Melodia

AI-Powered Music Generation Platform
Create full songs, lyrics, and cover art from simple text descriptions.

Overview

Melodia is a cutting-edge full-stack application that leverages the power of generative AI to transform text prompts into complete musical compositions. Unlike simple melody generators, Melodia creates a cohesive package including:

• High-Fidelity Audio: Generated using the ACE-Step model.
• Contextual Lyrics: Written by Qwen2-7B-Instruct based on your theme.
• Album Art: Visualized by Stable Diffusion Turbo.

Built with a modern tech stack, it features a responsive Next.js frontend and a scalable serverless Python backend running on Modal.

Key Features

• Text-to-Song Generation: Simply describe the vibe, genre, or topic (e.g., "A sad piano ballad about rain").
• Multi-Modal Output: Automatically generates audio, lyrics, and cover art in one go.
• Customization: Toggle instrumental mode or provide your own lyrics.
• User Dashboard: Track your generation history, manage credits, and organize your library.
• Social Features: Like and share songs with the community.
• Scalable Infrastructure: Powered by Modal for on-demand GPU inference and Cloudflare R2 for asset storage.

Architecture

The project is divided into two main components:

1. Frontend (/frontend): A Next.js 15 application handling the UI, authentication, and database interactions.
2. Backend (/backend): A Python-based AI engine running on Modal, responsible for the heavy lifting (inference).

Tech Stack

Category	Technologies
Frontend	Next.js 15 (App Router), React 19, Tailwind CSS v4, Shadcn UI
Backend	Python 3.10, Modal (Serverless GPU), FastAPI
AI Models	ACE-Step (Audio), Qwen2-7B (Lyrics/Prompt), SD-Turbo (Images)
Database	PostgreSQL, Prisma ORM
Storage	Cloudflare R2 (S3 Compatible)
Auth	Better Auth
Queue	Inngest (Event-driven background jobs)

Project Structure

root/
├── frontend/               # Next.js Application
│   ├── src/
│   │   ├── app/            # App Router pages & layouts
│   │   ├── components/     # React components (UI & Feature specific)
│   │   ├── actions/        # Server Actions (Generation logic)
│   │   ├── inngest/        # Background job definitions
│   │   └── lib/            # Utilities & configurations
│   ├── prisma/             # Database schema & migrations
│   └── public/             # Static assets
│
└── backend/                # Python AI Engine
    ├── main.py             # Modal app entry point & API
    ├── prompt.py           # Prompt engineering templates
    └── requirements.txt    # Python dependencies

Getting Started

Prerequisites

• Node.js (v18+ recommended)
• pnpm (Package manager)
• Python (3.10+)
• Modal CLI (pip install modal)
• PostgreSQL Database
• Cloudflare R2 Bucket

1. Clone the Repository

git clone https://github.com/Izume01/Melodia.git
cd Melodia

2. Backend Setup (Modal)

Navigate to the backend directory and install dependencies:

cd backend
pip install -r requirements.txt
modal setup  # Authenticate with Modal

Set up your Modal secrets (R2 credentials & Hugging Face token) via the Modal dashboard or CLI:

• R2_ACCOUNT_ID
• R2_ACCESS_KEY_ID
• R2_SECRET_ACCESS_KEY
• R2_BUCKET_NAME
• HF_TOKEN

Deploy or run the backend app:

modal serve main.py

3. Frontend Setup

Navigate to the frontend directory and install dependencies:

cd ../frontend
pnpm install

Create a .env file in the frontend root based on the example below:

# Database
DATABASE_URL="postgresql://user:password@localhost:5432/melodia"

# Auth (Better Auth)
BETTER_AUTH_SECRET="your_generated_secret"
BETTER_AUTH_URL="http://localhost:3000"

# Inngest
NEXT_PUBLIC_INNGEST_EVENT_KEY="local"
NEXT_PUBLIC_INNGEST_SIGNING_KEY="local"

# AWS / R2 (For client-side presigning if needed)
AWS_ACCESS_KEY_ID=""
AWS_SECRET_ACCESS_KEY=""
AWS_REGION="auto"
AWS_BUCKET_NAME=""
AWS_ENDPOINT=""

Initialize the database:

pnpm prisma generate
pnpm prisma migrate dev

Run the development server:

pnpm dev

Open http://localhost:3000 in your browser.

Roadmap

• Core Music Generation (Audio + Lyrics + Image)
• User Authentication & Profiles
• Song Library & History
• Social Sharing & Community Feed
• Advanced Music Controls (Tempo, Key, Instruments)
• Playlist Creation
• Mobile App (React Native)

Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository.
2. Create a new branch (git checkout -b feature/amazing-feature).
3. Commit your changes (git commit -m 'Add some amazing feature').
4. Push to the branch (git push origin feature/amazing-feature).
5. Open a Pull Request.

License

Distributed under the MIT License. See LICENSE for more information.

---

Built by Izume01