YuE2-Studio

YuE2 Studio

Full songs with an editable score, generated on your own GPU. One executable — no Python, no Node.js, no launcher.

English · Русский · 中文 · 日本語 · 한국어

YuE2 Studio is a desktop studio for YuE2, the open song model from M-A-P that writes a score before it sings. Describe a style, write the lyrics, and the model composes a melody with chords as sheet music, then performs it as a full song with vocals. The score comes back with the track: read it, edit it, and render the same composition again with a different sound. Windows installer with auto-update or a portable folder, runs offline on an NVIDIA card with 6 GB of VRAM or more; AMD and Intel cards through Vulkan are experimental.

It is built on yue2.cpp, the native C++/CUDA port of YuE2. The studio around it is Rust and React in a Tauri window — nothing in the runtime path is Python.

For AI agents

Given this repository, an agent can set everything up and drive the studio by itself:

1. Install the studio from the latest release and start it.
2. Connect to its MCP server at http://127.0.0.1:8791/mcp: claude mcp add --transport http yue2-studio http://127.0.0.1:8791/mcp
3. Read the skill it serves (resource studio://skill, prompt studio), the same text as docs/mcp-skill.md, and start with the tool studio_status.

llms.txt says the same for tools that look for it. To keep the skill in Claude Code, save docs/mcp-skill.md as ~/.claude/skills/yue2-studio/SKILL.md.

