88Z AI, 13 April — MiniMax releases Music 2.6 model with new Cover adaptation feature, optimized performance for traditional Chinese instruments, mid-low frequencies, and vocals. First packet latency is under 20 seconds, supporting precise instruction control, with three open-source Music Skills.
At a glance
- New Cover feature supports style and arrangement adaptation based on original songs
- First packet latency reduced to under 20 seconds with three open-source Music Skills
The update
MiniMax has officially launched its new AI music generation model, Music 2.6. This version introduces a Cover feature, allowing users to adapt styles and arrangements based on existing songs. In terms of audio quality, the model focuses on optimizing the temporal evolution logic of traditional Chinese instruments, enhancing mid-low frequency performance, and improving vocal naturalness. Regarding performance, the first packet latency has been reduced to under 20 seconds, while supporting precise instruction control for parameters such as BPM, tonality, and segment structure. Additionally, MiniMax has open-sourced three Music Skills for Agent integration and invocation.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- MiniMax 稀宇科技Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.