Files
MelodyMuse/README.md
T
Jannik b945417773 Add cancel, history, revert, and quality-of-life features
UX

- Add elapsed-time counter and Cancel button to in-flight generations,
  wired through AbortController so partial responses are discarded
  cleanly. The cancel action is available from both the input panel
  and the results header.
- Add a Recent generations panel below the input. The last 6 successful
  generations are saved to localStorage; one click reloads both the
  input fields and the generated assets.
- Add a Revert button to every editable card. It appears the moment
  the current value diverges from the last generated value and restores
  the field with a single click.
- Add an Empty state to the right panel with a friendly hint pointing
  at the Generate button and the Settings page.
- Add a 'Try an example' button that fills the input with a random
  starter idea (idea + mood + vocals).
- Add Cmd/Ctrl+Enter as a keyboard shortcut to generate.
- Add a Footer with project info and a privacy reminder.
- Add a 'Clear saved key' button to the Settings page so the user can
  remove the API key without overwriting it.

Bug fix

- Settings > Test Connection used to save the in-progress form values
  to localStorage before testing. It now uses the in-memory candidate
  config, so failed tests don't pollute the saved config.

Code quality

- Extract the duplicated useAutoHeight hook to src/lib/useAutoHeight.ts.
- Extract a useElapsed hook for the loading timer.
- Move InputValues into src/lib/types.ts (was duplicated in
  InputPanel.tsx) and add SECTION_LABELS, replacing the humanizeSection
  switch in HomePage.
- Centralize the filename sanitization: HomePage now calls
  sanitizeFilename from zip.ts instead of duplicating the regex.
- Add previewConfig / testConnectionWithConfig helpers to llm.ts to
  support in-memory connection tests.
2026-06-03 01:47:11 +02:00

152 lines
5.6 KiB
Markdown

# MelodyMuse
Generate all assets needed for a Suno AI song from a free-text description —
titles, lyrics, style prompt, video prompts (Abstract / Cinematic / Hybrid),
and a YouTube description, then download everything as a ZIP.
The app runs **entirely in your browser** as a single static SPA. There is no
backend, no database, no third-party services: the only network calls are
direct `fetch` requests from your browser to the AI provider's
OpenAI-compatible `/chat/completions` endpoint, using credentials that you
paste into the Settings page. Those credentials are kept in this browser's
`localStorage`.
## Features
- 🎵 **All 5 Suno assets in one click** — titles, lyrics, style, video prompts, YouTube description
- ✏️ **Inline editing** — every generated field is editable; revert any edit with one click
- 🔄 **Per-section regeneration** — regenerate just one section; the rest of the song is passed as context for consistency
-**Elapsed-time counter** + ❌ **Cancel** button for long generations
- 🕘 **Recent generations** — last 6 are kept in localStorage; one click to reload
- ⌨️ **Keyboard shortcut**`Cmd/Ctrl + Enter` to generate
- 🎲 **Try an example** — fill the input with a random sample idea
- 🌗 **Dark / light mode** — toggle in the header, persisted
- 💾 **Standalone** — no backend, no signup, no telemetry
## Tech stack
- React 18 + TypeScript + Vite
- Tailwind CSS (dark by default, light theme via `html.light`)
- JSZip for client-side ZIP generation
- `react-router-dom` for the two routes (`/`, `/settings`)
## Repository layout
```
MelodyMuse/
├── src/
│ ├── App.tsx
│ ├── main.tsx
│ ├── index.css # Tailwind layers + design-system components
│ ├── components/ # UI building blocks
│ │ ├── cards/ # The five result cards
│ │ ├── ConfigBanner.tsx
│ │ ├── CopyButton.tsx
│ │ ├── EqualizerIcon.tsx
│ │ ├── Footer.tsx
│ │ ├── HistoryPanel.tsx
│ │ ├── InputPanel.tsx
│ │ ├── ResultCard.tsx
│ │ ├── ResultsPanel.tsx
│ │ ├── SkeletonCard.tsx
│ │ ├── StickyZipBar.tsx
│ │ └── ThemeToggle.tsx
│ ├── pages/ # HomePage, SettingsPage
│ ├── lib/
│ │ ├── history.ts # recent-generations persistence
│ │ ├── llm.ts # direct fetch → provider, JSON extraction, config persistence
│ │ ├── prompts.ts # system + user prompt construction
│ │ ├── theme.ts # dark/light mode
│ │ ├── toast.tsx # toast context
│ │ ├── types.ts # shared TypeScript types + SECTION_LABELS
│ │ ├── useAutoHeight.ts # shared textarea auto-grow hook
│ │ ├── useElapsed.ts # shared "X seconds elapsed" hook
│ │ └── zip.ts # JSZip layout
│ └── vite-env.d.ts
├── public/favicon.svg
├── index.html
├── tailwind.config.js
├── vite.config.ts
├── tsconfig*.json
└── package.json
```
## Getting started
1. **Install dependencies**
```sh
npm install
```
2. **Start the dev server**
```sh
npm run dev
```
Open <http://localhost:5173> in your browser.
3. **Open Settings** and fill in:
- **API Endpoint URL** — e.g. `https://api.minimax.chat/v1`
- **API Key** — your provider's secret key
- **Model Name** — e.g. `MiniMax-M3`
Click **Save Configuration**, then **Test Connection** to confirm
everything is wired up. **Test Connection** uses your unsaved form
values — your changes are only persisted when you click **Save**.
4. **Generate**. Return to the home page, type a music idea, click
**Generate Song Assets** (or press `Cmd/Ctrl + Enter`).
## Build for production
```sh
npm run build
```
Outputs static assets in `dist/`. The `dist/` folder is a normal SPA — serve
it from any static host (GitHub Pages, Netlify, Vercel, `python -m http.server`,
…).
> ⚠️ **Heads up about deployment.** Because the API key is stored in the
> browser's `localStorage`, you should not serve a public deployment of this
> app and use it with a real key on a shared device. For personal/local use
> this is fine.
## CORS
The app makes direct cross-origin requests from the browser to your
provider. If your provider does not send the right `Access-Control-Allow-*`
headers for your origin, the request will fail with a CORS error. The
generated error message will explicitly call this out. Workarounds:
- Pick a provider/endpoint that already permits browser CORS (most managed
OpenAI-compatible services do).
- Run the app on the same origin as the API (i.e. front it with a tiny
proxy).
- Use a CORS-permissive browser extension during local development.
## Provider format
The configured endpoint must expose an OpenAI-compatible
`POST {api_endpoint}/chat/completions` route that accepts
`{ model, messages, max_tokens }` and returns
`{ choices: [{ message: { content } }] }`.
## Security notes
- The API key is held in `localStorage` and is only sent to the endpoint you
configure. No analytics, no telemetry, no third-party calls.
- Three localStorage keys are used:
- `melodymuse-config` — `{ api_endpoint, api_key, model_name }`
- `melodymuse-history` — the last 6 generations (input + assets)
- `melodymuse-theme` — `'dark' | 'light'`
- You can clear them at any time from your browser's devtools
(Application → Local Storage).
## License
Personal use. Do whatever you want with it.