Griffin is the world’s first Human Interaction Model. It sees you, hears you and talks back, all at the same time. Not a chain of systems taking turns, but one model in one conversation: it nods along, cuts in, gives you room to think. After a one-minute video call with it, not knowing what it was, 48% of people believed they’d been talking to a real person.

Interactive avatars for enterprise build trust through behavioral realism, precise conversational timing, and closed-loop perceptual AI. Here is how it works.

I built a minimal Gaussian Splatting implementation in pure PyTorch to understand how it actually works. This post goes through that code and explains what each piece does, why it’s there, and how it all fits together.

Modern AI faces can hold live conversations and read your expressions. Explore the rendering, turn-taking, and perception models that make it possible. 

The face-to-face conversational AI vs. chatbot comparison comes down to capability tiers. A guide to types, examples, and when to move from text to video.

Discover how AI video agents transform customer service training with realistic practice. Learn implementation strategies, benefits, and real-world applications.

Conversational AI for healthcare is evolving beyond chatbots. Learn how to build HIPAA-compliant patient video conversations with real-time AI Personas.

A hands-on experiment fine-tuning ACE-Step v1.5, an open-source AI music generation model, to fix its garbled lyric problem using LoRA and Attention Sharpness Regularization. What started as a random Friday night side project turned into a deep dive into how a 2-billion-parameter diffusion transformer actually processes text, and what breaks when you try to change it.

Introducing Raven-1. A multimodal perception system that captures not just what users say, but how they say it, how they look when they say it, and what that combination actually means. It interprets tone, expression, hesitation, and context in real time, enabling AI that can truly understand intent rather than simply respond to words.

Sparrow-1 is a specialized, multilingual audio model for real-time conversational flow and floor transfer. It predicts when a system should listen, wait, or speak, enabling response timing that mirrors human conversation rather than simply responding as fast as possible.

From theory to code: how diffusion and flow matching models turn Gaussian probability paths into vector fields, training targets and practical loss functions.

Discover the latest research in how LLMs use reinforcement learning to search, reason, and refine answers across multiple turns—boosting accuracy and enabling active problem-solving.

Choosing between Tavus and Anam comes down to one question: do you need an AI persona that can talk, or an AI human that can genuinely understand the person in front of it? This piece covers where the two platforms differ on emotion control, active listening, and perception, what that difference looks like in real-world conversation, and what an independent paired evaluation of 80 sessions found when users experienced both side by side.

We made an unexpected discovery while developing our premium conversational AI technology. Components of our advanced video pipeline could be isolated and explicitly optimized for lip synchronization, with remarkable results. This serendipitous research byproduct evolved into Hummingbird, a specialized zero-shot lip-sync model that achieves state-of-the-art performance compared to other leading solutions.

In this paper, we dive into the development and research behind Sparrow-0, exploring the innovative transformer-based approach for turn-taking and its integration alongside Raven and Phoenix models within our Conversational Video Interface (CVI), an end-to-end operating system designed for building responsive video agents.

This paper will cover the past, present and future of the talking-head generation research field. Specifically, we will dive deep into the trending 3D scene representations (NeRF -> 3DGS) and the benefits of employing 3DGS in avatar applications.

This research paper, written by the Tavus team, details the development of Phoenix, a groundbreaking generative model for realistic avatar creation and text-to-video generation. Phoenix leverages audio and text-driven 3D models, integrating volumetric rendering techniques and 2D Generative Adversarial Networks (GANs) to create lifelike replicas from short video clips.