Word error rate
WER
Formula
(Substitutions + insertions + deletions) ÷ total words in the reference transcript × 100
Related terms
Call transcription
Call transcription converts recorded or live call audio into searchable text using automatic speech recognition (ASR). It can run in real time, powering live agent guidance, or in batch after the call ends. Batch processing generally yields higher accuracy. Quality transcripts include speaker diarization, timestamps, and redaction of sensitive data like card numbers. Accuracy is measured by word error rate. OnClarity’s AI Agent QA uses transcripts to score 100% of conversations for QA and compliance. Example: a team searches six months of transcripts for every mention of a failed payment flow to find a root cause.
Voicebot
A voicebot is an automated phone agent that listens, understands, and responds using natural speech rather than touch-tone menus. It chains automatic speech recognition, natural language understanding, dialogue logic, and text-to-speech into a single pipeline. Callers can ask for what they need in their own words instead of navigating a DTMF menu tree. Production systems support barge-in, so a caller can interrupt mid-response. They are also tuned against a tight conversational latency budget to avoid dead air. OnClarity’s AI agents work across chat and voice, resolving routine calls and escalating to a human agent when needed. Example: a caller asks about a delivery date and gets a direct answer without touching a keypad or waiting in a queue.
Speech analytics
Speech analytics automates analysis of recorded or live customer calls. It uses speech-to-text transcription combined with natural language processing to extract keywords, topics, and sentiment. Many systems also measure acoustic signals such as silence, talk-over, and speaking pace, to flag stress or disengagement that word choice alone would miss. Real-time speech analytics prompts agents mid-call and raises live compliance flags. Post-call analysis surfaces trends and root causes across a larger call sample. Standard uses include detecting required compliance phrases, categorizing contact reasons, and feeding evidence into quality assurance scoring.

Support teams are no longer a cost centre.
See how AI Support Agent, Agent Assist, and VoC Analyst work on your own ticket volume.