Glossary

Call center and voice AI glossary

Short definitions of the terms that come up most in call centers and voice AI. Each term has its own page explaining how it works and why it matters.

A

AI voice agent
An AI voice agent is software that answers phone calls in natural speech, handles questions and tasks, and hands the call to a person when needed.
Automatic call distribution (ACD)
ACD is the call center function that automatically routes each incoming call to a suitable available operator according to rules you define.

B

Barge-in
Barge-in is a caller's ability to interrupt a voice agent mid-sentence, with the agent stopping to listen to what the caller just said.
Bring your own carrier (BYOC)
BYOC lets a business keep its existing phone carrier and numbers while connecting its line to a cloud call center or voice agent platform.

C

Call queue
A call queue holds incoming calls in order when no operator is free and connects each one to the next suitable operator when its turn comes.
Call summary
A call summary is a short record, usually generated by AI, of why someone called, the details collected and how the conversation ended.
Conversation design
Conversation design is the practice of planning what a voice or chat agent says, which details it collects and when it hands over to a person.
Conversational latency
Conversational latency is the time between a caller finishing speaking and an AI voice agent starting to reply.
CRM integration
CRM integration is the automatic transfer of call and conversation data into a customer relationship management system through an API or webhooks.

I

Interactive voice response (IVR)
IVR is an automated phone system that greets callers with recorded prompts and routes them through menus using keypad presses or short voice commands.
İYS (Message Management System)
İYS is Turkey's national system for recording consent to commercial electronic messages, where recipients can view and reject those consents.

K

KVKK and call recording
KVKK and call recording means handling recorded calls and transcripts under the notice, retention and security rules of Turkey's data protection law.

L

Large language model (LLM)
A large language model (LLM) is an AI model trained on vast amounts of text that, in a voice agent, understands the caller's request and writes the reply.

O

Outbound call campaign
An outbound call campaign is a planned effort to call a defined contact list for a specific purpose, within set calling hours and rules.

S

SIP (Session Initiation Protocol)
SIP is the standard signaling protocol that starts, modifies and ends voice and video calls over the internet.
Speech-to-text (STT)
Speech-to-text (STT) is AI technology that converts human speech into written text, either live during a call or from a recording.

T

Text-to-speech (TTS)
Text-to-speech (TTS) is AI technology that turns written text into spoken audio with natural intonation and emphasis, close to a human voice.

V

Voicemail and transcription
Voicemail is a recorded message a caller leaves when a call cannot be answered; transcription is that message automatically turned into text.

W

Warm transfer
A warm transfer passes a call to another person together with its context, so the caller does not have to repeat everything from the start.
WebRTC (Web Real-Time Communication)
WebRTC is an open web standard that lets browsers send real-time audio, video and data without plugins or extra software.

Ship a voice agent this week.

We onboard new teams in under five business days, with your scripts and your numbers.

Start a pilot