GRUV
MattVitelli/GRUVReviewed by AI
Checked by RepoPicks Radar on
What is GRUV?
GRUV is a small set of Python scripts from a 2015 university project. You copy your own music into a folder, run one script to convert it, another to train a neural network on the raw audio, and a third to produce a generated_song.wav file. There is no interface and no installer: you install Python plus Theano, Keras, NumPy, SciPy, h5py and the LAME and SoX audio converters, and run commands in a terminal. The README says the result often sounds like near-copies of the songs used for training. The code has not changed since 2020.
GRUV is free and can replace Suno.
How easy is it to install GRUV?
D · terminal, several tools or a specific graphics card · Windows
- Windows D
- macOS D
- Linux D
On Linux, the easiest case, you still install Python and seven separate libraries and command-line tools (Theano, Keras, NumPy, SciPy, h5py, LAME, SoX) and run three commands in a terminal; training is slow and the README talks about graphics-card memory errors. Windows and macOS are the same work, with the extra difficulty that LAME, SoX and Theano are harder to set up there.
Coming soon: install in 1 click with the RepoPicks app.
GRUV on GitHub
- Stars
- 797on Nov 10, 2026
- Downloads
- —all releases
- Growth
- +1stars in 6 days
Stars over time
Facts
- Runs on
- Windows, macOS, Linux
- You need to install
- Python, Other tools
- Disk space
- not determined
- Accounts or keys
- None
- Cost
- Free
- License
- No license (No license)
- Can replace
- Suno
- Last change on GitHub
- Nov 28, 2020
GRUV risk signals (4)
- Attentionobsolete pinned dependencies
README.md: "Note: This code works with Keras v. 0.1.0, later versions of Keras may not work." It also requires Theano, a library that was discontinued. Installing these old versions today is likely to fail.
AI review
- Attentionunmaintained since 2020
Last commit 2020-11-28 (2170 days before the check), no releases, and 27 open issues.
AI review
- InfoNo license detected
No license detected by GitHub, the license file, the LICENSES folder or the winget manifest
automatic check
- Infooutput may copy training songs
README.md: "Our current generation scheme uses the training / testing data as a seed sequence, which tends to produce verbatum copies of the original songs." What it generates can repeat the music you fed it, which matters if that music is not yours.
AI review
Evidence is shown in its original language.
What Radar could not check about GRUV
- Whether the old Theano and Keras 0.1.0 versions can still be installed and run at all today
- How long training takes and how much memory or graphics-card memory is needed for a given music library
- How much disk space the converted .npy data files take for your songs
- The real musical quality of the generated audio