AudioMuse-AI - Setup Wizard

Configure your media server, authentication and advanced settings.

Music Servers

Connect one or more media servers (Jellyfin, Emby, Navidrome, Lyrion, Plex, even several of the same type). Analysis covers every configured server: the default server runs first, then each remaining server in turn. Songs shared by several servers are recognized by their audio fingerprint and analyzed only once, and songs that exist on just one server are analyzed too, so the catalogue is the union of all your libraries. Alignment sweeps map the shared content across servers as analysis progresses. Use the server switcher at the bottom of the menu to pick which server the interface works against: playlists and searches then target that server, and tracks it does not have are skipped.

Name Type Default Actions

Authentication

Machine Learning Models

Choose the models that run during analysis. Turning a model off also turns off every feature that depends on it: open "What it does" under a model to see which pages use it and why. The small bar under a model shows how much of your library that feature can find right now; it fills up as the analysis runs.

MusiCNN Audio embeddings, mood and genre tags
Always on
Find songs by describing their sound
Find songs by the meaning of their lyrics
Transcribe lyrics when none are found
Identify a song from a recording
Advanced configuration
⚠️ Read the documentation first. These settings tune analysis, clustering and internal behavior. Wrong values can break analysis runs or produce poor playlists. Please review the PARAMETERS documentation on GitHub before changing anything here.
Lyrics API
These are the external APIs used to fetch lyrics before analysis. If no API is configured, or if all configured APIs fail or time out, AudioMuse-AI will fall back to local transcription with Whisper.

Paste a real example URL (with actual artist and track values) including http:// or https:// and click Analyze. AudioMuse-AI will call the URL, detect the parameters automatically, and show the JSON response so you can click the field that contains the lyrics.

API Slot 1

API Slot 2

AI Prompt
Choose how AudioMuse-AI asks your AI provider to name the playlists created by clustering. It is used only when a provider is selected under Advanced configuration → AI Provider & Playlist Naming.

Clustering Naming

The AI picks one word from the mood and lyrics of each playlist and AudioMuse-AI adds the genre, for example "Joyful Soul". This style has no prompt to edit.

Runs one quick K-Means clustering on up to 10000 of your songs and names every playlist with the selected naming style. Nothing is saved. It runs like any batch task, so it cannot start while another task is running.