This post is mostly just me bitching about the music industry but also genuine interest in what other people in this community do when it comes to music streaming. Apologies if this is an incomprehensible wall of text.

---

My favorite self-hosted project is Navidrome. I've been running it for years and it's been absolutely perfect the entire time. Related clients like Supersonic and Tempo have been fantastic as well. More than half of my donations to open source software have been to music related projects like these, I use them for multiple hours every day.

I'm giving up on using them though, because actually obtaining the music to stream has become harder and more expensive every year. Unlike self-hosted movie/tv streaming, the primary reason I self-host music is to support the artists. I feel better paying $10 for an album I enjoy compared to the artist getting pennies from me streaming it. I'm sure as hell not doing this to save money, I spend around $30/month on average on new music.

My only criteria for buying music is that it's at least CD-quality. Going back a few years, my options (ordered by preference at the time) were Bandcamp, Qobuz, 7Digital, the artist's own website, physical CDs that I'd rip myself, then finally giving up and using Soulseek. Bandcamp and Qobuz would typically cover 95% of what I was looking for, I'd rarely need to use Soulseek.

But over the course of those past few years...

Bandcamp was bought by Epic, then sold to Songtradr, half of its staff were laid off, and it's been a shell of its former self ever since. It seems like Bandcamp is now mostly ignored by artists, with albums rarely releasing or releasing far later than other platforms. It's genuinely a surprise when I find the artist or album I'm looking for on Bandcamp at this point.

Qobuz has been experiencing rapid enshittification as they try to get people to subscribe to their streaming service. Dark patterns added throughout the purchase and download process, albums being pulled from my account, and albums becoming more expensive (I'm seeing a whole lot more $15-$20 albums than $10 albums now).

7Digital is dead.

Artist websites rarely offer lossless downloads anymore. Last time I bought an album directly from an artist was Madeon in 2019, and that's now an archived page you have to go out of your way to find.

CDs are somehow still a reliable option, but I just cannot justify this anymore. At some point having a collection of 250 plastic discs that I rip precisely once and then store forever just doesn't make sense. I'm tired of buying physical clutter to get digital files. I sold a sizable chunk of my collection a few months ago.

Soulseek, the "fuck it I'm pirating it" option whenever I can't buy an album through any available means. Surprisingly even Soulseek seems to be suffering, I used to be able to find anything, but now even a slightly obscure release can be hard to find.

So now, my preferred options are Bandcamp, Qobuz if the album is less than $15, then Soulseek. I'm using Soulseek a hell of a lot more now, which defeats the point of why I do this in the first place. So fuck it, I subscribed to Tidal.

But like, what the fuck? Why is it so hard to give artists more money?

---

So, for others who self-host their music collection, or even still rock an iPod or something, what do you do? Do you buy lossy releases? Do you pirate everything? Is there a magical website that has every album for sale that I just don't know about? CDs? I can't be the only one with this problem, but I haven't seen anyone else talk about it.

I'm not the developer, but I thought I'd share this with the community. A pretty cool tool which reads Lidarr data and asks Spotify's API to return artist recommendations based on that data.

I have an old ThinkPad 11e running Debian that I have repurposed into a home server. It's only supposed to run TVheadend. I don't need any other services for now, but later on i might add a few uding docker.

Is it enough to set multiuser.target as default to disable gui and keep the system always on?

How can I disable all unnecessary services and minimize power usage?

I often see people mention the Portainer project and how it's useful, but I never hear any reason to use it other than as a more user friendly front end to service management.

So is there any particular feature or reason to use portainer over docker's CLI? Or is it simply a method of convenience?

This isn't only strictly for self hosting, but I figure people here would know better.

A while ago, I had requested help with using LLMs to manage all my teaching notes. I have since installed Ollama and been playing with it to get a feel for the setup.

I was also suggested the use of RAG (Retrieval Augmented Generation ) and CA (cognitive architecture). However, I am unclear on good self hosted options for these two tasks. Could you please suggest a few?

For example, I tried ragflow.io and installed it on my system, but it seems I need to setup an account with a username and password to use it. It remains unclear if I can use the system offline like the base ollama model, and that information won't be sent from my computer system.

