The project started with the idea of stitching audio and visuals together in a way to explore locations with the help of both sound and images. To visualise the information or the sounds, the first attempt was to capture the places, both through a camera and a recorder.

For one month across three cities, images and audio were collected. The aim was to capture the essence of different places across Delhi, Mumbai, and Dehradun, for example, the famous markets of Delhi, the local cuisine of Mumbai, and the temples of Dehradun. These places keep within themselves the essence of these regions.

The attempt is to empower users in a way where they can identify the locations on the basis of the sounds. Thus, they will be able to map these sounds in a better way. In the future, such systems can help locate areas on the web when only audio feed is available. This would give way to research in areas of geotagging, where anyone can upload a local sound and tag it to a specific location on the map. This would help to create immersive audio guides where people can go around a city collecting audio clues and thus exploring the city using the image suggestions and then finding those places in the real world.