What you can do

• A player of its own — a ten-band equalizer on Winamp’s frequencies with its presets, your own and .EQF files; a MilkDrop visualiser with hundreds of presets or a spectrum in ten looks, over the studio, fullscreen or in its own window; and a Winamp mode that turns the whole window into a skinned Winamp 2 whose windows move apart, dock and resize — the original skin and ten more included, sharp at any scale, the Winamp Skin Museum one click away, Ctrl+M to switch. The song, its place and the equalizer carry over both ways.
• Save as, and a Files panel — songs, stems, MIDI, lyric sheets, scores and videos are saved where you say, in Windows’ own Save dialog, and the Files panel shows each save.
• A proxy for the whole studio — HTTP, HTTPS, SOCKS5 or SOCKS4, with a login: model downloads, Hugging Face, OpenRouter and updates go through it.
• Full songs from a style and lyrics — up to ten minutes, in the languages the model sings. In Russian a stress mark (the combining acute U+0301, Alt+0769 on Windows) after a vowel moves the sung stress to it, as Ruach Studio documents. On an RTX 4090 with the Q8_0 set a 3:38 song renders in about 46 seconds.
• Read and edit the score — the model writes its composition in ABC notation first; the studio engraves it as sheet music. Edit the notes, tempo or key and create again: the composition stays, the performance changes. Or switch to melody-only, or no score at all.
• Compose the score first — write only the score from the style and lyrics, without singing it (the studio’s take on yue2.cpp’s yue-plan), read and fix it, then create.
• Covers — SheetSage2 listens to a recording and writes its melody as a score; YuE2 then sings that melody in your style. The words have to fit the melody: the original lyrics work best, new ones need the same syllables line by line with the stresses on the same notes, or the singing drifts off the tune — lines stretch, pause and slide into the wrong section. Transcription mistakes carry into the cover too. A track from your library can be transcribed from its menu.
• Exact replay — every track keeps its request and its audio codes, so it can be re-rendered bit for bit, or re-rendered with other steps, a new sound seed, several variations, or another output format, without composing again.
• 110 ready examples — the style/lyrics/score sets that ship with yue2.cpp, covers included, one click to load.
• Every engine setting — all seven sampling knobs (temperature, top-p, top-k, repetition penalty and its window, minimum and maximum tokens) for the score and for the audio codes, flow-matching steps, guidance, both seeds, lossless FLAC or MP3. Prompts open and save as JSON or YAML in the engine’s own request format, so they move freely between the studio, the yue2.cpp WebUI and yue-synth.
• Structured song writing — build a style from its musical fields and arrange lyrics in editable sections, while keeping the plain text editable. Give the writing assistant a language, a target of 8–32 lines and additional instructions.
• Song and render controls — voice and tempo fields; section, line/stanza and text-case tools; Keep/Words lyric preservation and exact checkpoint tokens; batch score-plan selection and chord mirroring in repeated sections. Edit scores with MIDI grid and octave controls. Transpose generation by −24 to +24 semitones, render vocals only through native HT-Demucs as MP3 or 32-bit WAV, and switch each LoRA on or off with weights from −10 to +10.
• A writing assistant — a local Gemma model or OpenRouter writes the style and lyrics from an idea and edits the score on request; or pick your connected agent (MCP) and it writes instead. Lyrics you wrote yourself get their section tags with one button, the words exactly as you wrote them.
• Word-level karaoke — enhanced LRC with a timestamp on every word, aligned by Parakeet or Whisper. Your lyrics are kept; only the timing is borrowed.
• Six stems on the GPU — drums, bass, other, vocals, guitar and piano with HT-Demucs.
• Any track to MIDI — a song, a stem or a processed take becomes multi-instrument MIDI (34 instrument groups and drums) with MuScriptor on the GPU, through HOT-Step’s native port. A piano roll fills in while it listens; play it against the original, mute or solo an instrument, save the .mid. Downloaded the first time it is used.
• A MIDI editor — a piano roll with tracks, instruments and drums: play a song in from a MIDI keyboard or the computer’s keys, record or draw it, edit a track’s MIDI, save it to the library as a track and send it to a cover, or open the create form’s score in it. A .mid file becomes the score: the voice and instrument chosen, chords read or guessed, karaoke words offered for the lyrics.
• Every result is a track — stems, a processed take, a re-render and a cover land in the library as tracks of their own, each marked with the one it was made from and keeping the settings it was made with.
• LoRA — LoRA and LoKr files for either half of the model, the composition or the sound, each with its own strength, picked in the create form. A catalogue of ready ones with their authors credited, and a search on Hugging Face that downloads what you pick.
• Train your own LoRA — an optional tab on the LoRA page: songs of one artist or style become a LoRA on your own card with HOT-Step’s trainer and its tuned recipe (LoKr, Prodigy, lyric timing from a forced aligner that also reads Cyrillic). Every setting of the recipe is editable. Datasets move between this studio and MiniMax Music3 Studio as a folder, and each saved checkpoint goes into the LoRA library in one click.
  • A three-step wizard — drop a folder of songs, check them, train. Albums with a cue sheet are cut into songs; titles and artists come from the tags, the file name and the folders.
  • Preparation on its own — lyrics come from the lyric databases players use (LRCLIB, QQ Music, Kugou), word for word; only a song none of them knows has its vocals separated and is heard by Whisper, with its usual hallucinations filtered out. The assistant lays the lyrics out in sections. MOSS-Music listens to every song and the assistant writes its style, with the tempo measured by Beat This! on the card.
  • Every song shows where it is — the lyrics and styles appear as each song is done, one model on the card at a time, each loaded once for the whole batch. A song that failed or was stopped has a button that finishes just that song.
  • Picks up after a restart — each song keeps what it has; a preparation cut off by a crash or a restart carries on by itself and redoes nothing.
  • Stop by drift or by epochs — stop when the composition half drifts too far from the base, or after a set number of passes over the songs.
  • A trigger word from the start — every dataset gets a rare word made from its name, which you can change.
  • Train further — not there yet at 750 steps? Set 1000 and the run goes on from its latest checkpoint with the same recipe and songs; the loss chart and the checkpoints continue instead of starting over.
• Audio processing — noise reduction, the Spectral Lifter, a vocal naturaliser, your own VST3 plugins in a chain, and mastering to a reference track. Compare before and after while it plays, then keep the result as a version of the track or throw it away.
• The sound as the model made it — the engine renders 32-bit float and the studio encodes it once, changing nothing on the way: lossless 24-bit FLAC by default (libFLAC, the reference encoder), MP3 with LAME when you choose it. Normalisation is a stage under Process, after mastering, never part of generation.
• A library of plain files — search, playlists, cover art from prompt templates, tracks exported with title, lyrics and cover in their own tags (Vorbis comments in a FLAC, ID3 in an MP3). Interface in English, Russian, Chinese, Japanese and Korean.
• A cover for every track — a track without one wears a free (CC0) Wikimedia Commons photograph that fits the genres, moods and instruments of its style, a pattern in one of 21 DiceBear styles, or a cover OpenRouter generates for every new track. It is chosen by the track’s seed, so it stays the same, a stem wears its song’s, and it is written into the file, so players show it after the download.
• One picture window — for a cover, and for the background and centre of a music video: Commons photographs by search starting from the scenes a style calls up, clips free of copyright for a background, the track’s pattern in any style, generation through OpenRouter, or a file of your own. No keys, no stock-site accounts.
• Music videos — a visualiser video of any track in 16:9, 9:16 or 1:1, with karaoke lyrics, text layers and effects, rendered to MP4 on your machine.
• Activity — a log in the sidebar of every change a connected agent makes and every message the studio shows.
• Likes, sorting and stems in order — a like is kept with the song for every window and agent, every list sorts by date, title or length, and a song’s stems fold under it.
• A song from a seed — hum, play or write an opening, turn on “Continue the song from this score”, and the model writes the rest of the song on from it in its key and meter, the opening coming back as a hook.
• Chord bed — a score of chords over rests written at once in the tempo, key and meter you set, one section per lyrics tag; the model writes the melody and the arrangement over it and the planning step is skipped.
• Chords and sections — chord variety so the song stops looping one progression, sections that do not open the way the one before did, chords outside the key, and the score held to the lyrics’ sections in their order.
• Covers that line up — Match sections to the score retags the lyric blocks by where the source recording sings them; the score view moves the voice an octave down or up, apart from the band, and Instrumental hands the voice’s notes to the instrument and keeps the chords.
• Extend a song — Re-render composes on from the track’s last frame by 15 seconds to 2 minutes; with a score, each section’s words wait until the score reaches it.
• AB2 solver — one network evaluation a step instead of two, about twice as fast at the same steps; midpoint stays the default.
• Around every song — a note of your own on each song, its parameters sent back to the form, shown as JSON or saved to a file; the engine’s stage, step and time left on the card while it renders; video export from 1080p to 240p with AAC from 128 to 320 kbps; quitting while a song is made asks first, and a song the studio was closed on starts again; karaoke can recognise words with Parakeet Ultra, Moondream’s fine-tune of Parakeet.