At the moment I have my NAS setup as a Proxmox VM with a hardware RAID card handling 6 2TB disks. My VMs are running on NVMEs with the NAS VM handling the data storage with the RAIDed volume passed through to the VM direct in Proxmox. I am running it as a large ext4 partition. Mostly photos, personal docs and a few films. Only I really use it. My desktop and laptop mount it over NFS. I have restic backups running weekly to two external HDDs. It all works pretty well and has for years.

I am now getting ZFS curious. I know I'll need to IT flash the HBA, or get another. I'm guessing it's best to create the zpool in Proxmox and pass that through to the NAS VM? Or would it be better to pass the individual disks through to the VM and manage the zpool from there?

I’ve set up subnet routing via Tailscale from my Oracle VPS to my home RPi4. The VPS has a static IPv4 and a /64 IPv6 allocation. I use the VPS to reverse traffic apps on the raspberry using nginx. I would like to take one step forward by tunneling v6 traffic from my home network to WAN, so every client gets its own IPv6 address. What's the best way to tunnel IPv6 traffic from my home network through the RPi4 to the Oracle VPS? I’m also comfortable with messing up my Asus AC86U router to provide publicly routable IPv6 addresses to all clients via DHCP.

Hey guys. I’ve been considering maybe moving to another OS for my home lab. Do you have have any suggestions? Especially former Unraid users? Mostly just for arrs though I would like to run reverse proxy/file hosting as well. Proxmox seems pretty trendy can I use it for arrs as well as backups?

Rant/extra info:

Tap for spoiler

I’ve been using Unraid for a couple years now, even paid for basic registration. I’ve largely used it to run all my arrs in docker, pihole and had a HASSIO VM running.

I recently tried setting up nextcloud, during the set up (which like nearly everything, I followed a video guide for) I ran into a novel error. So I deleted the nextcloud docker and got it from the official repo instead. Now my nextcloud share is gone and I can’t create new shares??

Stuff like this happened when I set up guac. Weird errors, plenty of which have little documentation or explanation. Plenty of which I need to ssh in or use Linux commands to fix. Which lead me to, “I’m having to learn this stuff anyway, why not spin up a Linux server and learn properly”.

Should I just rebuild/give Unraid a bit more time, it is young OS wise right?

Hey there!

I'm thinking about starting a blog about privacy guides, security, self-hosting, and other shenanigans, just for my own pleasure. I have my own server running Unraid and have been looking at self-hosting Ghost as the blog platform. However, I am wondering how "safe" it is to use one's own homelab for this. If you have any experience regarding this topic, I would gladly appreciate some tips.

I understand that it's relatively cheap to get a VPS, and that is always an option, but it is always more fun to self-host on one's own bare metal! :)

I know this is more hardware related, so please let me know if I should move this post elsewhere.

I built my first server earlier this year, and put buying a UPS on the back burner. Unfortunately for me, this might have already been my biggest mistake since going down this rabbit hole. The rental I’ll be in for at least another 10 months has some questionable wiring (a lot of rooms/outlets wired to the same breaker), which I believe has created some electrical anomalies and possibly killed some of my computer components. The memory on my PC went first, and now the 7-month-old PSU on my server is toast.

Bear in mind, I am not an electrician, so I could be entirely wrong on why this has happened. Regardless, it's time I invest in a UPS. I have searched forums, blogs, YouTube, and cannot find consistent pros and cons for any of the big manufacturers. It seems like APC and CyberPower are the two big consumer grade manufacturers, which is probably what I should be looking at.

Here is what my server currently consists of:

Type|Item|Notes :----|:----|:---- CPU | Intel Core i3-10100 | CPU Cooler | Thermalright Peerless Assassin | Motherboard | MSI MAG B560M | Memory | Corsair Vengeance LPX 32 GB (2 x 16 GB) DDR4-2666 CL16 Memory | Storage | Crucial P3 1 TB NVME SSD | X2 Storage | Hitachi Ultrastar He12 12 TB HDD | Storage | Western Digital Ultrastar DC HC520 12 TB HDD | X2 Case | Fractal Design Define 7 | Power Supply | be quiet! Pure Power 12 M 550 | Replacement until I finish the RMA process on the dead power supply. OS | Unraid | Estimated Wattage | 238W | I have not tested this personally, but I will say the server is never really being stressed all that much.

