In one embodiment, a method for sending a video message and a text message in a communication session is provided. The method includes determining when a contextual trigger is detected in the communication session between a first user and a second user. For example, the contextual trigger may be when a first user focuses on a window being used for the communication session. The first user may then input a text message. A video message of the first user in the communication session is also determined. The video message is determined based on when the contextual trigger is determined. For example, the video message may include video from a time before when the contextual trigger is determined, such as 10 or 20 seconds before, until a time when the first user is finished inputting the text message. The text message and video message are then sent to a second user.