Skip to content

The real-time AI
avatar glossary.

Build a shared language for conversation timing, speech audio, motion generation, client rendering, session reliability, and performance measurement.

Filter by letter

Start here

Directory

All terms

50 terms

A

Timing & turn-takingAcoustic Echo CancellationAcoustic echo cancellation removes the avatar’s speaker output from the microphone signal using a playback reference.Audio & streamingAudio BackpressureAudio backpressure is flow control applied when a producer generates audio faster than downstream components can consume it.Audio & streamingAudio ChunkingAudio chunking divides a continuous speech stream into ordered blocks that can be processed incrementally.Audio & streamingAudio PrebufferingAudio prebuffering accumulates a minimum amount of media before playback or downstream processing begins.Audio & streamingAudio ResamplingAudio resampling converts a signal from one sample rate to another while preserving its perceived timing and content.Audio & streamingAudio Sample RateSample rate is the number of audio samples captured or represented per second, measured in hertz.Sessions & reliabilityAudio-Only FallbackAudio-only fallback continues speech playback when avatar animation or rendering is unavailable.Performance & playbackAudio-Video SynchronizationAudio-video synchronization aligns avatar motion with the corresponding moments in speech playback.Rendering & runtimeAvatar Asset BundleAn avatar asset bundle packages the meshes, textures, rig data, animations, and metadata needed to render an avatar.Rendering & runtimeAvatar Asset PreloadingAvatar asset preloading fetches and prepares required resources before the avatar must first appear or speak.Rendering & runtimeAvatar Frame RateAvatar frame rate is the number of visual frames actually presented per second.Motion & lip syncAvatar Motion FrameAn avatar motion frame is a timestamped set of pose or facial-control values representing one instant of animation.Rendering & runtimeAvatar Render LoopAn avatar render loop repeatedly updates animation state and submits the next visual frame for display.Sessions & reliabilityAvatar SessionAn avatar session is a bounded runtime context containing configuration, authentication, connection, and conversational state.Audio & streamingAvatar Speech AudioAvatar speech audio is the speech signal the avatar should perform, normally the output of a TTS system rather than the user’s microphone.

B

C

D

E

F

I

J

K

L

M

P

R

S

T

V

W

Turn the concepts into a live avatar experience.

Contact us