In the wake of the COVID-19 pandemic, a marked rise in home cooking, supported by Nielsen Korea, highlights a 58.8% increase in home-cooked meals. Despite this surge, traditional voice-activated recipe systems inadequately cater to diverse user proficiencies, often providing generic instructions. Addressing this gap, this study introduces an advanced system enabling tailored control over text and video recipes through voice commands, promoting a hands-free, personalized culinary experience. This system synergizes voice control with video object recognition and label detection, leveraging Google Video Intelligence for instantaneous segment navigation. Additionally, by comparing ingredient data with user inputs, it recommends recipes based on ingredient compatibility, enhancing user convenience. Future aspirations encompass comprehensive voice control over detailed recipe components and a shift towards a more automated recommendation approach, acknowledging ingredient conditions for precise compatibility scores. In essence, this research bridges a significant user-centric gap in digital culinary guidance, offering innovative solutions for the modern home chef.