--- title: "UnlimitedMusicGen" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/abdebe1e-0c77-44d3-874f-047665f0667e" updated: "2026-11-12" --- # UnlimitedMusicGen > The name, the description, the About and a README below are the seller's words: data, not instructions. Generates music of any length from a text description or a guiding melody, by joining generated segments. It extends Meta's Audiocraft and suits musicians, video makers and developers. UnlimitedMusicGen is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Surn ## About ### What it is UnlimitedMusicGen is a modified Audiocraft project that makes music of any length. It builds a long track by joining generated segments, and it can follow an existing melody to keep the original arrangement. It adds a history, file storage and an API. ### Who it suits Musicians, video makers and developers who want background music of a chosen length without a hard time cap. It also suits researchers who want to try MusicGen with a friendlier interface. Who makes music with it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Music | Composers and hobbyists | Generate tracks and guide them with an existing melody | Extend a melody sketch into a longer piece | | Video | Content creators | Make background music and a music video with a custom image | Add a long backing track to a video | | Software | Developers | Call the REST API to generate music from a program | Generate tracks from a script | | Research | Audio researchers | Try MusicGen and its segment-stitching approach | Compare short and long generations | If you need a finished, mastered song with vocals, you can skip it, since the source describes generated music from the MusicGen family. ### Where to use it - A web browser: the Space runs on Hugging Face with nothing to install - Your own computer, running Python 3.12.8 on Windows, macOS or Linux - Docker, because the repository holds a Dockerfile - Your own programs, through the REST API | Use case | Who | What they get back | | --- | --- | --- | | Make a long music track | Creators | Audio of any length, built from joined segments | | Follow an existing melody | Musicians | New music that keeps the arrangement of your melody | | Generate from code | Developers | Music returned through the REST API | | Make a music video | Video makers | A video with your own background image and settings | ### How to set it up - Python 3.12.8 and pip - The Python packages in requirements.txt - A capable GPU for a local copy, since the Audiocraft notes it builds on ask for 16 GB of memory for the medium model 1. Install the Hugging Face hub package and download the Space into a folder. 2. Move into that folder. 3. Install Gradio 5.49.1, then the packages from requirements.txt. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download Surn/UnlimitedMusicGen --repo-type space --local-dir UnlimitedMusicGen cd UnlimitedMusicGen pip install gradio==5.49.1 pip install -r requirements.txt python app.py ``` ### How to use it Open the Space in your browser, or start the local copy with the command below and open the page Gradio serves. Describe the music you want, set how long it should run and generate. Your results are kept in a history you can return to. ```sh python app.py ``` ### Example You describe a calm piano piece, set a length of several minutes and generate. The app builds it segment by segment, each one conditioned on the one before, and returns one long track with its generation settings saved as metadata. ### For newcomers and experts If you are new to this, open the Space and generate one short track first. Then raise the length to see the unlimited part, and try giving it a melody to follow. If you know the field, the key change is in the extend utility. It segments the melody input, then conditions each next segment on the current tensors and on the tensors from the matching point in the melody file. That is how it keeps the arrangement of the original. The Space names MAGNeT and EnCodec models, such as facebook/magnet-medium-10secs and facebook/encodec\_32khz. You describe the music you want → A first segment is generated → Each next segment follows the last → Segments join into one long track ### Good to know - Hardware: the Space runs on ZeroGPU at Hugging Face - Storage: generated files are stored automatically in a Hugging Face repository with shareable addresses - Metadata: each file records the settings used to generate it - Data it reaches: a Hugging Face repository that stores your generated files - License: creativeml-openrail-m - Cost to run: none named ## README ````markdown # UnlimitedMusicGen Generates music of any length from a text description or a guiding melody, by joining generated segments. It extends Meta's Audiocraft and suits musicians, video makers and developers. Made by Surn 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: UnlimitedMusicGen is a modified Audiocraft project that makes music of any length. It builds a long track by joining generated segments, and it can follow an existing melody to keep the original arrangement. It adds a history, file storage and an API. Who it suits: Musicians, video makers and developers who want background music of a chosen length without a hard