**Your whole music library, taken apart and put back together however you like.**
Stemify splits every song in your Plex music library into stems (vocals, drums, bass, guitar, piano and other) and gives you players that mix them live. Mute the vocals and sing along, solo the bass to learn a part, or save an instrumental of a song and have it play that way every time.
Ever wanted to hear "Carry On Wayward Son" without the vocals so you can belt it out yourself? Or
It runs on iPhone (with CarPlay), Android (with Android Auto) and Linux desktop. A GPU on your server does the separating in the background.
mute the drums on a song to figure out what the bass player is actually doing back there? Stemify
splits every song in your library into its separate parts (vocals, drums, bass, guitar, piano and
"other"), keeps them organised next to your music, and gives you players that let you mix them
live, on your phone, in your car, and on your desktop.
It's a home-grown, slightly over-engineered love letter to karaoke, music nerdery and the joy of
- [How it works](#how-it-works)
pressing the "mute vocals" button at exactly the wrong moment.
- [Apps](#apps)
- [Setup](#setup)
---
- [iOS](#ios)
- [Android](#android)
## Contents
- [Desktop](#desktop)
- [Stem Now](#stem-now)
- [The big picture](#the-big-picture)
- [Reference](#reference)
- [What you get](#what-you-get)
- [Setting it up](#setting-it-up)
- [1. The server: stemd and stemserve](#1-the-server-stemd-and-stemserve)
- [2. The Android app](#2-the-android-app)
- [3. The desktop apps (optional)](#3-the-desktop-apps-optional)
- [Using the Android app](#using-the-android-app)
- [Stem Now: skipping the line](#stem-now-skipping-the-line)
- [The Equalizer](#the-equalizer)
- [Android Auto](#android-auto)
- [iOS and CarPlay](#ios-and-carplay)
- [The desktop apps](#the-desktop-apps)
- [Separation models](#separation-models)
- [How the pieces find each other](#how-the-pieces-find-each-other)
- [stemserve API](#stemserve-api)
- [Building and testing](#building-and-testing)
- [Building and testing](#building-and-testing)
- [Repo tour](#repo-tour)
- [Troubleshooting](#troubleshooting)
- [Troubleshooting and FAQ](#troubleshooting-and-faq)
- [Credits and license](#credits)
- [Credits](#credits)
- [License](#license)
---
## How it works
## The big picture
The stems folder mirrors the music folder. If a song lives at `Kansas/Leftoverture/01 Carry On.flac`, its stems live in `Stems/Kansas/Leftoverture/01 Carry On/`.
There are three moving parts, and they all agree on one simple idea: **the stems folder mirrors
the music folder.** If your song lives at `Kansas/Leftoverture/01 Carry On.flac`, its stems live at
`Stems/Kansas/Leftoverture/01 Carry On/`. That's it. That's the whole trick.
```
```
┌──────────────────────────── your server (unraid, in our case) ───────────────────────────┐
Mix presets are Full, Karaoke, A Cappella, No Drums, Rhythm, No Guitar and No Bass.
- A Plex music player with per-stem faders, mute and solo, and one-tap mixes: Full, Karaoke,
A Cappella, No Drums, Rhythm, No Guitar, No Bass.
- A Plexamp-style waveform seek bar that doubles as a volume control (drag sideways to seek, up and
down for volume). The waveform is scaled to each song, so you can actually see the quiet verse
and the big chorus.
- Live level meters for every stem, updated every frame and in sync with what you hear.
- A 10-band graphic EQ **plus** Equalizer APO-style parametric filters, with per-device profiles
that switch automatically when you plug in headphones or connect to Bluetooth.
- Paste in an AutoEQ correction for your headphones and you're done.
- Downloads for offline listening, stems and all.
- Gapless playback, a proper queue, playlists (create, reorder, rename), search, and "On This
Day" album birthdays on the home screen.
- "Stem Now": jump any song, album, artist or playlist to the front of the separation queue.
- An iOS-flavoured look in Black, Dark or White, at whatever refresh rate your panel can manage.
**In your car (Android Auto)**
## Setup
- A browse tree built for a rotary knob and no touchscreen, with voice search, a Vocals on/off
button and a Mix button right next to play/pause.
**On your desktop (Linux)**
Set up the server first, then the apps. The examples use Unraid paths and `192.168.86.2` for the server; use your own.