Compose and edit MIDI

The embedded Signal editor has multiple tracks, instruments, drums, MIDI keyboard recording, tempo changes, editable chord symbols and section markers. Save a new composition as MIDI and rendered audio in the library, or update an existing track’s MIDI. SoundFonts are bundled locally; the editor sends no analytics.

In YuE2, the same editor opens ABC scores and applies notes, chords and sections back to the create form. The visual editor replaces the older separate score editor. Use Apply to update the ABC score, or send a library MIDI track to cover mode.

Screenshots

The equalizer with its curve and MilkDrop over the studio, as the song plays	The whole window as Winamp 2: equalizer, playlist and MilkDrop, skinned
The score as sheet music and as ABC text — melody + chords, melody only, or none	A finished track — its lyrics and the score it was sung from, ready to reuse
Cover mode — pick a recording, SheetSage2 writes its melody down	Model sets — one quantisation per role, what is on disk, switch in one click
Any track to MIDI — a piano roll of every instrument, played against the original, with mute and solo	Your own LoRA trained on the card — loss and drift as it learns, a checkpoint every 50 steps
A dataset of 61 songs — lyrics found in the databases players use, styles written by ear	The LoRA catalogue — styles, artists and sound, each credited to its author
Audio processing — noise reduction, the Spectral Lifter, a vocal naturaliser, VST3, mastering	An agent over MCP — the address and the lines to paste into Claude Code or any client

The same screens in the language you read: Русский, 中文, 日本語, 한국어 — on the project page, or in docs/screenshots.

