Latency and performance
Voice is the only interface where half a second is noticed by everyone, including people who could not define latency. The terms here are the ones that end up in a service level agreement, so they are worth defining precisely before anyone signs.
Mean opinion score
Mean opinion score (MOS) is a 1 to 5 quality rating for synthesized or transmitted audio, produced by asking human listeners to score samples and averaging their answers, where 5 is excellent.
Time to first audio
Time to first audio (TTFA) is the end-to-end wall-clock delay from the moment a person stops speaking to the moment the reply becomes audible, and it decides more than any other number whether a voice agent feels alive.
Word error rate
Word error rate (WER) is the standard measure of transcription accuracy: the words a speech recognition system got wrong, counted as a percentage of the words that were actually said, where lower is better.
Every entry is reviewed and dated. Browse all categories.