- **Stemify (the separator)**: drag a song onto the window, get stems out the other side, preview them in sync,
export them. Material layout meets Windows 7 Aero glass, running at 240 Hz because why not.
- **Stemify Player**: your Plex library and its stems, with full mixing... dressed up as
Microsoft Excel 2016. Yes, really. Your boss will think you're working on the quarterly numbers.
**On the server**
### Server
- **stemd** separates everything automatically with BS-RoFormer SW (6 stems) on an NVIDIA GPU,
politely, at low priority, sharing the card with Plex transcodes.
- **stemserve** is one Python file using only the standard library. ffmpeg is optional.
---
You need Docker, and an NVIDIA GPU for stemd (on Unraid, install the Nvidia-Driver plugin). A CPU build exists for testing, but it's far too slow for a whole library.
## Setting it up
Make the folders, owned by `99:100` (Unraid's nobody:users):
The recommended order is server first, then phone, then (if you like) desktop. The examples below
use unraid paths and the addresses from the original setup (`192.168.86.2`). Swap in your own.
### 1. The server: stemd and stemserve
You need Docker, and for stemd an NVIDIA GPU (on unraid, install the **Nvidia-Driver** plugin from
the Apps tab). A CPU-only build exists for testing, but separating a whole library on a CPU is a
good way to celebrate several birthdays while you wait.
**Folders first** (owned by `99:100`, unraid's nobody:users):
**stemd** builds from the repo root because it borrows the `stemify` package. Copy the repo (or
**stemd** builds from the repo root because it uses the `stemify` package. Copy the repo (at least `stemify/`, `server/` and `.dockerignore`) to `/mnt/user/appdata/stemd/src`, then:
at least `stemify/`, `server/` and `.dockerignore`) to `/mnt/user/appdata/stemd/src`, then:
The first song downloads the model (about 700 MB). After that the log reads like a very calm
The first song downloads the model (about 700 MB). After that the log shows what's left, what it's on, and how fast it's going.
sports commentary: how many tracks are left, which one it's on, and how many times faster than
realtime it went.
**stemserve** is tiny. Copy the `server/` folder to `/mnt/user/appdata/stemserve` and either use
**stemserve** is one Python file using only the standard library. Copy `server/` to `/mnt/user/appdata/stemserve` and run `docker compose up -d --build` there, or by hand:
the included compose file:
```sh
cd /mnt/user/appdata/stemserve && docker compose up -d --build
`curl http://192.168.86.2:8765/api/info` should return JSON with a track count.
```sh
To update, copy the new files, rebuild, `docker rm -f` the container and run it again. Everything that matters lives in the mounted folders. Update stemd before stemserve.
curl http://192.168.86.2:8765/api/info
```
If you see a happy little JSON blob with a track count, you're in business.
| `QUEUE_DIR` | `STATE_DIR/queue` | Where Stem Now requests arrive |
| `MODELS_DIR` | `/models` | Model weights, downloaded on first use |
| `MODELS_DIR` | `/models` | Model weights, downloaded on first use |
| `MODEL` | `roformer_bs_sw` | Any model id from [the table below](#separation-models) |
| `MODEL` | `roformer_bs_sw` | Any id from [the model table](#separation-models) |
| `DEVICE` | `cuda` | `cuda`, `cuda:N` or `cpu` |
| `DEVICE` | `cuda` | `cuda`, `cuda:N` or `cpu` |
| `RESCAN_MIN` | `30` | Minutes between library scans once it's caught up |
| `RESCAN_MIN` | `30` | Minutes between library scans once caught up |
| `FP16` | `1` | Half precision on the GPU (`0` for full fp32) |
| `FP16` | `1` | Half precision on the GPU (`0` for fp32) |
| `OVERLAP`, `SEGMENT`, `SHIFTS` | `0.25`, `0`, `0` | Separation quality knobs, same as the desktop app |
| `OVERLAP`, `SEGMENT`, `SHIFTS` | `0.25`, `0`, `0` | Separation quality, same as the desktop app |
`docker build --build-arg TORCH_INDEX=cpu ...` makes a small GPU-less image for testing.
`docker build --build-arg TORCH_INDEX=cpu ...` makes a small CPU-only image.
