NeptuneHub/AudioMuse-AI-NV-plugin

AudioMuse-AI Navidrome Plugin enhances music discovery by using sonic analysis to queue similar songs in real time.

What it solves

This plugin brings advanced AI-driven music discovery features to the Navidrome music server. It allows users to generate automatic song mixes based on similarity, find similar artists, and retrieve artist information directly within their existing music player interface.

How it works

It acts as a bridge between the Navidrome server and the AudioMuse-AI core application. Once installed in Navidrome's plugin folder and configured with the AudioMuse-AI API URL, it translates requests from the Navidrome frontend into calls that the AudioMuse-AI engine understands. It supports multiple similarity engines, including standard song similarity, lyric-based analysis, hyperbolic similarity, and DCLAP, which can be selected via the plugin settings.

Who it’s for

This is for self-hosted music enthusiasts who use Navidrome as their primary music server and want to enhance their listening experience with AI-powered recommendations and discovery tools.

Highlights

  • Enables "Instant Mix" functionality for automatic song recommendations.
  • Provides artist similarity and detailed artist information.
  • Compatible with various Subsonic-compatible mobile and web frontends, such as Substreamer, Symfonium, and Feishin.
  • Supports multiple AI analysis engines, including DCLAP and lyric-based search.
  • Integrates seamlessly into the Navidrome web UI and plugin management system.

Related

  • Project
    NeptuneHub/AudioMuse-AI

    A self-hosted AI tool that uses sonic analysis to organize music libraries and generate groove-aware playlists without relying on metadata.

  • Project
    Dodelidoo-Labs/sonobarr

    A music discovery tool for Lidarr users that blends Last.fm, ListenBrainz, and AI to suggest new artists and sync them directly to their library.

  • Project
    iuliandita/digarr

    A self-hosted music discovery tool that uses AI to suggest artists and albums based on listening history and mood, integrating with tools like Lidarr and Spotify.

  • Project
    smthemex/ComfyUI_Sonic

    ComfyUI Sonic is a custom ComfyUI node that brings the research‑grade Sonic method—audio‑driven portrait animation—into a visual workflow. It bundles audio‑to‑latent, diffusion, face‑detection, and optional Stable Video Diffusion models, letting users generate short talking‑head videos by connecting an audio file, setting a duration, and running the graph. This fork fixes compatibility issues (torch‑soundfile, CUDA device selection, BF16, low‑VRAM, Mac MPS) and adds small UI improvements.

  • Dispatch
    Gemini Music Generation with Lyria 3

    Google DeepMind has integrated the Lyria 3 generative music model into the Gemini app, enabling users to create 30-second AI-generated tracks from text prompts or image and video uploads.