Qosmo’s core technologies are now available for hire!
Our AI models and algorithms have been developed over the years of working on our flagship projects such as AI DJ. Our products range from music generation to timbre transfer and can be used in real-time via api or on-device, supporting a wide range of use cases.
Img2Sound finds the best environmental sound or music for a given image. It supports a wide range of images, and can find a high-quality match to a Google Street View photo of an arbitrary location. In the current version, input is limited to still images, and the future product roadmap to support video input.
Our music generation system can automatically compose and generate music by specifying the genre and characteristics of a song. The a number of control parameters can be set and changes will be reflected in real time, allowing nuanced operations to be dynamically performed in response to inputs such as body movements, biological data from sensors or the environmental conditions of a particular location.
This product performs timbre transfer based on real-time sound generation technology, which was previously considered challenging with deep learning models. It can convert any input sound into targeted sound timber such as drums, saxophone, voices etc. It can also be used to apply pre-trained effects such as reverb and distortion, or to remove them.
The accuracy of this algorithm has continuously improved over time with the development of our flagship project, called “AI DJ”. By letting deep learning based AI model “listen” to a library of music, we have succeeded in quantifying the relevance of each song, automating the song selection know-how by professional DJs.
Get in touch with us here!