Live captions transcribe speech as it happens and display it with minimal delay, often fanned out from the SFU so everyone shares one transcription. Accuracy, latency, and speaker labelling determine whether they help or distract.
Definition
Real-time on-screen subtitles generated from speech during a call or broadcast, for accessibility and comprehension. Built on streaming ASR.
Live captions transcribe speech as it happens and display it with minimal delay, often fanned out from the SFU so everyone shares one transcription. Accuracy, latency, and speaker labelling determine whether they help or distract.
Also known as
live captioning, real-time subtitles, AI captions