · MIT License · showcase: 「残光」 (Music / Lyrics / Movie:NikusonP)
  15. </p>
  16. ---
  17. ## What it is
  18. Give an AI agent **a song and its lyrics**, and this kit lets it produce a finished, showreel-quality lyric music
  19. video in the ボカロ / V家手书 / 文字PV tradition. You get a 1920×1080 master, a natively re-laid-out 1080×1920
  20. vertical version, and share encodes.
  21. **It is front-end animation.** Every frame is drawn by HTML **Canvas2D** and composited by **WebGL2** in a
  22. headless browser. Playwright captures the frames and ffmpeg encodes them. No After Effects, no timeline editor.
  23. A frame is a pure function of song time `t`, so the film is code: re-rendering always gives the same result,
  24. parallel workers can render any frame, and an agent can review, fix and re-render a 4-minute MV in minutes.
  25. The kit has two parts:
  26. - **The skill** ([`skills/vocaloid-style-mv/`](skills/vocaloid-style-mv/)): `SKILL.md` plus method references that
  27. take an agent from *listen → concept → assets → storyboard → build → review → deliver*.
  28. - **The project template** ([`skills/vocaloid-style-mv/template/`](skills/vocaloid-style-mv/template/)): the engine,
  29. a scene library, the [JIZURA 字面](https://github.com/852wa/JIZURA) lyric-motion layer, audio-analysis and
  30. lyric-timing tools, AI image-generation tooling, Blender toon-3D shot scripts and the renderer. Every new MV
  31. project starts as a copy of it.
  32. The skill was written for Claude Code, but it is plain Markdown plus scripts, so other agents such as Codex
  33. can follow it too.
  34. ## Showcase: 「残光」
  35. **「残光」 (Zankō, "Afterglow"). Music / Lyrics / Movie:NikusonP.**
  36. A 3:46 MV with an original V家-style singer, 灯 (Akari). The sky cracks like glass, she falls into the night,
  37. keeps a small flame alive, gathers the pieces of her shattered heart, and walks a road made of her own tears
  38. toward the dawn. It has 68 beat-locked shots, JIZURA typography, two Blender toon-3D sequences, and a hard cut
  39. on the song's dead stop to a cyan afterimage. The full 1080p30 film renders in **≈4 minutes on an RTX 3080**
  40. (6,796 frames, 3 workers, ≈31 fps).
  41. <p align="center">
  42. <img src="docs/images/vertical_strip.jpg" alt="Five frames of the 9:16 vertical version" width="100%"><br>
  43. <sub>The 9:16 version is a re-layout, not a crop: JIZURA re-typesets every lyric natively for the tall frame.</sub>
  44. </p>
  45. <table>
  46. <tr>
  47. <td width="50%"><a href="examples/zanko/gallery/sheet_01.jpg"><img src="examples/zanko/gallery/sheet_01.jpg" alt="Contact sheet 0:45–1:28"></a></td>
  48. <td width="50%"><a href="examples/zanko/gallery/sheet_04.jpg"><img src="examples/zanko/gallery/sheet_04.jpg" alt="Contact sheet 3:00–3:43"></a></td>
  49. </tr>
  50. <tr>
  51. <td><a href="examples/zanko/gallery/blender_A.jpg"><img src="examples/zanko/gallery/blender_A.jpg" alt="Blender sequence A: street of 3D kanji"></a></td>
  52. <td><a href="examples/zanko/gallery/_core.jpg"><img src="examples/zanko/gallery/_core.jpg" alt="Generated character poses"></a></td>
  53. </tr>
  54. </table>
  55. More in the gallery (click to open full size):
  56. | what | files |
  57. |---|---|
  58. | Review contact sheets of the final render, one frame every 1.8 s | [0:00–0:43](examples/zanko/gallery/sheet_00.jpg) · [0:45–1:28](examples/zanko/gallery/sheet_01.jpg) · [1:30–2:13](examples/zanko/gallery/sheet_02.jpg) · [2:15–2:58](examples/zanko/gallery/sheet_03.jpg) · [3:00–3:43](examples/zanko/gallery/sheet_04.jpg) · [end card](examples/zanko/gallery/sheet_05.jpg) |
  59. | 9:16 vertical version | [part 1](examples/zanko/gallery/vsheet_01.jpg) · [part 2](examples/zanko/gallery/vsheet_02.jpg) |
  60. | Blender toon 3D | [A: dusk street of kanji](examples/zanko/gallery/blender_A.jpg) · [B: night railway crossing](examples/zanko/gallery/blender_B.jpg) |
  61. | Typography and colour | [JIZURA style probe](examples/zanko/gallery/jizura_styles.jpg) · [palette system](examples/zanko/gallery/style_palettes.png) |
  62. | Generated assets | [character masters](examples/zanko/gallery/_masters.jpg) · [poses](examples/zanko/gallery/_core.jpg) · [more poses](examples/zanko/gallery/_more.jpg) · [story poses](examples/zanko/gallery/_story_a.jpg) · [fixes](examples/zanko/gallery/_fix.jpg) · [backgrounds](examples/zanko/gallery/_bgs.jpg) · [night backgrounds + props](examples/zanko/gallery/_story.jpg) |
  63. The full case study (logline, colour script, shot structure, signature moments and how each was built) is in
  64. [`examples/zanko/`](examples/zanko/README.md).
