Ararat Music Studio

Ararat Music Studio

Makes music tracks from a text description, carries the style of an audio reference into a new track, or rearranges a recording while keeping its melody. For musicians and creators, with Armenian and eastern presets.

Made by Vadim777511 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: Ararat Music Studio is a Russian-language web studio built on the open ACE-Step 1.5 model. It makes a track from a written description, borrows the style of a reference recording, or rearranges that recording while keeping its melody and form.

Who it suits: Musicians, video creators and arrangers who want a quick draft of a song or a backing track. The presets lean toward Armenian and eastern sounds, including the duduk.

Industry | Who uses it | How they use it | Example
Music | Independent musicians | Draft a track from a description | Describe an instrumental piece with a duduk
Content creation | Video creators | Make a vocal or instrumental backing track | Choose a vocal language and a length
Production | Arrangers | Rearrange a recording and keep its melody | Add a WAV file and pick the keep-melody mode

People who need a finished, mastered release straight from the tool can skip it.

Where to use it:

• A browser: the Space runs on Hugging Face with nothing to install
• Windows, macOS or Linux: run a copy of the Space with Python 3.12

Use case | Who | What they get back
Track from a description | Musicians | An instrumental or vocal track
Style from a reference | Creators | A new track that follows the reference's style
New arrangement | Arrangers | A reworked version that keeps the melody and form

How to set it up:

• Python 3.12 with pip on Windows, macOS or Linux
• The Python packages listed in requirements.txt
• A Hugging Face account if you use the free ZeroGPU quota, which is limited

1. Install the Hugging Face hub package.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio 6.2.0 and the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download Vadim777511/ararat-music-studio --repo-type space --local-dir ararat-music-studio
cd ararat-music-studio
pip install gradio==6.2.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space page in a browser, or start your own copy with the command below. Write what the music should be like, or add a reference recording in WAV, MP3, FLAC, OGG or M4A. Then choose tempo, length and vocal language.

python app.py

The app offers two reference modes, one that follows the reference's style and one that keeps its melody. You can export the result as an MP3 at 320 kbps.

Example: You describe a calm instrumental piece with a duduk, set a tempo and a length, and run it. The app makes a track from that description, which you can export as an MP3.

For newcomers and experts: If you are new, open the Space and start with a short written description and no reference. The first run takes longer because the model downloads at that point.

For experts, the app is a single app.py on Gradio 6.2.0 that wraps ACE-Step 1.5 and runs on ZeroGPU hardware. The free GPU quota is small, so jobs may queue. The author notes that the model gives a musical result, not a guaranteed master.

You write a description or add a reference
You pick mode, tempo, length and language
ACE-Step 1.5 makes the track
You export the result as MP3

Good to know:

• License: mit
• Cost to run: a Hugging Face account for the limited free ZeroGPU quota, no other key named
• Data it reaches: an uploaded reference goes to a Hugging Face server, is deleted after processing, and results are kept only briefly
• Not for: confidential recordings, or releases made without checking your rights to the reference

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/Vadim777511/ararat-music-studio
• Files: https://huggingface.co/spaces/Vadim777511/ararat-music-studio/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.