Various implementations disclosed herein include devices, systems, and methods for performing scene-to-text conversion. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes obtaining environmental data corresponding to an environment. Based on the environmental data, a plurality of objects that are in the environment are identified. An audio output describing at least a first object of the plurality of objects in the environment is generated based on a characteristic value associated with a user of the device. The audio output is outputted.