Meet Phoenix, our frontier Replica Model
Unparalleled realism, powered by unparalleled research
Phoenix-2
Our groundbreaking Phoenix-2 model generates exceptionally realistic digital twins.
Developed in-house by our team, it leverages new audio and text-driven 3D models, integrating volumetric rendering techniques offered by 3D Gaussian Splatting, with 2D Generative Adversarial Networks (GANs), to create lifelike replicas from short video clips of a user.
Developed in-house by our team, it leverages new audio and text-driven 3D models, integrating volumetric rendering techniques offered by 3D Gaussian Splatting, with 2D Generative Adversarial Networks (GANs), to create lifelike replicas from short video clips of a user.
“The quality of Tavus replica models is market leading. We get access to a world-class AI team and don’t have to worry about building models. This is huge! We have more resources to actually focus on the application side of things: the workflows, the user experience, and building features quicker.”
Will Fletcher
CPO at Nesti.io
Powering AI video products
The Phoenix model powers our products via the replica API.
VIDEO GENERATION
Video Generation
Give users the ability to generate videos from a script with AI digital twins.
Conversational Video Interface
Conversational Video
Give users the ability to have real-time conversations with AI digital twins.
Create hyper-realistic replicas with minimal footage
A user submits 2 minutes of training footage, and consents to the creation their digital replica.
The model analyzes the inflections of how a user speaks and creates a voice and video model.
Ethical Digital Twins
With Tavus developers can build digital twin experiences that are widely used, in a safe and authorized way.
Safeguarding personal identity
Our models have built-in consent mechanisms, making unauthorized replication technically impossible.
Promote responsible use
We prevent misuse with automated content moderation, usage policies, and ethical guidelines.
Mitigate model biases
We are pioneering research and implementation to eliminate biases in AI model development, setting new standards.
Transparency and accountability
We commit to active & clear communication about AI capabilities and limitations with customers.
Access a world-class machine learning team
Our engineering teams have been hand selected from top universities and leading companies like Amazon, Descript, Google, and Apple.
Research initiatives
The team is at the forefront of AI video research and pushes model updates every two weeks based on the latest research and customer needs.