**stemserve**
**stemserve**
| Variable | Default | What it does |
| Variable | Default | What it does |
|---|---|---|
|---|---|---|
| `STEMS_DIR` | `/stems` | The stems folder |
| `STEMS_DIR` | `/stems` | The stems folder |
| `CACHE_DIR` | `/cache` | Opus transcodes and waveforms (safe to delete any time) |
| `CACHE_DIR` | `/cache` | Opus transcodes and waveforms (safe to delete) |
| `QUEUE_DIR` | `/queue` | stemd's "Stem Now" folder, shared with it |
| `QUEUE_DIR` | `/queue` | stemd's Stem Now folder, shared with it |
| `PORT` | `8765` | Listen port |
| `PORT` | `8765` | Listen port |
| `TOKEN` | empty | If set, every request needs`X-Stem-Token` or `?token=` |
| `TOKEN` | empty | If set, requests need `X-Stem-Token` or `?token=` |
| `INDEX_TTL` | `30` | Seconds between rescans of the stems folder |
| `INDEX_TTL` | `30` | Seconds between rescans of the stems folder |
</details>
</details>
**Updating later:** copy the new files over, rebuild the image, `docker rm -f` the container, and
### Connecting an app
run it again. Your stems, models and settings live in the mounted folders, so nothing is lost.
Update stemd before stemserve: if you separated songs before the project was called Stemify,
stemd renames their old done-markers on its first start so nothing gets separated twice.
### 2. The Android app
Every app asks for the same two things:
Built for (and lovingly tested on) a OnePlus 15, but any recent Android phone should be happy.
1.**Plex:** sign in with the 4-character code at [plex.tv/link](https://plex.tv/link) and pick your music library.
2.**Stem server:** in Settings, enter your stemserve address. It should say Online with a song count.
1. Grab `Stemify.apk` from the Releases page, or [build it yourself](#building-and-testing),
The apps check stemserve for newly separated songs every minute, so the library fills in as stemd works.
then sideload it:
```sh
adb install -r Stemify.apk
```
2. Open it and go to **Library → Connect** (or Settings → Plex). Enter the 4-character code at
[plex.tv/link](https://plex.tv/link) and pick your music library.
3. Visit **Settings → Stem Server** and point it at your stemserve. It should say "Online" with a
song count. (The default address is `http://192.168.86.2:8765`, which is almost certainly not
yours.)
The app checks stemserve for freshly separated songs every minute, so your library slowly "lights
## iOS
up" as stemd works through it.
### 3. The desktop apps (optional)
A SwiftUI app for iOS 17 or newer, with CarPlay and Siri ("play Paranoid in Stemify").
Linux, Python 3.12 and [uv](https://docs.astral.sh/uv/). The default setup uses PyTorch for ROCm
### Install
(AMD GPUs, developed on an RX 9070 XT). NVIDIA and CPU work too if you point the torch index
elsewhere in `pyproject.toml`.
```sh
Grab `stemify-<version>.ipa` from [Releases](https://git.iamchrisama.com/cdnutter/stemify/releases) and sideload it with AltStore, SideStore, Sideloadly or Feather. To get updates in AltStore, SideStore or Feather, add this source:
uv sync
uv run stemify # the drag-and-drop separator
```
uv run stemify-player # the Excel-shaped music player
./scripts/install-desktop.sh # adds both to your app grid ("--uninstall" removes them)
```
```
---
CarPlay and Siri need the `carplay-audio` and `siri` entitlements, which a free Apple ID can't sign. On a free sideload the app works on the phone but not in CarPlay or Siri. A paid developer account covers Siri; CarPlay audio also needs Apple to approve the entitlement for your team.
## Using the Android app
### Using it
**Tabs:** Library, Playlists, Search, Downloads and Settings.
- **Mixer:** on Now Playing, under the waveform. Tap **Save** to keep a mix for that song; it comes back every time the song plays.
- **Karaoke:** the mic button mutes vocals on every song and shows synced lyrics from [LRCLIB](https://lrclib.net). Tap a line to jump to it. Vocals can be On, Soft or Off, and Soft has a slider for how quiet.
- **Playlists:** the Playlists tab switches between Plex and Stem.
- Plex playlists sync with Plex and Plexamp.
- Stem playlists stay on the phone, and each song in them has its own mix, so one playlist can hold an instrumental of one song and an a cappella of the next.
- Copy any Plex playlist to a stem playlist from its menu.
