MiniMax Releases MiniMax-Music3: An Open-Weights Music Model Generating Complete Five-Minute Songs From Lyrics and a Structured Caption
MiniMax released MiniMax-Music3, an open-weights text-to-music model capable of generating up to five-minute songs from lyrics and structured captions in a single pass.
MiniMax has unveiled MiniMax-Music3, a generative audio model designed to create full-length musical tracks. The system accepts input in the form of lyrics with section tags alongside a structured caption to guide the composition.
The model operates as an open-weights release, allowing developers to access and potentially fine-tune the architecture. It outputs audio as 32 kHz, 16-bit stereo WAV files, maintaining quality suitable for various production needs.
A key feature is the ability to generate complete songs lasting up to five minutes in a single pass. This addresses common limitations in earlier text-to-music tools that often struggled with coherence over longer durations.
By providing open weights, MiniMax contributes to the broader ecosystem of generative AI tools. This release positions the company competitively within the landscape of AI music generation, offering users more control over the creative process.
This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.