A method and a system for instantly translating text within an image are provided. The method and the system are suitable for using a service end device to translate text within the image captured by a portable communication device. First, the image is captured by the portable communication device, and then transmitted to the service end device through a communication network. Next, the text within the image is recognized and translated into translation text by the service end device. The translation text is transmitted back to the portable communication device through the communication network and displayed by the portable communication device. Thereby, a user can take an image at any time and get to know what it means immediately.