- **Add to Playlist:** hold any song, album, artist or playlist. One sheet covers both kinds: pick Plex or Stem, pick the mix for stem playlists, then tap a playlist or make a new one right there.
- **Sorting:** artists, albums, songs and playlists sort like Plexamp. Songs has a shuffle-everything button.
- **Hold anything** for Add to Front or End of Queue, Download, Add to Playlist and Stem Now.
- **Equalizer:** same graphic EQ, parametric filters and APO/AutoEQ import as [Android](#equalizer).
**Stems are the norm, so the exceptions are what's marked.** Songs without stems yet say
## Android
**NO STEMS**, and albums and artists say **NO STEMS** or something like **7/10 STEMS** until
they're done. Those songs still play, just from the original file.
**Hold anything** (a song, album, artist or playlist) for:
Kotlin and Jetpack Compose, built and tested on a OnePlus 15. Grab `Stemify.apk` from Releases (or [build it](#building-and-testing)) and `adb install -r Stemify.apk`.
- **Add to Front of Queue** / **Add to End of Queue**
### Using it
- **Download** (or **Remove Download**)
- **Add to Playlist** (playlists can even go into other playlists)
- **Stem Now**, while any of it lacks stems
**The Now Playing screen** has the waveform seek bar, the mixer (faders, mute, solo, mix presets,
-**Tabs:** Library, Playlists, Search, Downloads and Settings.
meters, master volume) and the queue. Your mix can carry over from song to song or reset each
- **Badges:** songs without stems yet say NO STEMS, and albums and artists show NO STEMS or a count like 7/10 STEMS. They still play from the original file.
time, your choice.
- **Now Playing:** waveform seek bar (drag sideways to seek, up and down for volume), mixer, meters and queue. Your mix can carry over between songs or reset.
- **Stem Quality:** lossless FLAC, or Opus at a bitrate you choose (about an eighth of the size, transcoded and cached on the server).
- **Streaming** needs your home network, since Plex and stemserve are plain HTTP on the LAN. Downloads and already-streamed songs play anywhere.
**Downloads** are proper offline copies: every stem fully fetched (or the original file for songs
### Equalizer
without stems). Sort by download order, artist or release date.
**Stem Quality** decides how stems travel from the server: lossless FLAC, or Opus at a bitrate of
Settings → Equalizer has two parts.
your choosing, which takes roughly an eighth of the space and is transcoded and cached on the
server.
**Streaming** needs your home network (Plex and stemserve are plain HTTP on the LAN). Anything
- **Graphic EQ:** ten bands from 31 Hz to 16 kHz, with presets like Bass Booster, Late Night and Vocal Booster.
you've downloaded or already streamed plays anywhere.
- **Parametric filters**, modeled on [Equalizer APO](https://sourceforge.net/projects/equalizerapo/): Peak, Low/High Shelf, Low/High Pass (6 to 48 dB/oct), Band Pass, Notch and All Pass. Each has frequency, gain and Q, works on both channels or one, and can be toggled on its own. Drag the handle on the curve or tap a value to type it.
---
To correct headphones, copy a `ParametricEQ.txt` from [AutoEQ](https://github.com/jaakkopasanen/AutoEq) and choose **••• → Paste APO Config** on the Filters page. **Copy as APO Config** goes the other way.
## Stem Now: skipping the line
Profiles are tied to outputs (speaker, wired, each Bluetooth device, USB DACs) and switch automatically. Each has its own preamp, and anti-clipping adds just enough cut to keep the loudest point of the curve at 0 dBFS. A limiter on the master bus catches the rest.
stemd works through your library on its own, but a big library takes days. If you're desperate to
### Android Auto
karaoke your way through an album tonight, hold it and choose **Stem Now**.
Here's what happens:
Built for a 2016 Mazda MX-5 with Mazda Connect: 800×480, no touch, knob and wheel buttons only.
1. The app sends the songs that still lack stems to stemserve.
- Tabs for Playlists, Albums, Artists and Downloads (Downloads first when you're away from home).
2. stemserve drops a little request file into stemd's queue folder.
- Every song list starts with Shuffle all, and lists over 40 items split into A to Z folders.
3. stemd finishes the song it's on, then does yours next, ahead of everything else. If it was
- Now Playing has a Vocals on/off button and a Mix button that cycles presets. The mix shows on the artist line, like "Black Sabbath · Karaoke".
idle, it starts within about 5 seconds.