  65. ## Features
  66. - **Deterministic renderer.** Each frame is a pure function of `t`: seeded noise, closed-form particles, no
  67. wall-clock time. Parallel headless-browser workers seek arbitrary frames, and the segments join without seams.
  68. - **Layered compositing.** Each frame has a scene layer (Canvas2D illustration, camera, particles), a text layer
  69. (JIZURA lyrics, custom typography, HUD), a *foreground* layer (the character drawn in front of the lyrics, so
  70. text can pass behind her), and a WebGL2 post pass. The post pass does line boil on 2s, OKLab palette gradient
  71. maps, bloom, chromatic aberration, glitch, zoom blur, grain, flashes and letterbox. Text stays crisp because the
  72. scene-only effects never touch it.
  73. - **Scene library.** 24 parameterised scenes are included: `illust`, `kanjiSlam`, `typeCard`, `titleRiff`,
  74. `ember`, `heart`, `skyShatter`, `fall`, `flame`, `ink`, `thread`, `wetFloor`, `train`, `memories`, `road`,
  75. `panels`, `burst`, `tunnel`, `converge`, `afterimage`, `ref` (freeze / rewind / melt another shot), `seq`
  76. (image sequences), `jz`, `solid`. There are also 13 transitions: cut, xfade, flash, black, iris, irisClose,
  77. barrier, wipe, slices, push, zoom, ink, shatter. All of them are a toolbox to adapt, not a look to reuse.
  78. - **JIZURA 字面 lyric layer.** The upstream engine is built unmodified into a deterministic layer, with several
  79. plans (styles) per film, curated deny-lists, centre-free layouts for character shots, and native 9:16
  80. re-typesetting.
  81. - **A beat-locked edit.** `librosa` analysis gives beats, downbeats, bars, sections, stops, impacts and per-frame
  82. envelopes, and it handles tempo drift. Timeline helpers snap every cut to a real bar or beat.
  83. - **Lyric timing.** Official lyrics come first. faster-whisper, vocal-stem separation and forced alignment are
  84. there for timings, or for the case where no text exists. The output is an LRC file with JIZURA markup
  85. (`/` cut, `*emphasis*`, `!` キメ line).
  86. - **An original character and consistent assets.** The pipeline goes character bible → master candidates →
  87. every pose generated with the master as a reference image → chroma key to RGBA. Batch generation runs through
  88. the Codex CLI, and any image model works with the same method.
  89. - **Toon 3D.** The Blender 5.x shot scripts use EEVEE, Shader-to-RGB cel shading and Grease Pencil line art, at
  90. about 0.7 s per 1080p frame. Cameras are keyed to the beat grid, and the result plays back in the engine as an
  91. image sequence.
  92. - **Delivery.** You get a 16:9 master (NVENC CQ16 or x264), a share encode, a 9:16 vertical re-layout and 720p
  93. previews, plus review tools: stills, contact sheets, review sheets every N seconds, and a JIZURA cut inspector.
