A real-time portable sign language translation system for deaf-mutes will be presented. In the proposed system, a wireless hand gesture recognition glove for real-time translation of sign language commonly used in Taiwan is developed. To discriminate between different hand gestures, we have flex and inertial sensors embedded into the glove so that the three most important parameters, i.e., posture of the fingers, orientation of the palm, and motion of the hand, in Sign Language can be recognized without ambiguity. The finger flexion, palm orientation, and motion trajectory will be sampled periodically. Once the gesture is recognized as a valid signal, it will be encoded and sent to cell phone via Bluetooth Low Energy (BLE) for vocabulary look up. Finally, the vocabulary will be translated to speech via Google translator so that people can hear and know the meaning of the sign language. With the proposed system, the deaf-mutes can communicate with others easily.