Samples

Made in the released build on an RTX 4090 with the recommended BF16 set, nothing edited afterwards. Listen in the browser on the project page or download the MP3s from docs/samples.

Community reviews

Video reviews and tutorials from the community (the description links this repo):

AI Controversy · EN Ditch Suno: This FREE AI Makes Full Songs on Your PC	ArtSonica · ID Music AI GRATIS OFFLINE / NO INTERNET	AI VINCI · EN The Suno Killer is Here: it's called YuE2 Studio
Mamedov Info · RU YuE2-Studio: лучшая локальная замена Suno	ЮЛАВИ Studio · RU Забудь про Suno? Тестируем YuE2 Studio локально	Wizzdome-Music · EN YuE2 Studio On Your Own PC

More tutorials and reviews:

• Dream Travel — YuE2 Studio для генерации музыки прямо на компе · RU
• Luki AI Lab — NEW YuE2: a FREE alternative for your PC · EN
• Skillo Labs — Você já pode criar músicas com IA sem internet · PT
• 아빠너구리 TV — $0/Month AI Music with YuE2 Studio · KO
• Frihandhika — Tutorial YuE2 Studio di Windows · ID
• Run It Local — YuE2 Studio: FREE AI Songs on AMD (Beats ComfyUI) · EN
• Franck D Digital AI — YuE2 Studio Portable (tutoriel français) · FR
• EZTV — YUE2 Studio 教學 · ZH

Made a review or tutorial? Put a link to the project in the description — we feature the best ones on the site and here. Send yours through Issues.

What it needs

• Windows 10/11 x64.
• A GPU with 6 GB of VRAM or more:
  • NVIDIA, from the GTX 900 series on, runs on CUDA — the fastest path. The studio ships two CUDA builds of the engine and picks the one your card and driver run: CUDA 13 for Turing and newer (GTX 16, RTX 20–50, Tesla T4, A100, RTX A-series, L4/L40, H100) with driver 580 or newer, CUDA 12 for Maxwell, Pascal and Volta (GTX 900/1000, Titan X/Xp/V, Tesla M40, P40, P100, V100) and for any card on a driver from 525 to 579. Both carry compiled code for every one of those architectures, so nothing is left for the driver to compile.
  • AMD or Intel — experimental. The engine runs on Vulkan through the card’s own driver. The Vulkan path itself is verified on NVIDIA (the same words heard as on CUDA), but on AMD Radeon integrated graphics the song came out with unintelligible vocals, and discrete AMD and Intel cards are untested. Reports from owners are welcome.
  • Without a GPU the engine falls back to the processor, which works but is many times slower.
• 4–10 GB of disk for one model set.
• Training a LoRA (optional): an NVIDIA RTX 30-series card or newer with 11 GB of VRAM and about 8 GB more disk for the trainer and its weights, downloaded only when you open training. Describing songs by ear needs about 12 GB of VRAM and 10 GB more disk for MOSS-Music; without it the styles are written by hand.

Linux (experimental)

The .deb and the AppImage for Linux x86-64 are experimental. They come from the same code with the Linux build of the same engine (Vulkan, and the processor), but the author works on Windows and has not run them on a real Linux desktop. If you live on Linux, it would be great if you polished them and sent the fixes back as a pull request. The studio keeps its data in ~/.local/share/yue2-studio ($XDG_DATA_HOME).

What runs where

The paths for AMD and Intel cards (Vulkan, DirectML) and work on the processor are experimental: they exist for computers where the studio would not run at all otherwise. The main, tested path is an NVIDIA card.