Any recommendations would be greatly appreciated!

I want to selfhost my own personal website. This is just for fun, as a hobby and to show off my skills to others. nothing big.

I have my own server home but I want to have something that's separate from my personal stuff.

I do not need any support, meaning it can be as cheap as possible. I do not yet know how much RAM or CPU or storage I need. I guess CPU > 2GHz and 2GB RAM should be enough to start.

daily/weekly backup with rsync in case the hoster goes out of business.

I do not need a domain, I will use a dynamic dns hoster.

Last June, fans of Comedy Central – the long-running channel behind beloved programmes such as The Daily Show and South Park – received an unwelcome surprise. Paramount Global, Comedy Central’s parent company, unceremoniously purged the vast repository of video content on the channel’s website, which dated back to the late 1990s.

I’m happily serving a few websites and services publicly. Now I would like to host my Navidrome server, but keep the contents private on the web to stay out of trouble. I’m afraid that when I install a reverse proxy, it’ll take my other stuff online offline and causes me various headaches that I’m not really in the headspace for at the moment. Is there a safe way to go about doing this selectively?

cross-posted from: https://lemmy.ca/post/30126699

> I created this guide on how to install Jellyfin as a Podman Quadlet on your server. Enjoy.

I'm afraid this is going to attract the "why use podman when docker exists"-folks, so let me put this under the supposition that you're already sold on (considering) using podman for whatever reason. (For me, it has been the existence of pods, to be used in situations where pods make sense, but in a non-redundant, single-node setup.)

Now, I was trying to understand the purpose of quadlets and, frankly, I don't get it. It seems to me that as soon as I want a pod with more than one container, what I'll be writing is effectively a kubernetes configuration plus some systemd unit-like file, whereas with podman compose I just have the (arguably) simpler compose file and a systemd file (which works for all pod setups).

I would get that it's sort of simpler, more streamlined and possibly more stable using quadlets to let systemd manage single containers instead of putting podman run commands in systemd service files. Is that all there is to it, or do people utilise quadlets as a kind of lightweight almost-kubernetes distro which leverages systemd in a supposedly reasonable way? (Why would you want to do that if lightweight, fully compliant kubernetes distros are a thing, nowadays?)

Am I missing or misunderstanding something?

I would like to make some of my self-hosted services externally accessible. Currently I use a VPN to access stuff externally, however this doesn't work on all use-cases. I also use Tailscale for some things.

I would love to use cloudflare tunnels and another auth solution (like keycloak) to replace Tailscale and the VPN.

Is this feasible?

My end goal would be to setup Immich for my family, and have them not have to worry about Tailscale, a VPN or anything other than some initial login to keycloak (for example)

So, I'm trying to set up gluetun. I linked a Firefox container to it and apparently every check of DNS leaks shows that it's leaking. Cloudflare and quad9 are the servers, the same names that I've set to dot providers. So I am gathering from all of this that these leaks are to be expected? And non of the DNS servers show my real IP, always one of mullvad IPS. Am I getting this right?

The problem:

I manage computers for some loved ones from whom I now live several states away. All devices are linux environments and basically serve as home theater and light duty SOHO.

They have been running for several years without incident, but do require intervention for the "hard" stuff like major release upgrades. (And perhaps I like to slip some entertainment media onto their shared drive from time to time).

And I'd like to have an avenue to do this that doesn't necessarily involve planning a road trip.

Candidate solution(s):

Deploy a micro PC to sit on their network, whose sole purpose is as a headless SSH server. I would intend to SSH into that device, and from there SSH across the LAN to the necessary computers. The rationale is that I would only have one device answering the door, so to speak, at port 22, greatly simplifying port forwards and any need for static IPs.

With dual stack IPv4 + IPv6 internet service, would it be better that I attempt this through IPv6?

The micro PC would be scripted to retrieve the current public IP address every X hours and email it to me.

Another idea is to configure the immediate SSH box behind a Tor SSH hidden service or a I2P eepsite SSH. This way it would maintain a persistent, reachable address without requiring some cobbled together script & email IP notification.