  94. ## Pipeline
  95. ```mermaid
  96. flowchart LR
  97. A["song.wav + official lyrics"] --> B["Listen<br/>librosa beats · bars · sections<br/>lyric timing (LRC)"]
  98. B --> C["Concept<br/>thesis · colour script<br/>motifs · character bible"]
  99. C --> D["Assets<br/>Codex image gen<br/>chroma key → RGBA"]
  100. C --> E["Storyboard<br/>→ engine/timeline.js"]
  101. D --> F["Build<br/>engine scenes + JIZURA lyrics<br/>+ Blender toon 3D"]
  102. E --> F
  103. F --> G["Render<br/>Playwright + headless Edge<br/>+ ffmpeg NVENC"]
  104. G --> H["Review<br/>stills · contact sheets"]
  105. H -- "fix, 2–3 passes" --> F
  106. H --> I["Deliver<br/>16:9 master · share · 9:16"]
  107. ```
  108. What happens inside one frame:
  109. ```
  110. song time t ─┬─► scene layer Canvas2D 1920×1080: illustration, camera, particles ──┐
  111. ├─► text layer JIZURA 字面 + custom typography + HUD (transparent) ──┼─► WebGL2 post ─► frame
  112. └─► foreground layer the character, in front of the lyrics ────────────────┘ line boil · palette LUT · bloom
  113. CA · glitch · grain · flash
  114. ```
  115. ## Quick start
  116. **1. Check the machine.**
  117. ```bash
  118. python skills/vocaloid-style-mv/scripts/check_env.py
  119. ```
  120. **2a. Install the skill (recommended).** Copy it to your Claude Code skills folder:
  121. ```bash
  122. # macOS / Linux / Git Bash
  123. mkdir -p ~/.claude/skills && cp -r skills/vocaloid-style-mv ~/.claude/skills/
  124. ```
  125. ```powershell
  126. # Windows PowerShell
  127. New-Item -ItemType Directory -Force "$env:USERPROFILE\.claude\skills" | Out-Null
  128. Copy-Item -Recurse -Force skills\vocaloid-style-mv "$env:USERPROFILE\.claude\skills\"
  129. ```
  130. Then put your song and lyrics in a folder, open Claude Code there and ask:
  131. > make a V家手書き MV for this song (song.wav, lyrics.txt)
  132. The skill scaffolds a project, analyses the song, proposes a concept for you to check, generates the art, builds
  133. and renders the film, and reviews it. It stops at a few checkpoints along the way: the concept, the character
  134. master, the first stills and the first full render.
  135. **2b. Or use the template directly.**
  136. ```bash
  137. python skills/vocaloid-style-mv/scripts/new_project.py ../my-mv --song path/to/song.wav --lyrics path/to/lyrics.lrc --setup
  138. cd ../my-mv
  139. ```
  140. `--setup` installs Playwright and the Python packages, downloads the fonts, and clones and builds JIZURA.
  141. `--title`, `--title-sub`, `--artist` and `--credit` set the film's title, Latin subtitle, artist name and credit
  142. line in `engine/timeline.js`. Open your agent in `../my-mv` and ask for the MV as above. Agents without skill
  143. support can be pointed at `skills/vocaloid-style-mv/SKILL.md`.
  144. No song yet? Leave out `--song` / `--lyrics` and use a throwaway folder (the demo writes its own song and lyrics
  145. into the project). The new project then prints the commands for the procedural demo film 「蛍火」 (24 s; about
  146. 30 s to render on an RTX 3080), a smoke test that the machine renders end to end. Expected result:
  147. [16:9 clip](docs/images/demo_16x9.mp4) · [contact sheet](docs/images/demo_sheet.jpg) ·
  148. [9:16 sheet](docs/images/demo_vertical_sheet.jpg).
