Developers

Pricing

Resources

Company

Team

Start building

Resources

The avatar API glossary

Every term you need to understand real-time interactive AI avatars. From rendering and personas to latency, RAG and compliance.

Start here

Real-time avatar

A real-time avatar is a photorealistic digital character that listens, thinks, and speaks back inside a live audio and video stream, typically with sub-second response latency, so it can hold a two-way conversation rather than play a pre-rendered clip.

Avatar API

An avatar API is a developer interface for creating, configuring, and streaming interactive digital characters inside an application, so products can start live avatar sessions, pass user input to an agent, and return spoken video responses in real time.

Interactive avatar

An interactive avatar is a digital character that listens to a user and responds in real time, using speech, language model reasoning, and live animation to support a two-way conversation instead of a fixed script.

Sub-second latency

Sub-second latency is the end-to-end response time under one second between a user speaking and an avatar replying, covering speech recognition, model reasoning, speech synthesis, animation, and network streaming.

All terms

A

Avatar API

AI sales agent

An AI sales agent is an interactive avatar or voice agent configured to qualify prospects, answer product questions, guide buying decisions, and hand over to a human or booking flow when a lead is ready.

AI voice agent

An AI voice agent is a speech-first conversational agent that uses speech recognition, an LLM or agent workflow, and text-to-speech to understand spoken input and reply naturally in real time.

ASR (speech recognition)

ASR, or automatic speech recognition, is the system that converts live spoken audio into text so an avatar or agent can understand the user and decide what to do next.

B

Barge-in

Barge-in is the ability for a user to interrupt an avatar while it is speaking, so the system can stop the current response, listen to the new input, and continue the conversation naturally.

C

Customer support agent

A customer support agent is an interactive avatar configured to answer customer questions, retrieve approved help content, check account context, and route complex issues to the right workflow.

D

Diffusion model

A diffusion model is a generative AI model that learns to create realistic images or video frames from noise, and can be used in avatar systems to help produce photorealistic visual output.

Data residency

Data residency is the control over the geographic region where user data is processed and stored, which matters when avatar sessions include audio, video, transcripts, prompts, or logs.

F

Function calling

Function calling lets an LLM invoke approved tools or APIs during a conversation, so an avatar can fetch data, perform actions, or answer from live systems instead of relying on text generation alone.

G

Grounding

Grounding is the practice of anchoring a model's answer to trusted source content, retrieved documents, or tool results so an avatar can respond with verified information instead of guessing.

H

Hallucination

A hallucination is when a language model gives a confident but incorrect or unsupported answer, which is especially risky in avatar experiences because the response is delivered through a persuasive face and voice.

I

Interactive avatar

L

Lip sync

Lip sync is the process of aligning an avatar's mouth shapes and facial motion with generated speech audio, so the character appears to speak the words at the right time.

Latency budget

A latency budget is the total response-time allowance split across speech recognition, model reasoning, tools, text-to-speech, rendering, and streaming so a real-time avatar can stay conversational.

O

Onboarding assistant

An onboarding assistant is an avatar that guides new users through setup and product education, answering questions and adapting the flow based on what the user is trying to do.

P

Persona

A persona is the configured identity of an avatar, including its role, tone of voice, appearance, behaviour, knowledge boundaries, and rules for how it should respond to users.

Prompt

A prompt is the instruction and context given to a language model for a specific response, including the user's message, system rules, retrieved content, and tool results when available.

PII redaction

PII redaction is the process of removing or masking personally identifiable information from transcripts, logs, and stored records so avatar systems retain less sensitive user data.

R

Real-time avatar

RAG

RAG, or retrieval-augmented generation, is a pattern where an agent retrieves relevant documents or data at query time and uses them to produce a more accurate, grounded response.

S

Sub-second latency

SDP

SDP, or Session Description Protocol, is the WebRTC setup format that describes media tracks, codecs, and connection details so a browser and avatar service can start a live stream.

SOC 2

SOC 2 is a security and compliance audit framework that evaluates how a service manages controls for security, availability, confidentiality, processing integrity, and privacy.

System prompt

A system prompt is the persistent base instruction that sets an avatar's role, tone, boundaries, allowed behaviours, and escalation rules across the whole conversation.

T

Turn detection

Turn detection is the process of deciding when a user has finished speaking, so the avatar can respond at the right moment without interrupting or waiting too long.

TTS

TTS, or text-to-speech, is the system that converts a model's text response into spoken audio, giving an avatar a voice that can be streamed and lip-synced in real time.

V

Vector database

A vector database stores embeddings for semantic search, so an avatar or agent can retrieve relevant knowledge base content for RAG and answer user questions with the right context.

W

WebRTC

WebRTC is the browser standard for low-latency live audio and video streaming, commonly used to carry microphone input and avatar output during real-time interactive sessions.

Explore latest articles

Meet our most expressive model yet: Cara-4

Ben Carr

July 8, 2026

AI avatar API tools are easier to set up and debug

Caoimhe Murphy

June 2, 2026

Conversational AI API guide: choosing the right AI API

Ben Carr

June 2, 2026

Try the real-time avatar API trusted by 8,000 builders

Read the docs

Try the real-time avatar API trusted by 8,000 builders

Read the docs

How to use this glossary

Use this glossary when a term slows you down in docs, an RFP, or a build review. Search the exact phrase or jump by letter to find what you need quickly. Each card gives you the plain-English version; open a term page when you need deeper context, examples, and how it applies to real-time avatar systems.

Product

Company

Resources