Dedicated model · Available as managed deployment
Meta's MusicGen — a text-to-music model that generates music clips from a text description or an audio prompt, in a single-stage transformer. Validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only — an OpenAI-compatible endpoint on hardware only you use, operated by AxForge in the EU.
Why AxForge
| Music from a description | Genre, mood, instruments, tempo — describe it and MusicGen produces a clip; give it a melody and it follows it. |
|---|---|
| Your own music endpoint | Generation runs on a machine reserved for you; nothing is uploaded to a third-party music service. |
| Licence handled | MusicGen weights are released for non-commercial use; commercial use needs a licence from Meta, which AxForge arranges the deployment under. For a permissive model, see ACE-Step. |
Specifications
| Model | MusicGen — facebook |
|---|---|
| Modalities | Text → music / audio |
| Licence | Commercial licence needed — cc-by-nc-4.0; AxForge handles the licence where one is required |
| Hardware | NVIDIA DGX Spark (GB10, 128 GB unified memory) — owned and operated by AxForge |
| Rental term | Hour, week, month or year |
| Hardware pricing | €0.69/hour on demand · €0.66/hour by the week · €0.62/hour by the month · €0.55/hour by the year, excl. VAT |
| Managed service | Quoted per deployment |
| Region | Málaga, Spain (eu-es-1) |
Full details, benchmarks and FAQ on the MusicGen page. Prices exclude VAT.
How it works
| 1 | Request deployment — describe your traffic, context needs and rental term. |
|---|---|
| 2 | You receive the configuration, hardware rental and managed-service price in writing before anything is billed. |
| 3 | AxForge deploys MusicGen on a dedicated DGX Spark reserved for you. |
| 4 | Point your OpenAI SDK at your own endpoint with the model name you receive. |
| 5 | Adjust the term — hour, week, month or year — as your workload settles. |
Request deployment or sign in to start.
FAQ
Not on the serverless API — it is available as a managed deployment: validated on AxForge hardware and deployed on a dedicated DGX Spark for your traffic only. The serverless API serves Qwen3.8 27B.
Only with the appropriate licence — the weights are non-commercial. ACE-Step is the permissive alternative AxForge deploys the same way.
Short clips by default, extendable by continuation; AxForge confirms clip length and throughput with the deployment.
AxForge publishes only numbers it measures itself, and has not benchmarked this model on its nodes yet. For quality benchmarks, see the official model card.
Hardware by the hour, week, month or year; the managed service is quoted per deployment — both confirmed in writing before anything is billed.