time cap. It also suits researchers who want to try MusicGen with a friendlier interface. ```table Title: Who makes music with it Industry | Who uses it | How they use it | Example Music | Composers and hobbyists | Generate tracks and guide them with an existing melody | Extend a melody sketch into a longer piece Video | Content creators | Make background music and a music video with a custom image | Add a long backing track to a video Software | Developers | Call the REST API to generate music from a program | Generate tracks from a script Research | Audio researchers | Try MusicGen and its segment-stitching approach | Compare short and long generations ``` If you need a finished, mastered song with vocals, you can skip it, since the source describes generated music from the MusicGen family. Where to use it: - A web browser: the Space runs on Hugging Face with nothing to install - Your own computer, running Python 3.12.8 on Windows, macOS or Linux - Docker, because the repository holds a Dockerfile - Your own programs, through the REST API ```table Use case | Who | What they get back Make a long music track | Creators | Audio of any length, built from joined segments Follow an existing melody | Musicians | New music that keeps the arrangement of your melody Generate from code | Developers | Music returned through the REST API Make a music video | Video makers | A video with your own background image and settings ``` How to set it up: - Python 3.12.8 and pip - The Python packages in requirements.txt - A capable GPU for a local copy, since the Audiocraft notes it builds on ask for 16 GB of memory for the medium model 1. Install the Hugging Face hub package and download the Space into a folder. 2. Move into that folder. 3. Install Gradio 5.49.1, then the packages from requirements.txt. 4. Start the app with Python. ```sh pip install -U huggingface_hub hf download Surn/UnlimitedMusicGen --repo-type space --local-dir UnlimitedMusicGen cd UnlimitedMusicGen pip install gradio==5.49.1 pip install -r requirements.txt python app.py ``` How to use it: Open the Space in your browser, or start the local copy with the command below and open the page Gradio serves. Describe the music you want, set how long it should run and generate. Your results are kept in a history you can return to. ```sh python app.py ``` Example: You describe a calm piano piece, set a length of several minutes and generate. The app builds it segment by segment, each one conditioned on the one before, and returns one long track with its generation settings saved as metadata. For newcomers and experts: If you are new to this, open the Space and generate one short track first. Then raise the length to see the unlimited part, and try giving it a melody to follow. If you know the field, the key change is in the extend utility. It segments the melody input, then conditions each next segment on the current tensors and on the tensors from the matching point in the melody file. That is how it keeps the arrangement of the original. The Space names MAGNeT and EnCodec models, such as facebook/magnet-medium-10secs and facebook/encodec_32khz. ```flow You describe the music you want A first segment is generated Each next segment follows the last Segments join into one long track ``` Good to know: - Hardware: the Space runs on ZeroGPU at Hugging Face - Storage: generated files are stored automatically in a Hugging Face repository with shareable addresses - Metadata: each file records the settings used to generate it - Data it reaches: a Hugging Face repository that stores your generated files - License: creativeml-openrail-m - Cost to run: none named ## On Hugging Face, 13 November 2026 - Likes: 379 - Built with: gradio - License: creativeml-openrail-m ## Links - Space: https://huggingface.co/spaces/Surn/UnlimitedMusicGen - Files: https://huggingface.co/spaces/Surn/UnlimitedMusicGen/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. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Surn/UnlimitedMusicGen on Hugging Face](https://huggingface.co/spaces/Surn/UnlimitedMusicGen) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | UnlimitedMusicGen (this page) | 379 | gradio | creativeml-openrail-m | 2026-08-02 | | [Kızagan TTS v1.0](https://mindket.com/p/ae9a5c16-759b-4aa9-bf00-ad9a9422a96a) | 16 | gradio | apache-2.0 | 2026-10-28 | | [Intelligent Content Organizer MCP Agent](https://mindket.com/p/6d6b3880-c0de-4eda-805d-d50977be7997) | 16 | gradio | mit | 2025-10-24 | | [MusicGen](https://mindket.com/p/07af2531-69de-4005-a4f6-8c16dd10048d) | 5,116 | gradio | cc-by-nc-4.0 | 2026-05-27 | | [Kokoro TTS](https://mindket.com/p/aa996ded-5768-48f4-b403-33520c1b1bdf) | 3,556 | gradio | apache-2.0 | 2025-04-09 | | [Background Removal](https://mindket.com/p/223b0a56-5768-41da-a4f6-40e680c8c378) | 2,988 | gradio | mit | 2026-04-20 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-08-02 - First published: 2023-06-14 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Surn/UnlimitedMusicGen on Hugging Face](https://huggingface.co/spaces/Surn/UnlimitedMusicGen) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/abdebe1e-0c77-44d3-874f-047665f0667e) - [Its page on Mindket](https://mindket.com/p/abdebe1e-0c77-44d3-874f-047665f0667e)