Freedom251 › AI Music Playlist Generators

PlexMix

Paid LinuxSelf-hostedWeb

What PlexMix is

PlexMix builds personalized playlists from a Plex music library using natural-language mood descriptions and detailed track controls. It syncs Plex metadata into a local SQLite database and generates semantic embeddings for track search. Playlist filters can narrow results by genre, year, rating, artist, environment, instrument, tempo, energy, key, or danceability. Tracks can then be ordered by similarity, randomly, by alternating artists, or along an energy curve.

The project offers a command-line interface and an alpha web UI, and recommends the CLI for production use. It can be installed from PyPI or run through Docker Compose, with prebuilt amd64 and arm64 images described in its README. Optional Essentia analysis can extract tempo, key, energy, danceability, and loudness; optional MusicBrainz enrichment can add community-curated genres, canonical artist IDs, and recording-type detection. Playlists can be imported from files with track matching or exported as JSON or M3U. PlexMix can create Plex playlists when enabled, and says it does not change or delete tracks, albums, or artists. It is licensed under GNU AGPL v3. Local models support offline playlist and tag generation, while cloud AI providers need an API key and internet access.

Who it suits

PlexMix is for music lovers who manage a Plex library and want playlists shaped by natural-language requests and track filters. It may also suit people who prefer local models or want to run an open-source project themselves.

What it does well

Creates playlists from natural-language mood descriptions.
Offers filters for genre, year, artist, tempo, energy, and more.
Includes four track ordering modes.
Supports JSON and M3U playlist import and export.
Local embedding models can run offline and privately.
Licensed under GNU AGPL v3.

What to know first

Currently supports one music library at a time.
The web UI is alpha; the project recommends CLI use for production.
Cloud AI providers require an API key and internet access.

Limits

The project currently supports one music library at a time. The web interface is alpha, and the README recommends the CLI for production use.

Getting started

Visit the PlexMix project on GitHub.
Install from PyPI or run it with Docker Compose.
Connect to Plex and sync music metadata to the local database.
Choose a cloud AI provider with an API key or configure a documented local model.
Generate a playlist with a prompt and filters, then export it or create a Plex playlist when enabled.

Verdict

Choose PlexMix if you want to generate and shape playlists from a Plex library with natural-language prompts, filters, and multiple ordering modes. Look elsewhere if you need multiple music libraries at once or a production-ready web interface; the project recommends its CLI for production.

Questions

Is PlexMix free and open source?

Yes. It is listed as free and licensed under GNU AGPL v3.

What platforms does it support?

The listed platforms are Linux, self-hosted, and web. It can be installed from PyPI or run with Docker Compose.

Which AI providers can PlexMix use?

It supports Google Gemini, OpenAI GPT, Anthropic Claude, Cohere Command, local Gemma and Mistral models, and OpenAI-compatible local endpoints.

Can it work offline?

The README documents local models for offline playlist and tag generation, and says local embedding calls run offline and privately. Cloud AI providers need an API key and internet access.

Does PlexMix modify my Plex music files?

It can create Plex playlists when enabled. It says it does not modify or delete tracks, albums, or artists.

What is the cost of using its AI features?

The README estimates default Gemini playlist creation at ~$0.01 per playlist and says local embeddings are completely free.

Facts from PlexMix's own pages

AI providers: Supported providers include Google Gemini, OpenAI, Anthropic, Cohere, local models, and OpenAI-compatible endpoints. · github.com, 9 Oct 2026
Audio analysis: Optional Essentia analysis extracts features including tempo, key, energy, danceability, loudness, and spectral measures. · github.com, 9 Oct 2026
Cost note: The README estimates default Gemini playlist creation at ~$0.01 per playlist and local embeddings as completely free. · github.com, 9 Oct 2026
Credential storage: Credentials can be stored in the system keyring or passed as environment variables. · github.com, 8 Oct 2026
Deployment: The project can be installed from PyPI or source and deployed with Docker Compose; it publishes amd64 and arm64 Docker images. · github.com, 9 Oct 2026
Export and import: Playlists can be exported as JSON or M3U and imported from files with track matching. · github.com, 8 Oct 2026
Interfaces: PlexMix provides a command-line interface and an alpha web UI; the README recommends the CLI for production use. · github.com, 8 Oct 2026
Library limit: The README says PlexMix currently supports one music library at a time; multi-library support is on its roadmap. · github.com, 9 Oct 2026
License: The project is licensed under the GNU Affero General Public License v3.0. · github.com, 9 Oct 2026
License and audience: The project is licensed under GNU AGPL v3 and describes itself as made for music lovers. · github.com, 8 Oct 2026
Local library data: It syncs Plex music metadata to a local SQLite database and generates semantic embeddings for tracks. · github.com, 8 Oct 2026
Local storage: It syncs Plex music metadata to a local SQLite database and stores semantic embeddings for search. · github.com, 9 Oct 2026
Music metadata: Optional MusicBrainz enrichment provides community-curated genres, canonical artist IDs, and recording type detection. · github.com, 9 Oct 2026
Network requirements: Cloud AI providers require an API key and internet access, while the README documents local models for offline playlist and tag generation. · github.com, 9 Oct 2026
Ordering: It offers similarity, random, alternating-artist, and energy-curve track ordering modes. · github.com, 8 Oct 2026
Playlist controls: Playlist generation supports filters including genre, year, rating, artist, environment, instrument, tempo, energy, key, and danceability. · github.com, 8 Oct 2026
Playlist tools: Playlist generation supports filters, four ordering modes, saved templates, and JSON or M3U import and export. · github.com, 9 Oct 2026
Plex access: PlexMix reads Plex metadata and can create Plex playlists when enabled; it says it does not modify or delete tracks, albums, or artists. · github.com, 9 Oct 2026
Privacy option: Local embedding models run on the user's machine, and the README says their embedding calls run offline and privately. · github.com, 9 Oct 2026
Purpose: PlexMix creates AI-generated playlists from a user's Plex music library using mood descriptions. · github.com, 9 Oct 2026
Security: The web UI can be password-protected with PLEXMIX_UI_PASSWORD, which the README recommends when exposing it on a network. · github.com, 8 Oct 2026
Web interface: The README describes the web UI as Alpha and recommends the CLI for production use. · github.com, 9 Oct 2026

Where PlexMix stands on Freedom251

AI Music Playlist Generators#22 of 23