- Voice: "play Paranoid on Stemify" works for playlists, artists, albums and songs.
4. About a minute after each song finishes, the app notices and plays it with stems from then on.
- Away from home it notices the server is gone and only lists songs that will play.
Requests are handled oldest first and survive restarts. stemd matches the paths Plex reports to
Android Auto hides sideloaded apps until you allow them: in the phone's Android Auto settings, tap Version ten times, then ⋮ → Developer settings → Unknown sources.
files in its own music folder by their artist/album/file tail, so it doesn't matter that Plex and
stemd see the library under different mount points. Songs that failed before (corrupt files, or
anything over 40 minutes) are skipped; delete `state/failed.json` to give them all another shot.
---
To test without a car, start the head unit server from Auto's developer settings, then:
## The Equalizer
Find it in **Settings → Equalizer**. It's two equalizers wearing one trench coat.
**The graphic EQ** has ten octave bands from 31 Hz to 16 kHz, a response curve, and a pile of
presets borrowed in spirit from iOS (Bass Booster, Late Night, Vocal Booster and friends).
**Parametric Filters** are modelled on [Equalizer APO](https://sourceforge.net/projects/equalizerapo/):
| Type | What it's for |
|---|---|
| Peak | Boost or cut around one frequency |
| Low Shelf / High Shelf | Tilt everything below or above a frequency |
| Low Pass / High Pass | Roll off the top or bottom, at 6, 12, 24, 36 or 48 dB per octave |
| Band Pass | Keep only a band |
| Notch | Surgically remove one frequency (hello, 60 Hz hum) |
| All Pass | Shift phase without changing level, for the true connoisseur |
Every filter has frequency, gain and Q, can apply to **both channels, or just left or right**,
and can be switched off on its own to compare. Drag a filter's handle on its curve (sideways for
frequency, up and down for gain), use the sliders, or tap any value to type it in.
**Headphone corrections in two taps:** copy a `ParametricEQ.txt` from
[AutoEQ](https://github.com/jaakkopasanen/AutoEq) for your headphones, then on the Filters page
choose **••• → Paste APO Config**. You can also **Copy as APO Config** to take your settings to a
PC.
**Profiles** link to output devices: the phone speaker, wired headphones, each Bluetooth headset,
USB DACs. Plug something in and its profile switches on automatically, or pick one by hand.
**Preamp and anti-clipping:** each profile has its own manual preamp, and the anti-clipping switch
adds just enough extra cut that a full-scale signal at the curve's loudest point still peaks at
0 dBFS. A limiter on the master bus catches anything else, so cranking the bass won't make things
crackle.
---
## Android Auto
Designed for a 2016 Mazda MX-5 with the Mazda Connect retrofit: an 800×480 screen with touch
disabled, driven entirely by the commander knob and the steering wheel buttons. If it works there,
it'll work in your car.
- **Four tabs:** Playlists, Albums, Artists, Downloads (Downloads comes first when you're away
from home).
- **Shallow and short:** every song list starts with **Shuffle all**, and anything longer than 40
items splits into A to Z folders, so you never have to twiddle the knob through 400 songs at a
red light.
- **Now playing:** next to the transport controls you get **Vocals** on/off (instant karaoke),
**Mix** (cycles through the presets), shuffle and repeat. The current mix shows on the artist
line, e.g. "Black Sabbath · Karaoke".
- **Voice:** hold the talk button and say "play Paranoid on Stemify". Playlists, artists,
albums and songs all work.
- **Offline:** away from home, the app quickly notices the server is unreachable and lists only
songs that will actually play (downloaded or fully cached).
**Setting up the car (once):** Android Auto hides sideloaded apps until you allow them. On the
phone, search Settings for "Android Auto", tap **Version** ten times, then in the ⋮ menu go to
**Developer settings** and tick **Unknown sources**. Stemify then shows up in Auto's app
launcher.
**Testing without a car:** Google's Desktop Head Unit can impersonate the Miata. On the phone,
start the head unit server from Auto's developer settings, then:
Linux, Python 3.12 and [uv](https://docs.astral.sh/uv/). PyTorch defaults to ROCm (AMD); point the torch index in `pyproject.toml` elsewhere for NVIDIA or CPU.
