We all know that to fetch the answer of any question from ChatGPT, we have to write the text in the ChatGPT Prompt. It is highly inconvenient and it also doesn't provide any native option to scan the image and thereby recognizing text using camera or any hearing (Text-to-speech) option for the person with visual impairment.
Here we have created a AI assitant named Stella to recognize the text using camera 📷 or from image 🖼️ and then we are feeding the data to ChatGPT API for fetching the answer. The answer is then shown to the screen 💻 of the user.