%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
On September 12, MiniMax released its new music generation model, Music1.5, which marks a new breakthrough in AI music creation and opens up a new era of "one person is a band." Music1.5 not only extends the duration of generated music to 4 minutes but also features four major breakthroughs: strong controllability, natural and full vocals, rich orchestration layers, and clear song structures.
Music1.5 supports music creation up to 4 minutes, producing finished works instead of just demo samples. It allows users to customize and have strong control over the style, mood, and scene of a song. Users need only provide a simple natural language description, and Music1.5 will deliver a highly completed work. In advanced mode, users can also arrange specific lyrics for different parts of the song, such as the intro, verse, and chorus. Music1.5 supports customizing music features with 16 styles × 11 moods × 10 scenes, generating different vocal tones and singing styles. The sound is more transparent and realistic, with natural and full tone, smooth transitions without breaks, greatly enriching the emotional expression of songs.
In terms of orchestration, Music1.5 models instruments with fine-grained modeling, making the orchestration rich, the instrument layers clear, and the playing techniques varied. It also supports the generation of less common and ethnic Chinese instruments, such as multiple traditional Chinese folk instruments in the song "Jiangnan Rain and Poetry." In addition, Music1.5 achieves clear distinctions between the intro, verse, and chorus sections, with a clear chorus climax and a natural ending, providing a true "narrative-level" auditory experience.
These breakthroughs are based on MiniMax's self-developed capabilities in multi-modal areas such as text, speech, and vision. Music1.5 uses the power of text models to have a stronger understanding and control over text descriptions. It not only allows overall control over the style, emotional color, and applicable scenarios of a song, but also enables fine-grained control over vocal characteristics, generating vocal tones with different qualities.
Music1.5 is suitable for various scenarios, including using AI to inspire professional music creation, quickly customizing background music for films, games, and short videos, creating songs and MVs for virtual idols, and generating exclusive audio content for corporate brands. Additionally, Music1.5 also provides APIs for global developers, continuing to offer the highest cost-performance globally. Whether it's an application, tool, or creative workflow, it can be easily integrated, making AI become a "24-hour creative partner."
The release of Music1.5 not only lowers the barriers to music creation but also returns to the essence of hearing, allowing "good-sounding" music to naturally happen. The model is now available worldwide. Users can log in to minimaxi.com/audio/music immediately to experience it and create their next hit single.