`ios/` is a SwiftUI port of the Android app with the same features, plus CarPlay (browse tabs, Now Playing with Vocals and Mix buttons) and Siri ("play X in Stemify"). iOS 17 or newer.
```sh
uv sync
On top of the Android features: the Save chip in the mixer remembers a mix for that song and puts it back every time it plays, and the mic button turns on karaoke mode (vocals muted on every song, synced lyrics from [LRCLIB](https://lrclib.net) on Now Playing; tap a line to jump to it).
uv run stemify # the drag-and-drop separator
uv run stemify-player # the player
Build an unsigned IPA on a Mac with Xcode and xcodegen (`brew install xcodegen`):
./scripts/install-desktop.sh # add both to your app launcher (--uninstall removes them)
Sideload the IPA with Sideloadly or AltStore, which sign it with your Apple ID.
**Stemify** is the separator. Drop files on the window and each one is separated with your last-used model and device. You get a lane per stem with a waveform, solo, mute, gain and export (everything, one stem, or the current mix, as WAV, FLAC or MP3). Separation runs in its own process, results are cached, and it works on AMD, NVIDIA and CPU.
To get updates in AltStore, SideStore or Feather, add this source:
**Stemify Player** is your Plex library and its stems, dressed up as Microsoft Excel 2016. Sheets are your library, the zoom slider is master volume, Cell Styles are mix presets, and Undo/Redo skip songs. It reports plays to Plex, supports media keys and MPRIS, and remembers your queue and mix. More in [`stemify/player/README.md`](stemify/player/README.md).
After uploading a new release (tag `ios-v<version>`, asset `stemify-<version>.ipa`), run `ios/scripts/make-source.py` to regenerate `ios/source.json` and commit it. To work in Xcode instead, run `xcodegen generate` and open `Stemify.xcodeproj`.
A big library takes stemd days. Hold a song, album, artist or playlist and choose **Stem Now** to move its unseparated songs to the front.
CarPlay and Siri need the `carplay-audio` and `siri` entitlements. A free Apple ID can't sign those, so on a free sideload the app works on the phone but won't show up in CarPlay or Siri. A paid developer account covers Siri; CarPlay audio also needs Apple to approve the entitlement for your team.
1. The app sends the songs to stemserve, which drops a request file in stemd's queue folder.
2. stemd finishes the song it's on and does yours next. If it was idle, it starts within about 5 seconds.
3. About a minute after each song finishes, the app picks up its stems.
## The desktop apps
Requests run oldest first and survive restarts. stemd matches Plex's paths to its own files by the artist/album/file tail, so different mount points don't matter. Songs that failed before are skipped; delete `state/failed.json` to retry them.
### Stemify (the separator)
## Reference
Drop files onto the window. Each becomes a queue item, separation starts right away with your
### Separation models
last-used model and device, and when it's done you get a lane per stem with a waveform, solo, mute,
gain and export. Export everything, one stem, or your current mix, as WAV, FLAC or MP3.
Other niceties:
| Model id | Stems | Notes |
|---|---|---|
| `htdemucs` | 4 | HT Demucs, fast |
| `htdemucs_ft` | 4 | Fine-tuned, about 4x slower |
The 4-stem models give vocals, drums, bass and other. The 6-stem ones add guitar and piano.
---
## How the pieces find each other
The stems folder mirrors the music folder, with one folder per song:
```
```
Music/Kansas/Leftoverture/01 Carry On Wayward Son.flac
Music/Kansas/Leftoverture/01 Carry On Wayward Son.flac
Stems/Kansas/Leftoverture/01 Carry On Wayward Son/
Stems/Kansas/Leftoverture/01 Carry On Wayward Son/
.stemify.json ← the "this one's done" marker
.stemify.json done marker
01 Carry On Wayward Son - vocals.flac
01 Carry On Wayward Son - vocals.flac
01 Carry On Wayward Son - drums.flac
01 Carry On Wayward Son - drums.flac
01 Carry On Wayward Son - bass.flac
...
...
```
```
- Stems are written as 24-bit FLAC into a hidden `.partial` folder first, and the marker goes in
- Stems are written as 24-bit FLAC to a hidden `.partial` folder and the marker goes in last, so an interrupted separation is just redone.
last, so a separation interrupted by a reboot is simply redone next time. No half-baked songs.
