Touchscreens and buttons had became a medium for virus transmission during the COVID-19 pandemic. We have seen in our daily life that people use tissues and keys to press buttons inside elevators, on public screens, etc. In the post-COVID world, touch-free interaction with public touchscreens and buttons may become more popular. Motivated by the rise of visible light communication and sensing, we design a real-time embedded system to enable touch-free fingertip writing of the digits 0–9 with only ambient light and simple photodiodes. We propose an embedded deep learning model to learn the spatial and temporal patterns in the dynamic shadow for air-writing digits recognition. The model is devised with a lightweight convolutional architecture such that it can run on a resource-limited device. We evaluate our model using the LightDigit dataset [1] and report the results in terms of accuracy and inference time. LightDigit dataset. It is a new air-writing digits dataset collected by a researcher going through 70000 images in the MNIST dataset [2] and replicating them with air-writing and ambient light to obtain time-series information. The dataset contains 20880 instances of air-writing digits 0–9. Each instance has 500× 9= 4500 samples (ie, samples per photodiode× number of photodiodes). For more details about the LightDigit dataset please refer to [1].