Respeaking
Respeaking is a live-captioning method where a trained captioner listens to the broadcast and re-dictates it — with spoken punctuation and speaker labels — into a speech-recognition system tuned to their voice.
Respeaking became the dominant live-captioning method in much of the world because training a respeaker is faster than training a stenographer, while a controlled single voice keeps ASR accuracy high.
Related terms
Frequently asked
What is Respeaking?
Respeaking is a live-captioning method where a trained captioner listens to the broadcast and re-dictates it — with spoken punctuation and speaker labels — into a speech-recognition system tuned to their voice.
Why does Respeaking matter?
Respeaking became the dominant live-captioning method in much of the world because training a respeaker is faster than training a stenographer, while a controlled single voice keeps ASR accuracy high.
What terms are related to Respeaking?
Closely related concepts: Live captioning, Dictation — each has its own entry in this glossary.
Transcribe audio or video in 99+ languages — speaker labels, word timestamps, captions.
Transcribe a file →