The vOICe vision technology for the totally blind offers the experience of live camera views through sophisticated image-to-sound renderings. In theory this use of digital senses could lead to synthetic vision with truly visual sensations ("qualia") through crossmodal sensory integration, by exploiting the existing multisensory processing and neural plasticity of the human brain through training and education. The vOICe implements a form of sensory substitution where the goal is to bind visual input to visual qualia with a minimum of training time and effort, and improve quality of life (QoL) for blind users. The vOICe also acts as a research vehicle for the cognitive sciences to learn more about the dynamics of large-scale adaptive processes, including attention and expectation guided bottom-up and top-down learning processes, and involving cross-modal neuromodulation in the human brain. Neuroscience research has already shown that the visual cortex of even adult blind people can become responsive to sound, and sound-induced illusory flashes can be evoked in most sighted people. The vOICe technology may now build on this with live video from an unobtrusive head-mounted camera encoded in sound. The extent to which cortical plasticity and dynamic rerouting allow for functionally relevant rewiring or unmasking of neural pathways in the human brain is under investigation. Apart from functional relevance, a cross-modal binding for inducing visual sensations through sound (mental imagery and artificial synesthesia) would also be of great psychological importance. The possible role of The vOICe perceptual interface technology in cross-modal neuromodulation and synesthetic effects is being explored and developed under the Open Innovation paradigm together with many R&D partners around the world. Any potential clinical uses of The vOICe technology will be investigated only through qualified research partners in accordance with applicable laws and regulations. Possible future extensions include support for sonar, binocular vision, object recognition, eye-tracking and brainwave entrainment as neural engineering ingredients in a highly modular, adaptive and preferably non-invasive and unobtrusive brain-computer interface and cognitive vision system for augmented perception and augmented cognition.