A self-contained breathing and communication apparatus is described that can facilitate communication between a first user and a second user. A microphone can record sound when the first user speaks. The microphone can convert the recorded sound to a voice signal. A voice activity detection processor can detect spoken words and informative sounds of the first user from the converted voice signal. For this detection, the voice activity detection processor can remove noise from the voice signal. A voice-to-text processor can convert the detected words and informative sounds to a text message. A transmitter of the transmitting module can transmit the text message to a receiver of the second user via a communication network. A display device of the second user can display the text message on a graphical user interface. Related methods, apparatus, systems, techniques and articles are also described.