VuuWave User Guide

Write, generate, and refine complete songs on your own machine.

1. Getting started

VuuWave turns a written brief into a finished audio track. You describe the style, supply lyrics, set length and key, and the local MusicCore engine generates the song on your own GPU or CPU. Nothing is uploaded for generation.

  1. Pick a workspace folder in the top-left. Finished songs are saved directly into it.
  2. Fill in Style / Prompt and Lyrics in the Studio panel.
  3. Select Submit. The first run loads the models, so it takes longer than later runs.
  4. Play the result from the Results list on the left.
First run: loading the models takes a few seconds and occupies memory until you unload them. This is expected — see Backend & VRAM.

2. Top bar

ControlWhat it does
Workspace pathSelect the folder for this project. Generated songs are written to the folder root as Song title.mp3; a duplicate name gets (2), (3), and so on.
Engine control (bolt)Loads or unloads the MusicCore engine by hand. Red means models are missing. An outlined bolt means ready but unloaded — select it to load. A pulsing filled bolt means loaded — select it to unload and free the memory.
Settings (gear)Opens Host Settings: language, appearance, transparency, background, MCP server, and MusicCore inference backend.
The engine has no idle timeout. Once loaded it stays in memory until you unload it or close VuuWave. If you are switching to another GPU-heavy application, unload it first.

3. Studio: describing the song

FieldHow to use it
TitleBecomes the output file name, so keep it filename-safe.
BPMTempo in beats per minute. Leave empty to let the model choose.
KeyFor example C major or A minor.
DurationSong length in seconds. Generation time scales roughly linearly with this value.
Style / PromptGenre, instrumentation, mood, production feel. Concrete beats vague: warm lo-fi hip hop, dusty piano, vinyl noise, relaxed works better than nice music.
LyricsThe words that actually get sung. Write them out in full.
Pure instrumentalTurn on for a track with no vocals.
Reference audioOptional. Guides the result toward an existing track's character.
Lyrics are literal. Whatever is in the field gets sung. A placeholder such as [write chorus here] is sung as those words. Leave the field empty, or enable Pure instrumental, if you do not want vocals.

4. Results

The left panel lists everything generated in the current workspace. Each result offers:

ActionWhat it does
Play / Pause / StopPreview the track in place, with a waveform drawn from the real audio.
Use as referenceFeeds this track back in as reference audio for the next generation.
Reuse prompt and parametersReloads the exact settings that produced this track into the Studio panel, ready to adjust.
DeleteRemoves the result.
RefreshRescans the workspace folder.

Generation settings are embedded inside each MP3 or WAV file, which is what makes Reuse prompt and parameters work. Re-exporting a file through a third-party audio editor can strip that data; the file still plays, but its settings can no longer be recovered.

Switching workspaces changes which folder the list reads. Songs in the previous workspace are left untouched.

5. Agent panel

The right panel is the shared VuMos Agent V17, the same assistant used across Vuu products. It can read the current draft, write lyrics, propose a style prompt, and fill in and submit a generation for you.

Useful requests

The Agent can answer questions about VuuWave itself; it reads this guide when asked how something works. Its control bar offers model and mode selection, history, new chat, clear chat, and Agent Settings, which are shared with the same Agent in other Vuu products.

The Agent model shares your GPU. A large Agent model and the music engine both occupy video memory at the same time. This is the single most common cause of slow generation — see the next section.

6. Inference backend and video memory

This section explains the one performance problem you are most likely to hit, and how to avoid and recover from it.

6.1 The symptom

Generation that normally finishes in seconds suddenly takes minutes. The GPU reports 100% usage, but the card stays cool and quiet and its power draw is low. Once this starts, it does not get better on its own — and it stays slow even after you unload the Agent model.

6.2 What is happening

Your graphics card has a fixed amount of fast video memory (VRAM). The music engine and the Agent language model both need a share of it. When their combined demand exceeds what the card has, Windows silently moves part of the data out of VRAM into ordinary system memory, which the GPU can only reach across a much slower connection. The work still runs on the GPU — it just spends most of its time waiting for data. That is the low-power, high-usage pattern.

This does not reverse itself. Windows does not move the data back once your memory frees up. Unloading the Agent, or waiting, will not restore speed. Recovery requires restarting the engine process — see 6.4.

6.3 How to avoid it

VuuWave will refuse to start a generation when free video memory is critically low, and tells you so rather than starting a run that would crawl. This is a guard, not a guarantee — a job that fits at load time can still exceed the card at its peak.

6.4 How to recover once it is slow

  1. Open Settings → MUSICCORE INFERENCE and select Restart kernel. This is the quickest route.
  2. If that does not help, close VuuWave completely and reopen it.
  3. If generation is still slow after a full restart, the graphics driver itself may be in a bad state. Press Win+Ctrl+Shift+B to restart the display driver — the screen blinks once, open applications are unaffected.

6.5 Choosing a backend

Under Settings → MUSICCORE INFERENCE you choose how the music engine runs. The choice is fixed while the engine runs, so changing it restarts the kernel.

BackendCharacterChoose it when
Vulkan (GPU)Much faster, but depends on having enough video memory. If it runs short, speed collapses as described above.Default. Your card has room for the models you use.
CPUSlower, but completely predictable — the same request always takes about the same time, scaling with the song's length. Uses no video memory at all.Video memory is tight, you are running a large Agent model, or you want a run that cannot degrade partway through.

Measured on one test machine (RTX 5070 12 GB, 24-core CPU) as a rough sense of scale, not a specification: a 30 second song took about 6 seconds on Vulkan and about 53 seconds on CPU; a 200 second song took about 7 minutes on CPU. Your results will differ with hardware.

6.6 The two Vulkan options

OptionWhat it means
Bias the driver against demoting our VRAMLeave on. It asks the graphics driver to move some other application's data out first, if something has to be moved. It is only a request — it cannot reserve memory, take memory back from another program, or undo a slowdown that already happened.
Allow spilling into shared memoryLeave off. Off means an oversized model simply fails to load, with a clear error, instead of loading and then running many times slower. Turn it on only when you deliberately want to run a model too large for your card and accept the speed penalty.

7. Settings

8. Common questions

Generation suddenly became very slow.

Almost always video memory. See section 6 — restart the kernel from Settings to recover, then reduce what is loaded at once or switch to the CPU backend.

The bolt icon is red.

The model files are not installed yet. VuuWave opens the MusicCore resource download page automatically; download the separate GenPack and wait for the progress bar and extraction to finish.

Why does the first generation take longer?

Models load on first use. Later runs in the same session reuse them.

Closing VuuWave left memory occupied.

Close the window normally rather than ending the process from Task Manager. A normal close unloads the engine and shuts the kernel down; force-ending it mid-generation can leave the graphics driver holding memory, which then needs a driver or system restart.

Can I run VuuWave on a server without a GPU?

Not practically. The models need roughly 8 GB of memory just to load, and the CPU backend on a fast desktop processor takes minutes per song — a small virtual server cannot do it at all.

My song file lost its settings.

Re-exporting through a third-party audio editor discards the embedded generation data. Keep the original file if you want to reuse its settings.

How do I get help?

Ask in the Agent panel on the right. It can read this guide and answer questions about how VuuWave works.