• Training needs an NVIDIA card with 11 GB of video memory or more. The trainer has no other path, and on the processor one run would take days, so on any other machine the studio does not offer the training files.
• On AMD and Intel cards stems are separated on the processor: the HT-Demucs model does not run through DirectML (out of memory on a 2 GB integrated card, over 20 GB and minutes for 30 seconds of audio on a 24 GB one).
• Karaoke’s Parakeet runs on transcribe.cpp, the engine Dub Studio and Speech Studio use: its CUDA build on an NVIDIA card with a CUDA 13 driver (on Linux when the system has CUDA 13’s cuBLAS), its Vulkan build on any other card, its processor build without one; on a Mac, Metal on Apple silicon and the processor on Intel. The tempo model reaches any DirectX 12 card through DirectML, whose runtime comes with karaoke’s card path.
• “Auto” in a device choice takes the card when its runtime is installed, and the processor otherwise. The same table is in the studio, under Settings → Models.

Quick start

1. Install — run YuE2.Studio_x.y.z_x64-setup.exe from the latest release, or unzip the portable archive anywhere and run YuE2-Studio.exe.
2. Choose a model set — the first screen preselects the set your card can run. Press download; it fetches only what is missing and resumes if interrupted.
3. Create — write a style and lyrics, or load one of the examples, and press Create. The engine starts by itself and the song lands in your library with its score.

Everything the studio owns stays in its own folder: models, songs, settings, logs, temporary files and the WebView2 profile, beside YuE2-Studio.exe. That holds for the portable archive and for an installation into any folder the studio can write to; deleting the folder removes the studio. Only an installation into a read-only location such as Program Files falls back to %LOCALAPPDATA%\YuE2 Studio. The installed version updates itself: a new release is offered inside the studio and installed in place.

If the installer stops on WebView2. The studio’s window runs on Microsoft Edge WebView2, and the installer fetches it when Windows lacks it. On a blocked or unsteady connection, or on Windows 10 builds that refuse Microsoft’s small bootstrapper (error 0x80040902), that fetch fails and the installer says so. Install WebView2 from Microsoft’s standalone installer, Evergreen Standalone x64, then run the studio’s installer again.

Drive it from an agent (MCP)

While the studio is open it serves MCP at http://127.0.0.1:8791/mcp: an agent such as Claude Code, Claude Desktop or Cursor does everything the page does, through the same code - songs and scores, the library, covers, stems, MIDI, karaoke, processing, video clips, the player, LoRA, and a LoRA from a folder of songs end to end - and sees and works the window itself: a screenshot, its controls, clicks and typing. 162 tools, grouped by area. The model’s writing rules and official examples come with the server, so the agent writes the styles, lyrics and lyric layouts itself instead of the studio’s small assistant.

With Agent (MCP) chosen as the writing assistant (Settings, Models), the connected agent also answers the studio’s own write buttons and dataset preparation. Settings, Agent (MCP) shows whether an agent is connected and what to paste into the client.

claude mcp add --transport http yue2-studio http://127.0.0.1:8791/mcp

docs/mcp-skill.md is the skill an agent reads: every tool, what the model expects, and step-by-step recipes.

Models

A runnable YuE2 installation is a backbone (the 3B model that writes the score and the audio codes) and the VAE (turns them into 48 kHz stereo). SheetSage2 is optional: without it the studio generates, but cannot transcribe recordings for covers.

Every set also carries the decoder companion, 134 MB: Mothersuperior’s decoder adapter, published as the pair of the tokenizer head the LoRA trainer turns songs into codes with. The trainer keeps it frozen under every LoRA, so a LoRA is trained on the decoder it is heard through. A render merges it on Auto (Advanced - output) only under a LoRA trained in the studio; otherwise the song is decoded by the YuE2 checkpoint alone, as its authors, audio.cpp and ComfyUI render it. On and Off force it either way. In HOT-Step’s round trip of six real songs the decoder without it narrowed the stereo (left/right correlation 0.78–0.92 against the originals’ ~0.65), with it 0.57–0.72.

Sizes include SheetSage2 with the MERT-v2 encoder it reads (Q8_0, F32 in the native set) and the decoder companion. The studio detects your card and preselects the set, but the download is always your decision; the model manager also builds a custom mix role by role. Q5_K_M is the lightest quantisation published for YuE2.

