Trusted by the world's most innovative companies

Developers

Build conversational video agents

Out-of-the-box building blocks for real-time AI conversations: perception, dialogue, and rendering with <500ms end to end latency. Deploy white-labeled video agents that listen, react, and scale to production.

Explore APIs

Enterprise Solutions

Deploy AI humans at scale

Production-grade infrastructure for secure, real-time AI human deployment across learning & development, healthcare, sales, education, and support. Custom replicas, emotion control, and enterprise SLAs built in.

Book Demo

Pals

Your new intern, friend, or both

Your always-on AI companion that sees, hears, and responds in real-time. Ask questions, get things done, or just talk through your day, all face to face.

Get Access

What if you could talk to your computer like a friend?

What if you could talk to your computer like a friend?

Bridging the human-machine divide

Pioneering human computing since 2020

Tavus is a San Francisco–based AI research lab pioneering human computing, teaching machines the art of being human. We build foundational models that let AI see, hear, and respond like people do. We're turning the promise of science fiction into reality, where computing feels instinctive and truly alive. Because the next intelligence isn't just emotional — it's a coworker, a friend, a presence that actually knows you.
Speak with charlie

models

Models

We build models that teach machines perception, empathy, and expression so AI can finally understand the world as we do.
Our Research
Rendering

Phoenix [4]

Phoenix-4, a gaussian-diffusion rendering model developed to synthesize high-fidelity facial behavior at the speed of human interaction, is the result of building real-time facial animation systems that reproduce subtle, temporally consistent expressions with precise control over motion and identity.
Perception

Raven [1]

Raven-1, a novel multimodal perception model designed to unify object recognition, emotion detection, and adaptive attention within a single contextual framework, emerged from modeling how machines interpret people and environments by integrating visual input, emotional signals, and spatial relationships.
Emotional understanding

Sparrow [1]

Sparrow-1, a transformer-based dialogue model that captures conversational timing, responsiveness, and humanlike interaction flow using multimodal alignment techniques, embodies research into parsing communicative intent, emotional state, and turn-level structure across voice, language, and gesture.

Build with us

Join the team shaping how humans and machines understand each other. We’re researchers, engineers, and artists building AI that listens, learns, and connects like people do. Come decode the conversation with us.

join the team