Over time I've been on the lookout for social media for family to use. I haven't really found anything suitable, key thing is that posting photos and videos needs to be user friendly. For example, Friendica all but requiring you to upload your video to YouTube and post the embedded video is just not gonna fly.

I've seen Zusam in the past, which looks like it could become something but I don't think it's ready for me to try to get extended family into. (It's worth mentioning here that certain extended family have shown interest in using something like this)

Recently I've had a look around at some Enterprise social solutions, and have had a play with HumHub. It has a much more familiar look, things are separated into spaces that are similar to Facebook groups, and while media uploads aren't perfect I think they will work well enough.

HumHub has modules, many of which cost a decent amount of money, because they target the enterprise market. However, the community version is open source and the base features and free modules seem to work well.

Does anyone have experience using it? Any warnings I should know about? Any similar software that does a better job?

!

Recently I bought vps which have only ipv6. It's obviously that I don't have ipv6 home. So, here is question: how do you interact with such servers?

This is my guide for generating playlists for your local music library using ListenBrainz and the troi recommendation engine. troi is still being developed and the official documentation isn't great so I figured documenting my process might help others who are interested. I've tried this both with local folders on my Debian server and with my Navidrome library from my Macbook so I will do my best to explain both.

There are a few requirements

1. Your music must be tagged with MusicBrainz. I use beets for this but you can also use the MusicBrainz desktop client.
2. You need a ListenBrainz account. Data can be imported from Last.fm or Libre.fm if you have it.

Install troi

Install troi and nmslib with pip

pip install troi pip install nmslib-metabrainz

If you're on a managed python install use pipx and add the virtual environment to your PATH (don't forget to reload)

pipx install troi pipx inject troi nmslib-metabrainz export PATH="$PATH":"$HOME/.local/bin" source ~/.zshrc

Configure troi

Create a folder for your troi configuration files. I used ~/.config/troi. Create a file config.py in your configuration folder using the example format below. Edit DATABASE_FILE and MUSIC_DIRECTORIES to match your setup.

If you're using a Subsonic library (like Navidrome) you can fill in SUBSONIC_HOST with your instance url, SUBSONIC_USER and SUBSONIC_PASSWORD with your login and SUBSONIC_PORT with 443 (this is the only port that I could get to work with my docker setup)

``` ini

Where to find the database file

If path is passed with -d flag, this list is ignored.

DATABASE_FILE = "/users/sillyhatsonly/.config/troi/troi-db.db"

To connect to a Subsonic API

SUBSONIC_HOST = "https://music.myserver.dev" # include http:// or https:// SUBSONIC_USER = "admin" SUBSONIC_PASSWORD = "thisisnotmypassword" SUBSONIC_PORT = 443

List of music directories to scan by default

If paths are passed to scan command, this list is ignored.

Invalid directories are skipped.

MUSIC_DIRECTORIES = [ 'My/Music/Directory 1', 'My/Music/Directory 2', ] ```

Create your music database

Now create the database, scan the local directories specified in config.py and pull ListenBrainz tag/popularity metadata for all files. If you're using a Subsonic library run troi db subsonic instead of troi db scan

``` bash

create database

troi db create

scan music directories

troi db scan

pull music metadata

troi db metadata ```

Generate playlists

Generate playlists for your local library using ListenBrainz Radio Local. Specify a mode which sets how closely the resulting playlist will meet the prompt (easy/medium/hard from closest to furthest) and an entity reference either artist or tag. More details in the docs: LB Prompt Radio Reference

``` bash

tracks by Thou and similar artists

troi lb-radio easy 'artist:(thou)' -m <playlist-name>.m3u

tracks tagged 'jazz' and tracks tagged 'hip-hop'

troi lb-radio medium 'tag:(jazz)::or tag:(hip-hop)'

tracks tagged both 'indie rock' and 'experimental'

troi lb-radio medium 'tag:(indie rock, experimental)' ```

Another option is to generate weekly recommendations playlists for your ListenBrainz account

