Resources

Glossary

Short, direct definitions of the key terms in conversational AI and speech analytics — what they are, why they matter, and how they work in the platform.

AI secretary: An AI secretary is a voice AI agent for inbound calls that answers the call, holds a dialogue, qualifies the request and routes it to the right person. Unlike a simple answering machine, it understands speech and acts on a scenario rather than playing back fixed recordings.
Barge-in: Barge-in is the ability of a caller to interrupt a speaking voice agent: as soon as the person starts talking, the agent falls silent and switches to listening. This feature makes a conversation with the bot feel natural, close to a live dialogue.
Call transcription: Call transcription is the automatic conversion of a conversation's audio recording into text with timing attached to each turn. It answers the question "what was said" and serves as the base layer on top of which any conversation analysis runs.
CSAT: CSAT (Customer Satisfaction Score) is a metric of satisfaction with a specific interaction: a purchase, a support contact, a conversation. It's usually measured with the question "how satisfied are you?" on a scale immediately after the contact.
Diarization: Diarization is the automatic splitting of a conversation recording into turns by speaker: who spoke and when. It answers the question "who spoke," whereas speech recognition answers "what was said."
FCR: FCR (First Call Resolution) is the share of customer requests fully resolved in a single contact, without repeat calls or transfers. The metric shows how effectively support closes issues right away rather than stretching them across several interactions.
Knowledge base: A knowledge base is a structured collection of documents with answers, product facts, regulations, scripts and standard solutions, used by people and AI systems. In the context of conversations it's also a source of context from which AI draws reliable information when processing calls and written exchanges.
LLM (large language model): An LLM (large language model) is an AI model trained on large volumes of text that can understand and generate natural language. It can answer questions, summarize, extract data and hold a dialogue, working with text as a flexible input and output.
NPS: NPS (Net Promoter Score) is a metric of customers' willingness to recommend a company, based on the question "how likely are you to recommend us?" on a scale from 0 to 10. It shows customers' overall attitude toward the brand rather than satisfaction with a specific conversation.
Script compliance: Script compliance is a check of how well an agent followed the prescribed conversation scenario and service standards: whether they said the mandatory phrases, asked the required questions, kept the sequence and legal wordings. It turns the subjective judgment of "did they handle the call well" into a measurable indicator.
Semantic search: Semantic search is search by meaning rather than exact word match: it finds records close in meaning to the query even when they use different wording. It answers the question "what was the conversation about," whereas ordinary search looks for literal occurrences of phrases.
Sentiment analysis: Sentiment analysis is the automatic determination of the emotional coloring of a conversation: positive, negative or neutral. It shows how participants feel about the subject of the conversation and how their mood shifts over the course of the dialogue.
Speech analytics: Speech analytics is the automatic analysis of conversations (calls and written exchanges) to extract metrics, topics, tone and other data from what was said and how the dialogue unfolded. It turns recordings into structured data you can build dashboards on and make decisions from.
STT (speech recognition): STT (speech-to-text) is the technology of automatically converting spoken speech into text. It's the base component that makes it possible to read, search and analyze conversations, as well as to understand the caller in voice agents.
Voice AI agent: A voice AI agent is a software conversationalist that carries out a phone conversation by voice: it listens to the caller's speech, understands it and responds in real time according to a defined script. It combines speech recognition, a language model and voice synthesis into a single dialogue loop.

Ready to start?

Turn every conversation into data, knowledge and action

Start by analyzing your conversations — no risk, no bots required. The platform turns your archive into data and a knowledge base, and voice agents plug in when you're ready.

Start for free All plans and per-operation prices

Free plan, no card required.