Abstract
PictoVoice is an image-to-speech system designed to assist users in understanding visual information through
spoken descriptions. The system accepts an image as input and processes it to extract relevant visual features, which are
then used to generate a meaningful textual caption. The generated caption is subsequently converted into speech, enabling
users to understand the contents of an image through audio output. The system integrates image processing, visual feature
extraction, image captioning, and speech generation into a unified pipeline. Multilingual support for languages is currently
being implemented to improve accessibility for users from diverse linguistic backgrounds.