The GGUF files come from Serveurperso/YuE2-GGUF, pinned to revision e630f2b, the decoder companion from Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4, pinned to revision e2e63d8; all are checked by size and SHA-256. They are written to, and can be dropped into by hand at:

• <the studio's folder>\data\models\yue2-cpp\ — the portable folder, or the folder you installed into
• %LOCALAPPDATA%\YuE2 Studio\models\yue2-cpp\ — only for an installation into a read-only location

A file placed by hand with the exact catalogue name is recognised and never downloaded again.

Everything else the studio downloads

Each part is downloaded when you first use it, and each file can be downloaded by hand and put into the studio’s data folder — <the studio's folder>\data\, or %LOCALAPPDATA%\YuE2 Studio\ for an installation into a read-only location. A file with the exact name in the listed folder is recognised and not downloaded again.

The engine and the DLLs it needs

yue-server.exe → ggml.dll, ggml-base.dll            shipped inside the app
  loads at run time, whichever the machine can use:
  ├─ ggml-cuda.dll     → cublas64_13.dll, cublasLt64_13.dll (downloaded once), nvcuda.dll (NVIDIA driver)
  ├─ ggml-vulkan.dll   → vulkan-1.dll (every AMD, Intel and NVIDIA driver)
  └─ ggml-cpu-*.dll    nine builds, from SSE4.2 to AVX-512; the best one for the processor is picked
  + msvcp140, vcruntime140, vcruntime140_1, vcomp140   Visual C++ runtime, shipped app-local

Shipped inside the app. yue-server.exe, every ggml*.dll, built from the pinned yue2.cpp commit with all backends, and the Visual C++ runtime it needs live in resources\yue2-cpp\ beside the main executable. Nothing is installed into Windows. Settings → Local engine chooses the compute device: Auto (CUDA on NVIDIA, Vulkan on AMD and Intel, the processor without a GPU), or CUDA, Vulkan or the processor explicitly. On Vulkan the studio turns on the engine’s FP16 clamp: without it AMD Radeon integrated graphics rendered pure silence and the engine crashed encoding it.

Downloaded once, on the first engine start — on NVIDIA only.

A machine with the CUDA 13 toolkit already has cuBLAS on its PATH and downloads nothing. Behind a proxy, take the two DLLs from the archive’s bin\ folder and drop them next to yue-server.exe; the studio finds and uses them.

Architecture

React UI ─┐
          ├─ YuE2-Studio.exe   (Tauri window + Rust/Axum service on 127.0.0.1:8791)
Rust axum ┘        │
                   ├─ yue2.cpp `yue-server`   (C++/CUDA, GGUF, 127.0.0.1:18087)
                   ├─ music-train.exe         (HOT-Step ace-train, LoRA training, optional)
                   └─ vst-host.exe            (HOT-Step VST3 host, a process of its own)

The service is compiled into the desktop binary. It supervises the engine process, restarts it when you switch model sets, and imports finished songs itself, so a result is never lost if the window was reloaded or closed mid-generation. Progress is read from the engine’s own log: score, audio codes, acoustic rendering, decoding.

Building from source

npm --prefix app install
npm --prefix desktop install
cargo test --workspace
npm --prefix app test

Developing the UI against a running service:

cargo run -p music-server           # service on 127.0.0.1:8791
npm --prefix app run dev            # UI on 127.0.0.1:3791

The engine: scripts/build-yue-runtime.ps1 -RuntimeBackend all builds the pinned yue2.cpp commit (engines/yue2-cpp-source.json) with runtime-loaded CUDA, Vulkan and CPU backends, using CUDA 13, the Vulkan SDK, MSVC and Ninja. scripts/build-release.ps1 -Version X.Y.Z produces the NSIS installer, the portable archive and the signed latest.json for the updater; it reads the signing key from TAURI_SIGNING_PRIVATE_KEY or %USERPROFILE%\.tauri\yue2-studio.key. Model weights are never part of a release.

