# NeptuneHub/AudioMuse-AI

AudioMuse-AI uses sonic analysis to rediscover forgotten songs, uncover hidden connections in your music library, and generate intelligent playlists for Navidrome, Jellyfin, LMS, Lyrion, Emby and Plex: no metadata or external services required.

Repository: https://github.com/NeptuneHub/AudioMuse-AI
Canonical: https://ross.abutalabs.com/products/audiomuse-ai
Homepage: https://neptunehub.github.io/AudioMuse-AI/
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: jellyfin, playlist, docker, k3s, kubernetes, llm, librosa, navidrome, sonic-analysis, jellyfin-plugin, onnx, clap, emby, lyrion, smart-playlists, music, self-hosted, plex
Last push: 2026-08-26T07:06:21+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 33
- inputs: {"age_days": 466, "days_push": 7, "days_rel": 12, "gap_med": 2.0, "n_releases_24m": 83}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2496, forks 145 (observed 2026-08-28T04:06:56.578999+00:00)

## What it is
AudioMuse-AI is a self-hosted application that performs sonic analysis on your music library to generate intelligent, AI-driven playlists without relying on metadata or external services. It integrates with self-hosted music servers like Navidrome, Jellyfin, LMS, Lyrion, Emby, and Plex, offering features like clustering, instant playlists, and a visual music map.

## Use cases
- generate smart playlists from my local music library
- find sonically similar songs in my collection
- create playlists for Navidrome or Jellyfin automatically
- visualize my music library as a 2D map
- rediscover forgotten songs in my music collection
- generate playlists from natural language prompts like 'high-tempo low-energy'
- analyze music across multiple media servers with duplicate detection

## When to choose
- you self-host music on Navidrome, Jellyfin, Plex, Emby, LMS, or Lyrion and want AI-generated playlists
- you want playlist generation based on actual audio characteristics rather than metadata or external APIs
- you want to explore and visualize your music library's sonic landscape
- you want a self-hosted, privacy-friendly alternative to streaming service recommendation engines

## When to avoid
- you use a cloud streaming service like Spotify or Apple Music instead of self-hosted music servers
- you only need simple metadata-based playlists without audio analysis
- you cannot run Docker, Kubernetes, or native desktop applications
- your library is very small and manual playlist curation is sufficient

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, audio-processing, nlp, data-visualization, self-hosted
- domain: audio, media, machine-learning, self-hosted
- platform: windows, self-hosted, cross-platform
- tags: sonic-analysis, playlist-generation, music-library, navidrome, jellyfin, plex, emby, lyrion, lms, clap, librosa, onnx, llm, smart-playlists, music-map, audio, docker, kubernetes, linux, macos

## Member repositories
- NeptuneHub/AudioMuse-AI (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:56.578999+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:27:10.632765+00:00, confidence not recorded.
  - readme: https://github.com/NeptuneHub/AudioMuse-AI (fetched 2026-08-28T04:06:56.578999+00:00, sha cebd692b8d02)
  - homepage: https://neptunehub.github.io/AudioMuse-AI/ (fetched 2026-08-29T10:09:39.115173+00:00, sha 168595c4b884)
- Data as of 2026-08-30T08:39:29.467469+00:00.