Facial rigging

Facial rigging is the system of controls that moves an avatar's face, including mouth shapes, eyes, brows, jaw, and expressions, so speech and emotion can be animated believably.

How facial rigging works

Facial rigging is the control system that lets an avatar's face move. It defines how the mouth, jaw, eyes, brows, cheeks, and expressions can be animated.

In real-time avatars, facial rigging connects speech and behaviour to visible motion. The system has to produce mouth shapes for lip sync while also adding expression, blinking, gaze, and subtle motion that make the face feel alive.

A concrete example: when an avatar answers a support question, the facial rig drives the mouth for the spoken words while raising the brows or softening the expression to match the tone.

A good rig gives the model enough control to be expressive without creating unstable or uncanny movement. It is one of the foundations of believable avatar rendering.

Diagram explaining how the Anam Engine is used for AI developers

Diagram of how Anam works

What Anam ships

Anam's Cara-4 model delivers expressive real-time avatars with around 150 ms server-side avatar-generation latency once a session is running, across 70+ languages. Builders use JavaScript and Python SDKs or integrations for LiveKit, Pipecat, ElevenLabs Agents, Agora, and VideoSDK. Bring any AI stack including OpenAI, Claude, Gemini, Mistral, Groq, Deepgram, Cartesia, or custom providers. The platform supports WebRTC delivery, SOC 2 Type II, HIPAA, zero data retention, and regional data residency. Sessions stream low-latency audio and video to browsers and native apps.

Explore the real-time avatar API →

Related terms

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.

Digital human

A digital human is a realistic virtual person designed to communicate with users through a face, voice, expressions, and conversational behaviour, often powered by AI models and live media streaming.

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.

Multimodal model

A multimodal model is an AI model that can work with more than one type of input or output, such as text, audio, images, video, or structured data in the same agent workflow.

Frequently asked questions

What is facial rigging in avatars?

Facial rigging is the set of controls that moves an avatar's face, including mouth, jaw, eyes, brows, cheeks, and expressions during speech and interaction.

How is facial rigging related to lip sync?

Lip sync uses part of the facial rig to match mouth shapes to speech. The full rig also controls expression, gaze, blinking, and other motion beyond the mouth.

Why does facial rigging matter for real-time avatars?

The rig has to move quickly and consistently while the avatar speaks live. Poor rigging can make even a high-quality face look stiff, delayed, or unnatural.

What makes a facial rig feel natural?

Natural rigging combines accurate mouth shapes, expressive range, stable identity, believable micro-movements, and timing that stays aligned with the generated voice.

Last updated: 17th July 2026 · Reviewed quarterly.

← Back to glossary

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

Read the docs

HIPAA & SOC 2 Certified