  149. <details>
  150. <summary>The main commands the agent runs (all from the project root)</summary>
  151. ```bash
  152. python tools/analyze_audio.py # audio/song.wav → analysis/audio.json (+ overview.png)
  153. python tools/imagegen.py assets/char/jobs_core.jsonl --out-dir assets/char --concurrency 8
  154. node tools/stills.mjs --times 12.5,62.6,130.8 --sheet check # stills + contact sheet → render/stills/
  155. node tools/render_final.mjs --name mv # full render + audio mux → render/mv.mp4
  156. python tools/review_sheets.py render/mv.mp4 --step 1.8 --out render/review1
  157. ```
  158. The skill's [`references/01-workflow.md`](skills/vocaloid-style-mv/references/01-workflow.md) has the full
  159. sequence, acceptance criteria and time budget. A procedural demo song in `template/demo/` is a smoke test that
  160. proves a new machine renders end to end. Its film, 「蛍火」: [16:9 clip](docs/images/demo_16x9.mp4) ·
  161. [contact sheet](docs/images/demo_sheet.jpg) · [9:16 sheet](docs/images/demo_vertical_sheet.jpg).
  162. </details>
  163. ## Requirements
  164. | | what | notes |
  165. |---|---|---|
  166. | **required** | Node.js 20+ | Playwright, the render and stills scripts |
  167. | **required** | Python 3.10+ | `librosa`, `numpy`, `scipy`, `soundfile`, `pillow`, `matplotlib` (setup installs them) |
  168. | **required** | ffmpeg + ffprobe on `PATH` | encoding, audio mux, frame extraction |
  169. | **required** | Microsoft Edge or Google Chrome | headless WebGL2 through Playwright (`msedge` / `chrome` channel) |
  170. | **required** | git | setup clones JIZURA |
  171. | optional | NVIDIA GPU (NVENC) | GPU WebGL plus hardware H.264. Without it, encoding falls back to x264, and software WebGL is about 10× slower |
  172. | optional | Blender 5.x | toon 3D sequences. Without it, the agent stages the 3D moments in 2.5D |
  173. | optional | Codex CLI, or another image generator | character and background art. Any model works with the reference-image + chroma-key method |
  174. | optional | faster-whisper (+ CUDA) | only when no official lyrics exist, or to align timings |
  175. Windows 11 (PowerShell 5.1 or Git Bash) is the tested platform. macOS and Linux are supported through the
  176. cross-platform scripts but have seen less testing. Reference numbers from 「残光」 on an RTX 3080: audio analysis
  177. under 1 min; one generated image 30–110 s (8–10 in parallel); Blender ≈0.7 s/frame; full 1080p render ≈4 min.
  178. Setup clones JIZURA at the tested commit `fc16bfe`; the template's deny-lists and scheme indices are checked
  179. against it. To use another version, set the environment variable `JIZURA_REF` to a branch, tag or full commit
  180. sha for setup (e.g. `main` to follow upstream). `JIZURA_DIR` points setup at an existing local clone and takes precedence.
  181. ## Repository layout
  182. ```
  183. vocaloid-style-mv-pipeline/
  184. ├── README.md · README.zh-CN.md · README.ja.md
  185. ├── LICENSE · THIRD_PARTY_NOTICES.md
  186. ├── skills/
  187. │ └── vocaloid-style-mv/ ← the installable skill (copy to ~/.claude/skills/)
  188. │ ├── SKILL.md ← entry point: phases, principles, checkpoints
  189. │ ├── references/ ← method: workflow, creative direction, audio & lyrics, assets,
  190. │ │ engine, JIZURA, Blender, render & delivery, QA & lessons
  191. │ ├── scripts/ ← new_project.py (scaffold), check_env.py (environment check)
  192. │ └── template/ ← copied into every new MV project
  193. │ ├── engine/ ← core/ (util, assets, gl, draw, trans, main), scenes/ (library),
  194. │ │ index.html, vertical.html + vertical.js, fonts/
  195. │ ├── jizura/app/ ← JIZURA adapter + host pages (bundle built at setup from vendor/JIZURA)
  196. │ ├── tools/ ← analysis, lyric timing, image gen, stills, render, review sheets
  197. │ ├── blender/ ← toon 3D shot scripts
  198. │ ├── assets/ ← style/ (palettes + LUTs), char/, bg/
  199. │ ├── analysis/ · audio/ ← filled per song
  200. │ └── demo/ ← procedural smoke-test song
  201. ├── examples/
  202. │ └── zanko/ ← 「残光」 case study: storyboard, timeline, prompts, gallery
  203. └── docs/images/ ← README images
  204. ```
  205. ## Similar craft, different film
  206. The kit aims for **another film of the same quality**, not a 残光 clone. A few ideas carry through the skill:
  207. - **The concept comes from the new song.** The agent reads *your* lyrics and structure first. From them it
  208. finds a thesis (what the song is about visually), a colour script, master shapes and motifs, a character, and
  209. 6–10 signature moments placed on the song's real chorus downbeats, stops and instrumental hits.