Linux packages are built on the release machine in an Ubuntu 22.04 container (glibc 2.35; Docker, under WSL on Windows): scripts/build-linux-docker.sh <output folder> builds the committed HEAD with scripts/build-release-linux.sh and checks that the engine starts. Only the .dmg is built on GitHub, by the macOS build workflow (.github/workflows/release-unix.yml, started by hand, optionally with a release tag to attach it to): there is no Mac on the release machine.

On macOS there is no packaged engine, so build it once from source (needs Xcode command line tools and CMake) and again whenever engines/yue2-cpp-source.json moves to a new commit:

scripts/build-yue-runtime.sh ~/yue2-engine          # builds the pinned commit with Metal
YUE_ENGINE_ROOT=~/yue2-engine cargo run -p music-server

Audio to MIDI is Windows-only as a download; on macOS scripts/build-midi-runtime.sh <dir> builds HOT-Step’s ace-midi with Metal (point YUE_MIDI_BIN at the resulting music-midi; the dmg bundles it).

YUE_ENGINE_ROOT (or YUE_ENGINE_BIN, the path of yue-server itself) tells the studio where the engine is; for the desktop app set it in the environment before launching it. Auto then lets the engine choose Metal and falls back to the CPU.

Anonymous statistics and news

The studio asks the author’s server for news at start and then every hour. The request carries no id, so news arrive whatever you choose below: new items appear on top of the News page or as a strip across the top of the window, and with no connection the studio shows the news of its release.

The setup screen of the first start has a checkbox Send anonymous usage statistics, checked by default. The same switch is in Settings → Anonymous statistics, next to What is sent (the exact report of today) and New install id. While it is checked, the studio sends a day’s report a minute after start, every six hours, two minutes after work ends and when it closes (a later report of the same day replaces the earlier one):

• a random install id made on this computer, not tied to the hardware or an account; unchecking the box deletes it;
• the studio and its version, the OS name and version, the window language;
• the graphics card as vendor, a video memory bucket (up to 8, 12, 16, 24+ GB) and the backend (CUDA, Vulkan or processor);
• how many songs were made, failed or were cancelled that day, and the model sets they were made on: a ready-made set by name with its parts, one put together by hand by its parts, each with its number of songs;
• why a song failed, as one line with paths, names, links and anything in quotes removed on this computer before it leaves; the server keeps these reasons 30 days.

Never: lyrics, prompts, audio, file names or paths, anything personal. The server keeps the country Cloudflare reports for the connection, not the IP address. DO_NOT_TRACK=1 or STUDIO_TELEMETRY=0 in the environment turns statistics off entirely: no id exists and nothing is counted.

Other Projects by @timoncool

Authors

• Nerual Dreming — Telegram | neuro-cartel.com | ArtGeneration.me
• Нейро-Софт — Telegram | portable neural networks

