Skip to content
latestai.eulatestai.eu

Open-weights text-to-music model from MiniMax that generates songs with vocals and lyrics across genres and languages.

Available in EUMusicModel

Updated EU status checked Last shown

MiniMax Music 3 at a glance

What is MiniMax Music 3?
MiniMax Music 3 is a model from MiniMax. Open-weights text-to-music model from MiniMax that generates songs with vocals and lyrics across genres and languages.
Who makes MiniMax Music 3?
MiniMax Music 3 is made by MiniMax.
Does MiniMax Music 3 work in the EU?
Available in the EU. Open weights can be downloaded and run locally anywhere, and no EU exclusion was found in the provided material. The license text was not reviewed. Last verified 14 Nov 2026.
How much does MiniMax Music 3 cost?
Open source. Weights are free to download and run locally. Hosted API pricing was not found in the provided material.
Where was MiniMax Music 3 shown?
In 2 creator videos by AI Search. Most recently by AI Search on 16 Aug 2026, at 31:03 in “New Deepseek, GLM 5.3, Grok 4.6, LTX 2.5, Qwen 3.8, Gemini 3.7: AI NEWS”.

Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.

About

MiniMax Music 3 (listed by MiniMax as Music 3.0) is an open-weights music generation model. It takes a text style prompt and structured lyrics and produces full songs with vocals, covering multiple genres and languages. MiniMax describes it as a production-ready, versatile music model.

According to creator reports, the full model is about 9.8 GB, with an int8 version intended for lower-end GPUs and a smallest quantized version of about 2.5 GB. It can be run locally in ComfyUI, and ComfyUI has a tutorial page for it. One reviewer measured about 3-4 minutes to generate a 1-minute song on a 16 GB VRAM GPU.

Reviewers note that quality is below the latest Suno models and that the model currently supports text-to-music only. It is aimed at users who want local or self-hosted music generation rather than a hosted service. The license terms were not stated in the provided material.

Key features
  • Text-to-music with vocals and structured lyrics
  • Multiple genres and languages
  • Open weights, runnable locally in ComfyUI
  • Quantized variants (int8, smallest about 2.5 GB) for lower-VRAM GPUs
  • Text-to-music only at present
2 moments

As seen on YouTube

Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.

AI
AI Search15 Aug 2026
Live demo
The BEST local AI music generator is here!

Open-source text-to-music model with vocals and lyrics across genres and languages. Smallest quantized version is 2.5 GB. The creator installs it in ComfyUI and runs it locally; a 1-minute song took about 3-4 minutes on 16 GB VRAM. Quality is below the latest Suno models, and it is text-to-music only for now.

Keep exploring

Similar AI tools

Closest neighbours by meaning, not just by category.