Facts
- Noted
- generates songs with vocals from text prompts · 2026-08-15
- Noted
- supports Japanese vocals · 2026-08-15
- Noted
- can produce tracks up to five minutes long · 2026-08-15
- Noted
- free to use · 2026-08-15
- Noted
- can run locally · 2026-08-15
- Noted
- demo app available on Hugging Face · 2026-08-15
- Noted
- extends the company's open-model push into music generation · 2026-08-15
Connections
Structured graph also available as JSON at /public/entities/minimax-music3.
CC BY 4.0.
Aug 15
Chinese AI developer MiniMax released the music generation AI MiniMax-Music3 on August 14, 2026. The model generates songs with vocals from text prompts, supports Japanese vocals, and can produce tracks up to five minutes long. It is free to use and can run locally, with a demo app available on Hugging Face.