``` bash

-m flag saves to the specified m3u playlist

troi weekly-jams <username> -m <playlist-name>.m3u

-u flag uploads the playlist via Subsonic API

troi weekly-jams <username> -u ```

Automate weekly playlists

You can automate weekly playlists with a script. I wrote a script that scans my music directory, removes missing files, generates a playlist, and saves it locally as an m3u

``` bash #!/bin/sh

scan music directory and pull metadata using the database in our troi config folder

troi db scan 'My/Music/Directory 1' -q -d '/users/sillyhatsonly/.config/troi/troi-db.db' troi db metadata 'My/Music/Directory 1' -q -d '/users/sillyhatsonly/.config/troi/troi-db.db'

clean up the database and remove any missing files

troi db cleanup --remove -q -d '/users/sillyhatsonly/.config/troi/troi-db.db'

generate weekly playlist and save locally to m3u

troi weekly-jams <username> -d '/users/sillyhatsonly/.config/troi/troi-db.db' -y -q -m /users/sillyhatsonly/music/playlists/weekly-$(date +%Y%m%d).m3u ```

Then set it up to run weekly as a cron job.

______

That's all I've done so far. Hopefully this makes sense. I welcome comments or questions. If anyone else has been using troi with their local music libraries I'd love to hear about your experience. Playlist generation was the one feature I really missed when I stopped using streaming platforms so I'm excited about this tool!

Background

Hello fellow self-hosters and homelabbers, A few weeks ago I was able to fill my new NAS with the proper hardware I needed to expand on my earlier setup. Due to the new capabilities I also wanted a fresh restart. But the more I think about doing one thing, the more I hit other road blocks amd think about doing Y. So I wanted to ask how you would solve my goal.

My current (main) setup:

• Hardware: 11th Gen i5 Nuc with a 8TB HDD attached via USB
• OS: Debian 11
• Software: OMV6 for management and Docker for a diverse set of containers
• Current containers: HortusFox + MongoDB, *arrs-stack, Jellyfin, uptime kuma, unifi network application + mariaDB, traefik, wallos

Current available hardware for use:

1x 13th gen i3 NUC running Proxmox 8.2 1x 11th gen i5 NUC 1x uGreen DXP4800+ NAS with 4x15TB HDDs in Raidz2. The OS is TrueNAS scale

My plans:

• NAS storage made accessible via NFS to the proxmox VE.
• NAS storage mainly planned as mass-storage for Jellyfin.
• Reimage my 11th gen NUC with a bare-metal Debian install for Docker. (I will not virtualize on the 11th Gen NUC because I can't pass the iGPU to the VM and not really interested in LXC containers)

Problems and questions I have at this moment:

1: Should I do a media-storage VM only utilized for serving media and do the computing on another VM or do a general VM for both?

• Upside to an all-in-one VM: Less problems with serving storage between many different nodes and keeping it organized. Upside to specialized VMs (storage & compute VM): Better focus on ressources like CPU and RAM. 2: Should I place my whole docker stack again on the 11th Gen NUC or place the stacks in their own VM(s)? Example: service stack in service-focused VM media-focused stack in media VM (which also serves the files for jellyfin) Jellyfin bare-metal/dockerized on NUC 11th Gen

I hope someone can maybe help me untangle my grown mess and plans. My skills with Linux are not very deep and very beginner level. If you are willing to help please be patient with stupid questions.

If you have any better solutions, pointers to research, (blog) articles on architecting such solutions, examples how you solved storage/management or just willing to help me, I'd be very grateful :)

Hi folks,

Just set up Nginx Proxy Manager + Pihole and a new domain with Porkbun. All is working and I have all my services service.mydomain.com, however some services such as pihole seem to be strictly reachable with /admin at the end. This means with my current setup it only directs me to pihole.mydomain.com which leads to a 403 Forbidden.

This is what I have tried, but with no prevail. Not really getting the hang of this so would really appriciate a pinpoint on this :)

!

Hello everyone! I was thinking about starting a website where to dump some guides on stuff Iearn about selfhosting and general IT stuff.

I don't want a WordPress or similar. I want static pages (but I'm ok with some JavaScript for navigation maybe, or for proper display on different kind of devices). Ideally I'd like to host it on an AWS S3 bucket since it has the built-in option for static hosting.

I could even go back to the '90s and do it myself from scratch in textedit and html by hand, but I'm pretty sure there are better options out there.

I took a look at Hugo but even that it seems overly complicated for what I need.

