Music Flamingo

Music Flamingo

Lets you try NVIDIA's Music Flamingo models on music audio in a Gradio page, on ZeroGPU hardware at Hugging Face. For researchers and developers who work with audio and music.

Made by nvidia on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Music Flamingo is an NVIDIA Space for trying the Music Flamingo models in a Gradio page. It names the nvidia/music-flamingo-hf and nvidia/music-flamingo-2601-hf models, and it runs on ZeroGPU hardware, so you can use it in a browser with nothing to install.

Who it suits: It suits researchers and developers who work with music or audio and want to see what these models do before building on them.

Industry | Who uses it | How they use it | Example
Audio research | Researchers | Try the models on music clips | Open the Space and load a short clip
Software | Developers | Check whether the models fit a music feature | Read app.py to see how the models are called
Music and media | Creators | Explore what an audio model says about music | Try a few clips and compare

If you work only with text or images, you can skip it.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• A local copy of the files, run on Python 3.12 under Windows, macOS or Linux

Use case | Who | What they get back
Try the models | Researchers | Results from the Music Flamingo models on audio
Check feature fit | Developers | A hands-on feel for what the models can do
Study the code | Developers | A short app.py to read

How to set it up:

• A web browser, which is all the online page needs
• Python 3.12 and the packages in requirements.txt, for a local copy
• The system packages in packages.txt, installed with apt-get

1. Open the Space's page on Hugging Face to use it online. Nothing needs installing.
2. For a local copy, install the Hugging Face hub package and download the Space's files.
3. Move into the downloaded folder.
4. Install Gradio 5.49.1, then the packages from requirements.txt.
5. Start the app with python app.py.

pip install -U huggingface_hub
hf download nvidia/music-flamingo --repo-type space --local-dir music-flamingo
cd music-flamingo
pip install gradio==5.49.1
pip install -r requirements.txt
python app.py

How to use it: Open the page, or the one your local copy starts, and follow the controls the Gradio interface shows. The README lists no controls, so the page itself is the guide.

Example: Open the Space and give it a short piece of music. The page runs the model on that audio and shows what it returns.

For newcomers and experts: Open the Space page and try one short clip first. Nothing needs installing, and you see what the models do before you decide to copy the code.

The Space names four models and one dataset: nvidia/MF-Skills appears as both. The repository holds app.py, requirements.txt and packages.txt, and the README says nothing about how the models are used, so app.py is the place to read.

You give the page some audio
app.py passes it to a Music Flamingo model
The model processes the audio
The page shows what comes back

Good to know: The README is only a configuration header, so the details of inputs and limits are not documented.

• License: Apache 2.0
• Cost to run: none named, and the online copy runs on ZeroGPU hardware
• Data it reaches: the audio you give it and the models the Space names

On Hugging Face, 13 November 2026

• Likes: 221
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/nvidia/music-flamingo
• Files: https://huggingface.co/spaces/nvidia/music-flamingo/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.