Av3ry is an AI program and a virtual persona, who is composing music, communicating with people and learning from interactions. Av3ry combines natural language processing, algorithmic composition, data crawling and machine learning. She*he is constantly operating and creates music, poems and pictures in the moment - based on communication with interacting users. The music pieces are based on the criteria specified by the users. So the result is instant and individual - and send directly to a single user. The program extracts key features from the description of the users and tries to generate the pieces accordingly. Through the feedback of the users after listening to the result the algorithm can learn and fine-tune its parameters. In the same way the language generation is updated and adjusted through the conversations.
All music generation done in Max. All Webhook Handling in Node in Max. Text Generation in JS in Max.