Creating videos is a complex and highly skilled task that traditionally demands significant manual labor. To overcome this challenge, we propose an AI-based innovative approach that automatically generates news videos by text, producing high-quality, photorealistic content suitable for various purposes, including advertisement, news, and educational material creation. By scaling AI technologies, our approach can bring an increase in efficiency while reducing production costs without compromising high standards of visual and editorial quality. This transmutation technology will fundamentally change video production into a more accessible, significantly more scaled, and more adaptive creation in response to the dynamic needs of modern media consumption. A main feature of the system is its utilization of a massively multilingual speech model, enabling it to accommodate the diverse linguistic landscape of India. Additionally, the system incorporates a lip-sync model, synchronizing the lip movements of the anchor with the corresponding audio file. The output of the system is delivered in video format, providing a seamless and immersive viewing experience for the audience.