Acknowledgements

• M-A-P for YuE2-3B, the YuE2 VAE and SheetSage2.
• Mothersuperior for the real-audio tokenizer head the trainer’s codes come from and its paired decoder adapter, the decoder companion every render and every training runs on.
• Serveurperso for yue2.cpp, its examples and the GGUF conversions.
• scragnog for HOT-Step-CPP: the LoRA trainer the studio runs (its native joint AR/NAR training for YuE2), the training weights in scragnog/YuE2-GGUF, the VST3 host, and the noise reduction, Spectral Lifter and mastering designs the studio’s audio processing is ported from.
• sergree for matchering, the reference mastering algorithm, and jeankassio for the vocal naturalizer in ComfyUI_MusicTools.
• The authors of the LoRA in the catalogue, each credited and linked on its card: Mothersuperior, monsterovich, atomtanstudio, HaileyStorm and ntc-ai.
• The LAME project for the MP3 encoder, Xiph.Org for libFLAC, the FLAC encoder, and Serial-ATA for lofty, which writes the tags.
• crmne for Spotifast (MIT): the equalizer solves its band gains as its eq.rs does.
• Jordan Eldredge and the Webamp team for Webamp (MIT), which the Winamp mode runs, and for the Winamp Skin Museum. Winamp and its base skin are Nullsoft’s.
• Jordan Berg for Butterchurn and butterchurn-presets (MIT), MilkDrop in the browser. MilkDrop itself is Ryan Geiss’s, and each preset is its author’s, named in its title.
• Henrique Vianna for audioMotion-analyzer (AGPL-3.0), the spectrum looks of the visualiser.
• Borewit for music-metadata (MIT) and Stuart Knightley for JSZip (MIT), which read tracks and skins in the Winamp mode.
• The authors of the skins that come with the studio: Winamp’s base skin 2.91 (Nullsoft); Winamp5 Classified (Sven Kistner, Zarko Jovic, GuidoD, Wildrose-Wally); Winamp3 Classified (Steve Gedikian, John Slegers, PeterPan, Wildrose-Wally); Bento Classified and Internet Archive (LuigiHann); Mac OS X 1.5 Aqua (DeeLight); TopazAmp (Kelly McLarnon); Vizor (ViDA); Zaxon Remake (Daniel Jansson); Green Dimension V2 (its author, who signs the readme in ASCII art); XMMS Turquoise (from the XMMS project). Each skin keeps its own readme inside the .wsz.
• Wikimedia Commons and the photographers and filmmakers who give their work to it under CC0 or into the public domain, many of them through Unsplash: the pictures and clips a track and its video can wear. A chosen picture keeps a link to its page.
• Florian Körner for DiceBear (MIT) and the authors of its CC0 styles, the patterns a track without a cover wears, and the resvg authors, whose renderer writes them into the track as PNG.
• MRafStudio for the ideas of pull request #34: the Activity log, sorting, likes kept in the library and stems under their song.
• wangsoft for the Hugging Face mirror setting from wangsoft’s fork, and SkySlider for the Linux pieces from SkySlider’s fork: adapter detection and the parent-death signal.
• stalexxx for pull request #51: the service on macOS with Metal, a question before quitting during a song, and a stop that is kept at once.
• pytraveler for YuE2-ComfyUI (Apache-2.0): the reader and writer of YuE2’s score, the score as a MIDI file and a MIDI file read back into a score are ported from it.
• ryohey for signal (MIT), the MIDI editor, and Milton Paredes for the A320U SoundFonts it plays (GPL-2.0).

Support the Author

I build open-source software and do AI research. Most of what I create is free and available to everyone. Your donations help me keep creating without worrying about where the next meal comes from =)

All donation methods · Русский · 中文 · 日本語 · 한국어 | dalink.to/nerual_dreming | boosty.to/neuro_art

• BTC: 1E7dHL22RpyhJGVpcvKdbyZgksSYkYeEBC
• ETH (ERC20): 0xb5db65adf478983186d4897ba92fe2c25c594a0c
• USDT (TRC20): TQST9Lp2TjK6FiVkn4fwfGUee7NmkxEE7C

Star History

License

The studio is MIT, and so is yue2.cpp. The models are not. The YuE2-3B and YuE2 VAE weights are CC BY-NC 4.0 with an individual-creator permission (MODEL_LICENSE, 16 September 2026): personal users, content creators and musicians acting on their own may use them free of charge and publish, sell, license or otherwise monetize the songs they make, as long as the use is not illegal, harmful or deceptive. Companies that want to use the weights commercially need a license from their authors. SheetSage2, which reads the source song for covers, and the decoder companion (Mothersuperior) are CC BY-NC 4.0 without that permission.

One bundled component is under a different licence: the visualiser’s spectrum looks come from audioMotion-analyzer, which is AGPL-3.0; its source, like the studio’s, is public.

The score reader and writer and the MIDI import are ported from YuE2-ComfyUI, which is Apache-2.0; its licence is kept in licenses/YuE2-ComfyUI-Apache-2.0.txt. The MIDI editor is signal, MIT, built from our fork; the A320U SoundFonts it plays are GPL-2.0, their licence in licenses/A320U-soundfont-GPL-2.0.txt.

What changed and when is in CHANGELOG.md.