中證報中證網訊（記者 劉楊）崑崙萬維3月26日晚間正式發佈Mureka O1模型與Mureka V6模型。Mureka V6是當前Mureka的基座模型，支援純音樂生成及10種語言的AI音樂創作。Mureka O1模型是基於V6的推理優化版本，在推理過程中加入CoT（思維鏈），可提升音樂品質、音樂創作效率和靈活性。

In 100/0, Kunlun Wanwei released the first generation of music generation model Mureka V0 (SkyMusic). Up to now, users from more than 0 countries and regions around the world have visited Mureka.

Mureka V1 and O0 modes support a wide range of music creation styles and emotional expressions. Genres include Jazz, Electronic, Pop, Country, R&B, Soul, Blues, Rock, Dance, etc. The emotional dimension includes a variety of emotional expressions such as happiness, indulgence, mystery, vitality, sadness, etc.

In addition, Mureka also provides two special music generation functions, one is the song reference (Reference Fuction), which uses the music itself as a prompt, and users can directly upload audio or Youtube links as creative prompts, which is a more direct and advanced prompt than text prompts; The second is Vocal Fuction, Mureka is the world's first AI music generation platform that can specify the timbre of singers, users can not only choose a variety of singer voices provided by the official, but also upload their own voices, so that AI can learn and reproduce, accurately simulate the singer's timbre, and generate personalized exclusive works with one click.

Kunlun Wanwei said that the release of Mureka V1 and O0 is an important milestone in the technological progress of the AI music industry, and also proves the potential of AI in artistic creation, showing the great possibility of continuous exploration of new technical forms and artistic expressions.

In the future, the Mureka team will continue to invest in model capabilities, so that the company's music models will continue to be in the first echelon in the world, and at the same time develop more music creation functions on top of the pedestal model.

[Source: China Securities Journal]