Hmmify: AI-Powered Minecraft Villager Vocal Transformer

Web app that turns any audio into a Minecraft villager "singing" cover using Demucs vocal seperation and RVC

Key Features

AI Vocal Separation: Utilizes the Demucs model to isolate high-fidelity vocals from background instrumentals.
Voice Conversion Pipeline: Implements RVC-v2 (Retrieval-based Voice Conversion) to re-voice isolated vocals into the iconic Minecraft villager timbre.
Dynamic Visualizations: Features a React-based animation system that synchronizes character movement with audio playback.
Intelligent Caching: file-based caching layer to minimize redundant API calls and optimize performance.

Frontend
Next.js 14, React, Tailwind CSS, Framer Motion

Backend
Node.js, Next.js API Routes (Serverless)

AI/Processing
Replicate API, Demucs, RVC-v2, FFmpeg

NOTE: It takes quite a while to process, especially with wav files, so have some shorts pulled up or something idk lol

Name		Name	Last commit message	Last commit date
Latest commit History 40 Commits
app		app
components		components
data		data
fonts		fonts
lib		lib
public		public
screenshots		screenshots
.gitignore		.gitignore
README.md		README.md
next.config.js		next.config.js
package-lock.json		package-lock.json
package.json		package.json
postcss.config.js		postcss.config.js
tailwind.config.ts		tailwind.config.ts
tsconfig.json		tsconfig.json