This disclosure describes systems, methods, and devices related to smart notifications for online collaboration applications. A method may include receiving, by at least one processor of a device, audio data from an audio stream presented using a video application of the device; identifying, by the at least one processor, a keyword for which to search in the audio data; determining, by the at least one processor, that the audio data includes a representation of the keyword; generating, by the at least one processor, based on the determination that the audio data includes the representation of the keyword, a notification indicating that the keyword was identified in the audio data; and causing presentation, by the at least one processor, of the notification using the device.