Call transcription
Call transcription converts the audio of a phone call into written text, either live during the call or from a recording afterwards.
Also called: speech-to-text, ASR transcript
Transcription is produced by speech-to-text (also called automatic speech recognition). Live transcription is what lets an AI receptionist understand a caller at all; the same text can be kept as a record of the call.
Transcripts are searchable and quick to skim, but they are verbatim: long, and not always easy to act on. That is why most products pair them with a post-call summary.
Accuracy varies with audio quality, accents, background noise and vocabulary; names and addresses are the usual weak points, which is one reason a text confirmation to the caller is useful.