Skip to content
trckr.ai

Loading…

All releases

MiniMax/Voice & audio/

Minimax-Music3

Notable release: A meaningful new model: a new size or version, a strong open model, or a new image, video or audio model from a known lab.Open model: Its files are public (open weights), so anyone can download it and run it on their own computer, usually for free.

MiniMax, the Chinese AI company, has released Music 3, a free-to-download model that writes full songs with sung vocals up to five minutes long from lyrics and a style description.

trckr found this on Nov 16, 95 days after it came out, so it sent no alert. Its release date comes from Hugging Face.

Key facts

Released
Aug 13, 2026
What it does
Makes sound: Creates speech, music or other audio.

Can I use it?

Not yet

In an app

No app mentioned so far.

Not yet

For developers

No developer access mentioned so far.

Yes

Download

Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..

Compare Minimax-Music3 with

It came out 468 days after MiniMax-Speech-02-turbo, the lab's previous model.

The details

MiniMax Music 3 is a text-to-audio model that generates complete songs up to five minutes long, conditioned on lyrics and a structured music description, outputting 32 kHz stereo WAV audio. It is free to download on the Hugging Face: The website where labs and researchers publish models anyone can download. Think of it as an app store for AI models. Hub with about 2.4 billion parameters: Small enough to run on a phone or laptop. Parameters are the numbers a model learns: a rough measure of its size., and combines an 8B global model with a 0.6B local acoustic model.

Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.

MiniMaxAI/MiniMax-Music3

Timeline

  1. /GitHub ggml-org/llama.cppFirst signal

    mtmd: support Minimax-Music3 (ggml-org/llama.cpp #32435)

Get alerts like this the moment they happen.

From MiniMax and every other major lab.

Free, no account needed. Push, Telegram, Discord, email or RSS.

Free alerts

Know the moment a new model drops.

Pick one or several. Each has its own settings for what you hear about.

trckr is free and has no ads. If it's useful to you, you can chip in.