  210. - **The scene library is a toolbox.** Most shots are generic `illust` shots (background, camera, character,
  211. effects). The special scenes show *techniques* such as shatter, ink growth, strobing silhouettes, image-sequence
  212. playback and per-beat slams. A new song needs new metaphors, so the agent adapts these scenes or writes new ones.
  213. - **[`examples/zanko`](examples/zanko/README.md) is a case study, not a preset.** Learn how a lyric became an
  214. image and how a section built up. Do not reuse its cracked sky, glass heart, ribbon or palettes for a song that
  215. never mentions them. The skill's creative-direction reference has a *variation matrix* (world, time arc,
  216. palette, shape, material, line style, character, typography, 3D role, transitions, ending). If a new plan
  217. matches 残光 on more than three axes, the agent pushes further.
  218. - **Night or daylight.** The template's defaults are tuned for 残光's dusk and night; for a bright, daytime film
  219. the agent re-tunes the lyric colours, the post look and the palettes before the first still.
  220. - **The character is original.** Every pose is generated from one master reference. Existing characters are
  221. never imitated.
  222. - **Look at every result.** Stills and contact sheets get reviewed like an art director would, then fixed and
  223. re-rendered. Most of the quality comes from this review loop.
  224. ## Credits
  225. - **Kit, 「残光」 song, lyrics and movie:** NikusonP. *Music / Lyrics / Movie:NikusonP*
  226. - **[JIZURA 字面](https://github.com/852wa/JIZURA)** by 852wa: lyric-motion engine, MIT, © 2026 hakoniwa (fetched at setup, not vendored)
  227. - **Fonts:** Google Fonts families (Noto Sans/Serif JP & SC, Zen Old Mincho, Zen Kaku Gothic New, Shippori
  228. Mincho B1, Kaisei Tokumin, Klee One, Yuji Syuku, DotGothic16, Dela Gothic One, Rampart One, Reggae One, M PLUS
  229. Rounded 1c), SIL OFL 1.1
  230. - **[Playwright](https://playwright.dev/)** (Apache-2.0) · **[librosa](https://librosa.org/)** (ISC) ·
  231. **NumPy / SciPy** (BSD-3-Clause) · **Pillow** (MIT-CMU) · **soundfile** (BSD-3-Clause) ·
  232. **[faster-whisper](https://github.com/SYSTRAN/faster-whisper)** (MIT) · **CTranslate2** (MIT) ·
  233. **ONNX Runtime** (MIT)
  234. - **External tools:** [Blender](https://www.blender.org/) (GPL), [FFmpeg](https://ffmpeg.org/) (LGPL/GPL),
  235. [Codex CLI](https://github.com/openai/codex) (illustrations generated with an AI image model), Microsoft Edge
  236. - Built with [Claude Code](https://claude.com/claude-code).
  237. Full details, including the optional models and their terms: [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md).
  238. ## License
  239. The kit's code, skill and documentation are released under the [MIT License](LICENSE), © 2026 NikusonP.
  240. The song 「残光」, its lyrics, the character 灯 and the MV frames in `examples/zanko/` and `docs/images/` are
  241. © 2026 NikusonP, all rights reserved — they are **not** covered by the MIT License and are included only as a case study. **The song audio and the full-resolution artwork are not
  242. in this repository.** Please don't reuse the 残光 material as the material of your own MV. Make your own from
  243. your song; that is what the kit is for. Third-party components keep their own licences; see
  244. [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md).
  245. **Trademark notice.** VOCALOID is a registered trademark of Yamaha Corporation. This is an independent project, not affiliated with, sponsored or endorsed by Yamaha Corporation; "Vocaloid-style" describes the visual genre of fan-made music videos (ボカロMV / V家手书).
  246. ---
  247. <p align="center">Author: <b>NikusonP</b></p>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.