- If a folder has the same song in several formats, the best one wins (FLAC/WAV, then M4A, Opus/Ogg, MP3, WMA).
- When a folder holds the same song in several formats, the best one wins (FLAC/WAV, then M4A,
- Plex reports paths as its container sees them, so the apps match songs to stems by path suffix, check durations, and learn the prefix from the first confident match.
Opus/Ogg, MP3, WMA).
- Plex reports file paths as *its* container sees them, so the apps match them to stems by suffix,
checking durations along the way, and learn the path prefix from the first confident match. A
song called "Intro.flac" on one album will never steal another album's intro.
---
### stemserve API
## stemserve API
| Request | Returns |
| Request | Returns |
|---|---|
|---|---|
| `GET /api/info` | Track count, whether ffmpeg is available, whether Stem Now is set up |
| `GET /api/info` | Track count, ffmpeg availability, whether Stem Now is set up |
| `GET /api/index` | Every finished song (with ETag, so unchanged indexes cost one tiny 304) |
| `GET /api/index` | Every finished song (with ETag) |
| `GET /api/peaks?key=K&n=256` | Per-stem loudness envelopes for waveforms, 0 to 1000 |
| `GET /api/peaks?key=K&n=256` | Per-stem loudness envelopes for waveforms, 0 to 1000 |
| `POST /api/prepare?key=K&fmt=opus&br=256` | Starts Opus transcodes in the background |
| `POST /api/prepare?key=K&fmt=opus&br=256` | Starts Opus transcodes in the background |
| `POST /api/stem` with `{"paths": [...]}` | Stem Now: stemd separates these Plex files next |
| `POST /api/stem` with `{"paths": [...]}` | Stem Now for these Plex files |
| `GET /file/K/<file>.flac[?fmt=opus&br=256]` | The stem itself, with HTTP range support for seeking |
| `GET /file/K/<file>.flac[?fmt=opus&br=256]` | The stem, with range support |
`K` is the song's folder under the stems root, e.g. `Kansas/Leftoverture/01 Carry On Wayward Son`.
`K` is the song's folder under the stems root, like `Kansas/Leftoverture/01 Carry On Wayward Son`. Outside Docker:
xcodegen generate # or open Stemify.xcodeproj in Xcode
```
The version lives in `ios/project.yml` (`MARKETING_VERSION` and `CURRENT_PROJECT_VERSION`). To release, tag `ios-v<version>`, attach `stemify-<version>.ipa`, then run `GITEA_TOKEN=... ios/scripts/make-source.py` and commit the new `ios/source.json`.
**Android** needs JDK 21 and the Android SDK (`android/local.properties` points at it):
**Android** needs JDK 21 and the Android SDK (`android/local.properties` points at it):
JAVA_HOME=/path/to/jdk-21 ./gradlew testDebugUnitTest # stem matching, EQ and filter maths, limiter, cache, car tree
JAVA_HOME=/path/to/jdk-21 ./gradlew testDebugUnitTest # matching, EQ maths, limiter, cache, car tree
```
```
The cache and index tests stream real stems from a stemserve on `localhost:8765` and skip
The cache and index tests use a stemserve on `localhost:8765` and skip themselves without one.
themselves when there isn't one. Debug builds include a hook for screenshots and back-gesture
testing (`app/src/debug`); release builds don't.
**Desktop** apps can be checked without opening a window:
**Desktop** can be checked without a window:
```sh
```sh
QT_QPA_PLATFORM=offscreen uv run stemify-player --no-mpris --screenshot /tmp/p.png@5 --quit-after 6
QT_QPA_PLATFORM=offscreen uv run stemify-player --no-mpris --screenshot /tmp/p.png@5 --quit-after 6
```
```
---
## Troubleshooting
## Repo tour
**A song says NO STEMS.** Hold it and choose Stem Now.
```
**Stem Now says "stemserve needs updating" or "queue folder isn't mounted".** stemserve is older than the app or is missing the `/queue` mount. The queue folder has to be owned by `99:100` before the container first starts, or Docker creates it as root.
