Skip to main content
Tavus uses the Conversational Video Interface (CVI) as its end-to-end pipeline to bring the human layer to AI. A PAL is what you build in CVI. Configure its Face to define how it looks, its Voice to define how it sounds, and its behavior, knowledge, objectives, guardrails, tools, and pipeline layers to shape how it thinks and acts.
Terminology update: Tavus now uses PAL for what you build, Face for how it looks, and Voice for how it sounds in the API and docs. Legacy names persona and replica still work on existing endpoints and request fields (/v2/personas, /v2/replicas, persona_id, replica_id, and related aliases) for backward compatibility.

​
Developer Guides

Follow our in-depth technical resources to help you build, customize, and integrate with Tavus:

Conversational Video Interface

Learn how Tavus turns AI into conversational video.

What Is a PAL?

Configure how your PAL thinks and acts.

Face

Build a hyper-realistic face using Phoenix.

​
Conversational Use Cases

anna

Sales Development Rep

Engage with Anna, the Tavus sales development rep.
lucas

Interviewer

Screen candidates at scale with an engaging experience.
gloria2

Customer Support

Support users with product issues.
ruby

Medical Intake

Run a structured pre-visit intake flow.