Vocal editing
Choose sections from different takes and combine them. Edit individual pitches in the vocal editor or apply real-time pitch correction. Noise reduction and de-reverb are also included.
Record vocals and arrange MIDI. Connect an MCP client such as Claude to let AI edit the project directly.
In PowerShell, run Get-FileHash on the downloaded file and compare the result with this value.
A reduced interface for vocal recording, with a backing track and up to eight vocal tracks. Genre presets set up the vocal effects.
Multitrack audio and MIDI editing with direct control over track effects, routing and automation.
Remove vocals from a song and adjust its key and tempo. Includes synchronized lyrics, a guide melody and recording scores.
Choose sections from different takes and combine them. Edit individual pitches in the vocal editor or apply real-time pitch correction. Noise reduction and de-reverb are also included.
Edit notes and pedals in the piano roll, then view the same MIDI as a score. Export the score as a PDF or print it.
Built-in SFZ sampler, synthesizer and the GeneralUser GS SoundFont
Route audio through buses and sends, and use other tracks as sidechain inputs. Record knob and fader movements as automation.
Supports 64-bit VST3, CLAP and VST2 plug-ins.
Analyzes the song and builds a master chain for the selected template’s loudness target. Compare the processed and original audio, and check the LUFS and true peak measurements.
Separate a song into vocals and instrumental, or into vocals, drums, bass and other instruments. Processing runs on your PC without uploading the file.
The HTDemucs model is included in the installer. The UVR vocal separation model is an optional download.
An MCP client such as Claude can add tracks and edit MIDI and effects. Changes appear in llmuse and can be undone with Ctrl+Z.
Create a piano track and add Am, F, C and G chords, two bars each.
claude mcp add llmuse -- "C:\Users\<user>\AppData\Local\Programs\llmuse\llmuse-mcp.exe"
The MCP server is included. A separate AI client is required and its service may charge fees. Setup instructions are in USER_GUIDE.en.md in the install folder.
Synthesize vocals from a melody and Korean or Japanese lyrics using UTAU voicebanks. Edit pitch curves and vibrato for individual notes.
Namine Ritsu, Kasane Teto and Song-SoRi are available to download during setup or in the app. Each voicebank has its own terms of use.
A microphone and headphones are recommended for recording.
The installer isn't code-signed yet, so SmartScreen can't verify the publisher. Before you run it, get the file's SHA-256 with Get-FileHash in PowerShell and compare it with the value under Check the file below the download button. If they don't match, don't run it, and download it again from this site.
No. llmuse runs only on 64-bit Windows 10 and 11.
Yes, 64-bit VST3, CLAP and VST2 plug-ins. llmuse looks in the standard folders and the VST folders FL Studio installs, and you can add your own. FL Studio's own Fruity plug-ins only run inside FL Studio.
No. Stem separation runs on your PC and doesn't use the internet. HTDemucs comes with the installer, and the UVR vocal model is downloaded once, during setup or in the app.
Every voicebank has its own terms. For example, companies need a separate contract to use Kasane Teto, and Song-SoRi asks you to talk to its maker before earning money with it. llmuse shows a summary and a link to the terms before you download, but terms can change, so read the original before you release.
Install llmuse, then register llmuse-mcp.exe from the install folder as an MCP server in Claude Code or Claude Desktop. The exact command and settings are in USER_GUIDE.en.md in the same folder.
No. Once a day it checks a small version file on this website and tells you when a new version is out. It never installs anything by itself, and you can turn the check off in Settings.
Ask a question, report a bug or suggest an improvement. Add your e-mail address if you want a reply.
Freeware for Windows 10 and 11, 64-bit. No account needed.