AI Voice Agent Glossary

Plain-English definitions of the key terms used in AI voice agents, conversational AI, and telephony — from STT and TTS to SIP trunking and prosody modeling.

A B C D E F G I L N P S T V W

AI Voice Agent

Software that conducts real-time phone conversations using STT, an LLM, and TTS.

ASR (Automatic Speech Recognition)

Technology that converts spoken audio into written text in real time.

Barge-In

A caller's ability to interrupt an AI agent mid-speech and redirect the conversation.

BYON (Bring Your Own Number)

The ability to connect an existing phone number to TurboCall via SIP trunking.

Conversational AI

AI systems designed to simulate human conversation across voice, text, and chat.

Call Routing

The process of directing an inbound call to the correct destination — human agent, department, or AI flow.

DTMF (Dual-Tone Multi-Frequency)

The touch-tone signals generated when pressing phone keys, used in traditional IVR systems.

DPA (Data Processing Agreement)

A contract between a data controller and processor defining GDPR-compliant data handling.

Emotional Intelligence (Voice AI)

The ability of a voice AI to detect and respond appropriately to a caller's emotional state.

End-to-End Latency

The total time from a caller finishing a sentence to when the AI begins its response.

Fallback Response

A pre-defined AI response triggered when the caller's intent cannot be understood.

GDPR (General Data Protection Regulation)

EU regulation governing the collection, storage, and processing of personal data.

IVR (Interactive Voice Response)

A traditional phone system that routes calls using pre-recorded menus and touch-tone input.

Intent Recognition

The NLU process of identifying what action a caller wants to take based on their words.

LLM (Large Language Model)

An AI model trained on large text datasets, used as the reasoning engine in AI voice agents.

Latency

The delay between a caller's speech and the AI's audible response. Under 400ms is considered natural.

NLU (Natural Language Understanding)

The AI capability to interpret the meaning and intent behind spoken or written language.

Neural TTS (Neural Text-to-Speech)

Deep learning-based synthesis of human-sounding speech from text.

Prosody

The patterns of rhythm, stress, and intonation in speech that make voices sound natural.

PCI-DSS

Payment Card Industry Data Security Standard — required for collecting card data over the phone.

Sentiment Detection

Real-time analysis of a caller's emotional tone — frustration, satisfaction, urgency, or confusion.

SIP (Session Initiation Protocol)

The standard protocol for initiating, maintaining, and terminating real-time communication sessions, including phone calls.

SIP Trunking

Delivering telephone calls over an internet connection using the SIP protocol.

SOC 2 (Service Organization Control 2)

An auditing standard that verifies a company's security, availability, and confidentiality controls.

STT (Speech-to-Text)

Technology that converts spoken audio into text, the first stage of an AI voice agent pipeline.

Streaming TTS

A technique where audio synthesis begins before the full text is generated, reducing response latency.

TCPA (Telephone Consumer Protection Act)

US law governing outbound calling, autodialers, and consent requirements for phone-based marketing.

TTS (Text-to-Speech)

Technology that converts written text into spoken audio, the output stage of an AI voice agent.

Turn-Taking

The mechanism by which an AI voice agent determines when a caller has finished speaking before responding.

Voice Cloning

Creating a synthetic replica of a specific person's voice from a short audio sample.

Voice Persona

A configured AI voice identity with a specific name, voice, tone, and conversational style.

Webhook

An HTTP callback that sends real-time data to an external URL when a specific event occurs, such as a call ending.

Warm Transfer

A call transfer where the AI brief a human agent with context before connecting the caller.

Ready to put these concepts to work?

TurboCall gives you sub-400ms AI voice agents with neural TTS, NLU, SIP trunking, and CRM integrations — no code required.

Start Free Trial Explore AI Voice Agent