Tavus, a company specializing in Conversational Video Interfaces (CVI), has announced the launch of three new generative AI models: Phoenix-3, Raven-0, and Sparrow-0. These models are designed to enhance interactions between humans and AI, providing more authentic and personalized experiences.
Introducing our new family of state-of-the-art AI models: Phoenix-3, Raven-0, and Sparrow-0.
— Tavus (@heytavus) March 6, 2025
Together they bring Conversational Video Interfaces (CVI) to the next level, and power Charlie, our new demo persona 👋 pic.twitter.com/vaqX9InvwX
Phoenix-3 is an advanced facial animation model that accurately reproduces facial expressions, micro-expressions, and lip synchronization. It enables seamless, context-dependent emotional responses while preserving the user’s identity. Raven-0 gives AI visual perception capabilities, allowing it to interpret and respond to visual cues and context in real time. This model can read text, recognize gestures, and detect emotions, making interactions more natural and intuitive.
Sparrow-0 focuses on improving conversational timing and flow. It adapts to natural speech patterns, understanding the rhythm and context of dialogue. This model outperforms current leading systems in transition accuracy, achieving a mean absolute error of 0.3989 compared to the previous best of 1.7467.
These models work together as an intelligent system within the Tavus operating system for Conversational Video. The company demonstrated the capabilities of these models using an AI agent named Charlie, which can conduct live dialogue, search the internet, analyze screens, and generate images seamlessly. Tavus will make these models openly available through their APIs starting March 6, 2025. The company envisions widespread adoption of this technology, particularly in the form of digital humans that could become as common as smartphones. Several leading brands and startups are already integrating this technology into their workflows.
