---
title: "Deploy AudioMuse-AI"
description: "AI sonic analysis & smart playlists for Navidrome, Jellyfin, Plex, Emby"
category: "AI/ML"
url: https://railway.com/deploy/audiomuse-ai
---

# Deploy AudioMuse-AI

AI sonic analysis & smart playlists for Navidrome, Jellyfin, Plex, Emby

**[Deploy AudioMuse-AI on Railway](https://railway.com/template/audiomuse-ai)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/audiomuse-ai/manifest.json

- **Creator:** My Projects
- **Category:** AI/ML

## Template content

### audiomuse-worker https://raw.githubusercontent.com/NeptuneHub/AudioMuse-AI/main/native-build/macos/assets/menubar-icon.svg

- **Image:** ghcr.io/neptunehub/audiomuse-ai:latest

### Postgres https://devicons.railway.app/i/postgresql.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:18

### audiomuse https://raw.githubusercontent.com/NeptuneHub/AudioMuse-AI/main/native-build/macos/assets/menubar-icon.svg

- **Image:** ghcr.io/neptunehub/audiomuse-ai:latest
- **Public domain:** Yes

## Documentation

# Deploy and Host AudioMuse-AI on Railway

[AudioMuse-AI](https://github.com/NeptuneHub/AudioMuse-AI) brings AI-powered sonic analysis to your self-hosted music library. It analyzes every track's audio (tempo, key, mood, energy, embeddings) and uses it to generate smart playlists, "instant mix" song paths, similar-song search, clustering and natural-language playlist creation — for **Navidrome, Jellyfin, Emby, Plex, LMS and Lyrion**, even several servers at once.

## About Hosting AudioMuse-AI

This template mirrors the official Docker Compose deployment:

| Service | Purpose |
|---|---|
| **audiomuse** | Flask web UI + API (`SERVICE_TYPE=flask`), public HTTPS domain |
| **audiomuse-worker** | Background analysis / clustering queue workers (`SERVICE_TYPE=worker`) |
| **Postgres** | Stores analysis results, configuration and users |

Both app services use the official `ghcr.io/neptunehub/audiomuse-ai` image and connect to Postgres over Railway's private network. Authentication is on by default; a random admin password, JWT secret and API token are generated for every deployment.

**After deploy — do this right away:**
1. Open the **audiomuse** domain. On a fresh install the **Setup Wizard** opens.
2. Connect your media server (URL + credentials/API token) and finish the wizard. Until a media server is configured the wizard is reachable without login, so complete it immediately.
3. Log in as `admin` with the password from the audiomuse service's `AUDIOMUSE_PASSWORD` variable.
4. Start an analysis, then explore playlists, Instant Mix and similar-song search.

## Common Use Cases

- Automatic mood/energy-based playlists for Navidrome or Jellyfin
- "Song path" mixes that smoothly transition between two tracks
- Similar-song and natural-language search over your own library
- Feeding AudioMuse plugins for Navidrome, Jellyfin and other clients via the API token

## Dependencies for AudioMuse-AI Hosting

- A reachable media server (Navidrome, Jellyfin, Emby, Plex, LMS or Lyrion)
- PostgreSQL (included)

### Deployment Dependencies

- Source: https://github.com/NeptuneHub/AudioMuse-AI
- Docs: https://github.com/NeptuneHub/AudioMuse-AI/tree/main/docs

### Implementation Details

Audio analysis is CPU-heavy. The project recommends ~8 GB RAM and 4 vCPUs for large libraries; scale the **audiomuse-worker** service's resources (or replicas) in Railway to speed up analysis. Plugins that call the API use `Authorization: Bearer` with the `API_TOKEN` value.

## Why Deploy AudioMuse-AI on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying AudioMuse-AI on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/audiomuse-ai