Selfhosted

This is a Jellyfin problem; not a beets problem. You can easily solve it with beets config if you’d like to, though.

The distinction between what you want vs. what you’re getting is that Jellyfin is grouping by the “Artist” tag instead of the “Album Artist” tag. I haven’t touched Jellyfin in years, but look for a builtin setting or alternative view to group by album artist - you’ll almost certainly find it.

If you want to solve it in beets, you can do that through a custom script, the FtInTitle plugin, or a combo of the inline + advancedrewrite plugins. Remember to run a re-import on the Jellyfin side after making your tweaks to the beets pipeline to make your changes show up without duplication.

I use Lidarr. I know its primary purpose is downloading but if you just never configure those parts, it can do all the renaming, folder organization, and metadata tagging. It uses MusicBrainz primarily, iirc. You can also configure scripts to run it through beets or other tools too.

There's no perfect solution for this because music metadata is a lot more complicated than movies or tv. But Lidarr gets pretty close to set-and-forget.

I've also tried MusicBrainz Picard with pretty decent results but I found it sort of suffered from the problems you described for your current system.

Bro you leaked your ip wtf 🤯🤯😂💣💣🧨✈️

Musicbrainz Picard --> mp3Tag --> MusicBee

• Picard handles the initial tagging.
• mp3Tag handles the clean-up. I like things "just so", and some of the time Picard goes rogue. The Actions function is super powerful for automating "fixing" tags. Oh, and you can cut, filter and paste an entire directory's worth of song tags if you want to bulk remove a bunch of unwanted tags that Picard adds.
• MusicBee is the database. I like the Inbox feature that allows me to do a last check before "promoting" the files to my master library.

There are portable versions of all three, so you can lock a version in your music directory and never worry about updates ruining your tags.

I use picard, which works great, but is by no means automatic. Keep an eye on https://github.com/sentriz/wrtag, I think it’ll be really clean and highly functional in the near future.

I gave up on automating it, I download with slskd, and run musicbrainz Picard (import slskd download folder, and set it to always save to the jellyfin music folder/rename with my preferred sorting method). This has the bonus of downloading the cover art, and rarely has issues.

Use one artist for album artist. For the artist field, look up how to properly split entries. This is different for IDv3 vs Vorbis. Split the artists and Jellyfin will handle it fine.

For music. I use navidrome. It works a load better then jellyfin for this IMO. You can use the same file location for both jellyfin and navidrome if needed.

I too was unsatisfied with jellyfin's music handling. Not only was the website disorganized and bad at using the built-in album art, but all the android music players i could find for it were also barely usable as well.

I can't use musicbee because it's windows only. I still want synchronized play history, metadata updates, and everything between my phone, pc, and mp3 player so a single OS software was out of the question.

I use a combination of beets, navidrome, and tempo. Beets is the metadata manager; once i've beet imported an album, it's ready for navidrome to pick it up and serve it to any of my devices. (I have a custom sync script for my mp3 player that does the same). Navidome serves the music to any connected devices, converts it on the fly to lower quality (for low speed phone network situations) and also keeps track of my play counts, and my playlists for me. It's not nearly as complicated as some of the other setups, which I also prefer.

I use tempo on my phone to connect to navidrome on the go and it has worked out incredibly well so far.

First, I made 'Album Artists' my landing page. 'Artists" includes everyone tagged in the metadata, 'Album Artists' only contains the primary artists. For me, the difference is 350 album artists vs 1412 artists.

I run everything through Picard when I add something to the server. Sometimes I have to change the metadata (for example I hate having an entry for '&' like Elton John & Hans Zimmer and I'll change it so the album is included in both Elton John and Hans Zimmer but theres no entry for them together). But generally it's pretty simple and smooth.

Looks like this:

collapsed inline media

I come back to this problem every year or so because I’m never satisfied with my music metadata. Years ago I had my musicbrainz picard settings dialed in really nicely, where I could drag folder over and it would spit out the right thing like 7 out of 10 times. It still required a lot of doubled checking and manual oversight though, so I was never satisfied.

I tried mediamonkey for a while, because it has decent metadata support and plugs into most of the expected APIs. But when all is said and done, all these tools use the same data sources, and none of them are exactly consistent with each other so matches aren’t as straightforward as they should be.

Lidar never quite did it for me, so I haven’t looked at my install in a couple years. But based on @skoberlink@lemmy.world’s recommendation I’ll try a fresh install and see if get I better results this time. I’m always happy in the arr interfaces.

hello, maybe try wrtag which was written to be a faster version of beets. it handles album artists out of the box (multi valued tags instead of one string with ft. delimiters). it can be configured with the path format syntax to be similar to your current beets config

https://github.com/sentriz/wrtag

Tag them beforehand with Lidarr. Works very well for me.