android/ the Android and Android Auto app (Kotlin, Jetpack Compose, Media3)
app/src/main/java/com/stemify/mobile/
plex/ Plex library, search, playlists, artwork, play reporting
stems/ stemserve client, path matching, which albums have stems
cache/ sparse block cache for streaming, and downloads
engine/ decoders, the sample-locked mixer, EQ, limiter, meters
eq/ EQ profiles, device switching, APO config import/export
playback/ queue, audio focus, mix presets, the Media3 session
auto/ Android Auto browse tree, voice search, offline mode
ui/ every screen, hand-built iOS-style components
server/
stemd.py the GPU separation daemon
stemserve.py the stem file server (standard library only)
*.Dockerfile, docker-compose.yml
stemify/ the desktop separator (PySide6 + QML) and shared separation code
worker/ separation backends (Demucs, RoFormer) in a separate process
player/ Stemify Player, the Excel-shaped one
library_core.py the folder layout rules shared with stemd
scripts/install-desktop.sh
specs.txt the original design doc for the desktop separator
```
---
**stemd is separating on the CPU.** The container can't see the GPU. Run it with `--runtime=nvidia` and the NVIDIA variables above.
## Troubleshooting and FAQ
**stemd says "out of GPU memory".** Something else is using VRAM. stemd retries that song next pass without marking it failed.
**A song says NO STEMS and I'm impatient.**
**The stem server shows Offline.** Check the address in Settings, try `curl http://<server>:8765/api/info` from another machine, and if stemserve has a `TOKEN`, set the same one in the app.
Hold it and choose **Stem Now**. It'll be next in line.
**Stem Now says "stemserve needs updating" or "queue folder isn't mounted".**
**Stemify isn't in CarPlay or Siri.** The IPA was signed without those entitlements. See [iOS install](#install).
stemserve is older than the app, or it's missing the `/queue` mount. See
[the server setup](#1-the-server-stemd-and-stemserve). The queue folder needs to be owned by
`99:100` *before* the container first starts, or Docker creates it as root and nobody can write
to it.
**stemd says it's separating on the CPU.**
**Stemify isn't in Android Auto.** Turn on Unknown sources in Auto's developer settings. See [Android Auto](#android-auto).
The container can't see the GPU. Make sure it's running with `--runtime=nvidia` and the NVIDIA
environment variables shown above.
**stemd keeps saying "out of GPU memory".**
**Songs listed in `state/failed.json`.** Usually corrupt files or "songs" over 40 minutes (DJ mixes, radio rips). They retry when the file changes; delete the file to retry everything.
Something else (Plex transcoding, a game server, your ambitions) is hogging VRAM. stemd shrugs and
retries that song on the next pass. Nothing is marked failed.
**The Stem Server page says Offline.**
Check the address in Settings → Stem Server, check `curl http://<server>:8765/api/info` from
another machine, and if you set a `TOKEN` on the server, set the same one in the app.
**The app doesn't show up in Android Auto.**
Sideloaded apps need **Unknown sources** turned on in Auto's developer settings. See
[setting up the car](#android-auto).
**Some songs are marked failed in `state/failed.json`.**
Usually corrupt files, or "songs" over 40 minutes (those are almost always DJ mixes or radio rips).
Failed tracks retry automatically when the file changes; delete the file to retry everything.
**Why is the desktop player an Excel spreadsheet?**
We don't talk about it.
---
## Credits
## Credits
Standing on the shoulders of some very clever people:
- [Demucs](https://github.com/adefossez/demucs) by Alexandre Défossez
- [Demucs](https://github.com/adefossez/demucs) by Alexandre Défossez
- BS-RoFormer and Mel-RoFormer models, including the SW 6-stem model by jarredou, Viperx's 1297,
- BS-RoFormer and Mel-RoFormer models (SW 6-stem by jarredou, Viperx 1297, Kim FT by unwa) via [python-audio-separator](https://github.com/nomadkaraoke/python-audio-separator)
- [Equalizer APO](https://sourceforge.net/projects/equalizerapo/) and [AutoEQ](https://github.com/jaakkopasanen/AutoEq), whose formats the EQ reads and writes
"localizedDescription":"- Add to Playlist is now one sheet instead of a string of pop-ups: Plex and Stem tabs, type a new playlist name right in the list, playlist art, and mix chips for stem playlists.\n- Song menus have a single \"Add to Playlist\u2026\" entry for both kinds; the sheet remembers which tab you used last.\n\nUnsigned IPA: sideload with AltStore, SideStore or Feather.",
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
cdnutterandClaude Opus 5.5