Chaphasilor [he/him]

OpenRouter is like a market place for AI model providers. So other companies can offer access to AI models through their servers, and OpenRouter will expose them to you via a unified interface. When you send a request to a certain AI model, OpenRouter forwards that request to the currently cheapest provider that’s available.

So it helps you get easy access to thousands of models for a competitive price, without having to pay tens of different providers and figuring out which is cheapest and such. It’s a convenience thing, mostly.

what the fuck

Wow, they’re not holding back!

And Bandcamp officially supporting OpenSubsonic clients wasn’t on my bingo card for sure!

So to answer your question: OpenSubsonic is only for music, and Jellyfin does much more than music. Adopting OpenSubsonic would mean maintaining two APIs, which doesn’t make a lot of sense.

Meanwhile Navidrome is adding Jellyfin API compatibility to get access to more clients :P

Why would you host it? I just downloaded the zip archive a while ago to have a backup in case the service goes down, but I don’t really know any lrclib integration that supports providing a custom API URL anyway.

You should try the beta, if you haven’t yet!

Not a fan of a tag, since it’s not transparent enough. Sounds like every minor use of AI would warrant a tag, which seems past the point.

The disclosure comment I feel works well. People that care about if/how AI was used can check it to get a proper impression of the scale of and workflow for AI usage, and those who don’t care can ignore it.

A soft fork of forgejo*

Don’t listen to MJ Rathbun here