Any ideas or suggestions?

Thanks!

Hi. I've installed Filestash in a Docker container, which included passing a previously generated Dropbox access token to Filestash, as per the yaml file on the gihub page.

• DROPBOX_CLIENT_ID=<dropbox_key>

When I connect to Filestash (just set up locally for now), and then click to connect to Dropbox, I get the following error from the Dropbox webpage that opens:

**Error (400) It seems the app you were using submitted a bad request. If you would like to report this error to the app's developer, include the information below.

More details for developers

Invalid client_id: <same dropbox key as above>.**

There's nothing that looks like an error in the Filestash logs. I've generated new tokens and tried again, same result.

Has anyone managed to add Dropbox to Filestash, and if so, would you mind explaining the steps you took?

(I've since set it up for external access via my domain, and npm, same error).

Thanks Rob

In the last couple of weeks, I've started getting this error ~1/5 times when I try to open one of my own locally hosted services.

!

I've never used ECH, and have always explicitly restricted nginx to TLS1.2 which doesn't support it. Why am I suddenly getting this, why is it randomly erroring, then working just fine again 2min later, and how can I prevent it altogether? Is anyone else experiencing this?

I'm primarily noticing it with Ombi. I'm also mainly using Chrome Android for this. But, checking just now; DuckDuckGo loads the page just fine everytime, and Firefox is flat out refusing to load it at all.

! Firefox refuses to show the cert it claims is invalid, and 'accept and continue' just re-loads this error page. Chrome will show the cert; and it's the correct, valid cert from LE.

There's 20+ services going through the same nginx proxy, all using the same wildcard cert and identical ssl configurations; but Ombi is the only one suddenly giving me this issue regularly.

The vast majority of my services are accessed via lan/vpn; I don't need or want ECH, though I'd like to keep a basic https setup at least.

Solution: replace local A/AAAA records with a CNAME record pointing to a local only domain with its own local A/AAAA records. See below comments for clarification.

Is anyone using dockge?

I used it for a bit and found it very intuitive but checking their github makes me wonder if it is still developed? Last commit was five months ago.

Hello there,

I'm looking for a self-hosted rental system. It's for a smaller institution, which is renting out hardware (for free and non-commercial use), and the current system (EasyJob) is way too bloated.

The service should be publishable to the internet, ideally hostable via Docker or a ProxMox VM, and should have a user-management.

I was thinking about using something like an e-commerce service?

Do you have a good idea regarding this topic?

Best regards

Any recommendations for a good non-subscription-based alternative? I could setup syncthing for files, and I have URbackup for images, but I always relied on Macrium more than URbackup. What do other people use?

>Why have you removed the one-time license option?

>Many of our home customers' feedback indicated a preference for the certainty provided by an annual plan. The annual plan offers assurance that you always have access to the latest version with innovations such as improvements we’ve made in compression speeds and algorithms. It also ensures you have access to critical updates and are protected against new threats and risks. Lastly, our annual plan ensures you always have access to technical support (one-time licenses only offer 12 months of support).

Who can suggest an ethical SMTP provider for low volume transactional mail? I'm willing to pay up to 2€/month for a few hundred mails per month.

Hello everyone, I have some questions and need food for thought about clamAV. First, do you use it and why ? If yes, how are you running it ? I plan to maybe use it for nextcloud (and *arr stack later)

I'm looking at getting a 10 gigabit network switch. I only have 3 devices that could use that speed right now but I do plan on upgrading things over time.

Any recommendations?

Hey, remember me ?

I posted about some entreprise SSDs here before, and now I made a full blog post about their insides! With even more pictures!

I hope you enjoy it :)

I want to be able to access (watch and record) a couple of FTA tv channels on several devices on my LAN.

I already have a couple of USB tuners so I don't want to spend money on HDHomerun.

I did some research and most people recommended TVheadend.

I've also stumbled upon minisatip but there is almost no documentation for it.

Any recommendations?