Check its license. It has its own license: read it before using it for work.

Is waivepulse still maintained?

Yes, active. Last change 5 days ago.

Can I trust waivepulse?

New, little track record. 27 stars, 6 months old. Look at the code and the owner before running it.

gitmanual

Reading the repo

Opening the box…

How to install waivepulse on macOS (weellio/waivepulse) · gitmanual

How to install on macOS

weellio/waivepulse

Local offline AI music generation and some editing - lyrics + genre tags → MP3 with vocals

Python#ai#awesome-ai-music#daw#generation

Before you start

Is it free?: Check its licenseIt has its own license: read it before using it for work.
Still maintained?: Yes, activeLast change 5 days ago.
Can I trust it?: New, little track record27 stars, 6 months old. Look at the code and the owner before running it.

Difficulty: Moderate
Time: about 15 min
Stars: ★ 27
Activity: Updated this month

Saved setup from 4 h ago

Will it work on macOS?

Yes, it runs on macOS

You'll build it yourself with Python.

Your system

macOS Windows Linux

Start here

Website ↗waivepulse.comThe project's own site.

Setup script in the repo

The maintainers included setup.sh. Run it from the cloned folder after reading it.

bash setup.sh

Also: start.sh, setup.bat, start.bat

3 steps on macOS

Download setup.sh

Then run bash setup.sh. It stops at the first error and is safe to run again. Servers and tests aren't started; it lists them at the end. Read it first.

Clone the repository

Needs Git: xcode-select --install

git clone https://github.com/weellio/waivepulse.git
cd waivepulse

2
Install the required runtimes
Python 3.x (no version pinned)
```
brew install python
```

Install dependencies

python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

From the README: Quick start

First-time setup (run once)

Windows:

setup.bat

Linux:

bash setup.sh

The script installs Python, ffmpeg, and git if missing; checks your NVIDIA and CUDA versions; creates a Python virtual environment; installs PyTorch with the right CUDA build, heartlib, and dependencies; then downloads the HeartMuLa weights (~21 GB).

The default install location is ~/HeartMuLa/ (Linux) or %USERPROFILE%\HeartMuLa\ (Windows). To install somewhere else, set WAIVEPULSE_VENV and WAIVEPULSE_CKPT before running setup.

Launch (every time)

Windows:

start.bat

Linux:

bash start.sh

Open http://localhost:7861 in any browser. The launcher kills any old server process on port 7861 before starting.

Did you get it running?

No reports for macOS yet.

Still stuck? Get a written guide

GitManual AI Agent reads the 2 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.