Machine learning multimedia conversion assignment

A method and system for improving a machine learning multimedia conversion process is provided. The method includes automatically connecting hardware devices to a server hardware device. Audio and/or video data from a meeting between individuals is recorded form a location and each individual is identified via sensor data. Attributes for each user are identified and the audio and/or video data is converted to text data. Portions of the text data are analyzed and associated with each individual. Action items in the text data are identified and assigned to the individuals based on the attributes. Self-learning software code for executing future multimedia conversion processes is generated based on the assigning and the self-learning software code is modified based on results of executing the future multimedia conversion processes.