Tavus Research: Pioneering Human Computing

PIONEERING HUMAN COMPUTING

We’re teaching machines the art of being human: bringing together rendering, perception, emotion, and understanding to create AI humans that feel natural, intuitive, and alive.

Models

We build models to teach machines to see, hear, understand and even look human. We give machines presence and EQ, allowing them to understand you deeply, and in turn, building trust and connection with them.

Phoenix [4.5]

Phoenix-4.5, the most natural and realistic human rendering model on the market, designed to give AI a face, presence, and emotional range. The A gaussian-diffusion based model synthesizes high-fidelity facial behavior in real time, with contextually accurate emotions, expressions, and movement.

Raven [1]

Raven-1, our multi-modal perception model, giving machines the ability to see, hear and understand in real-time. It translates facial expressions, tone, gaze, emotion, and environmental context into rich conversational signals, helping your AI respond with empathy, awareness, and intent.

Sparrow [2]

Sparrow-2 is our real-time conversational understanding model, built for natural conversational flow in noisy, multi-speaker environments. It models semantics, prosody, speaker identity, backchannels, interruptions, background speech, noise, and unclear audio to determine when to listen, wait, speak, or continue speaking.

Research areas

We study how intelligence perceives context, emotion, and tone to create AI that understands and acts as humans do.

contextual perception

Understanding meaning beyond words. Tone, timing, intent, and everything unsaid.

Audio understanding

Teaching machines to truly listen. Not just to sounds, but to emotion, cadence, and rhythm.

Agentic interaction

Building systems that act with awareness, not automation. Capable of response, reasoning, and restraint.

human-like speech

Synthesizing voice that carries emotion, not just words. Warmth, hesitation, humor, humanity.

Real-time rendering

Turning intelligence into motion. Seamless, lifelike expression that feels natural and alive.

Conversational intelligence

Making dialogue intuitive and human. Conversations that adapt, remember, and build trust over time.

Where research becomes reality

Our research manifests as the traits that make AI feel human.

EXPRESSIVE Empathetic Actionable Personalized

Expressive (and authentic)

AI Humans bring face-to-face connection to every conversation.

Real-time conversation

Trained on millions of conversations to deliver smooth, humanlike dialogue.

Superhuman perception

Understands actions, emotions, and screenshares to respond with context.

Lifelike presence

Displays expressive reactions and movement that build trust and engagement.

Perceptive (and aware)

AI Humans are modeled after us: they see, sense, and understand to build trust through real conversation.

Perception

Deciphers nonverbal cues like body language and micro-expressions. Uses context to adapt responses and create meaningful, two-way interactions.

Multimodal

Every input adds context, ensuring the AI Human sees the full picture: screenshare, voice, and surroundings.

Awareness

Monitors key events and behaviors to trigger function calls while continuously sensing subtle background shifts with real-time data.

Thinking (with agency)

AI Humans are fully formed, with the cognitive skills needed for efficient, effective conversations.

Knowledge

Industry-leading RAG grounds responses in your data. 15x faster than other solutions.

Memory

Remembers past interactions to personalize responses and pickup conversations where they left off. Free to toggle on or off to fit any interaction.

Structure

Uses customizable frameworks and logic branching to naturally structure conversations and keep moving toward your goals.

Deployable (and customizable)

AI Humans are designed to work for you: scalable, flexible, and ready to perform.

Scale

Deploy and manage AI Humans at scale, with infrastructure, WebRTC, VAD, and ASR fully managed behind the scenes.

Insights

Transcripts, visual context, and emotional markers from every conversation are accessible and used to inform improve user experiences.

White-labeled

Developer first APIs. With simple, plug-and-play endpoints, you can embed AI Humans into any website or platform with ease.

PAL Maker

Bring PALs into your next AI conversation.