Tavus introduces the world's fastest digital proxy solution for video chats

A video research company specializing in generative artificial intelligence (AI) has announced the release of the world's fastest digital twin solution for real-time video calling.

San Francisco-based company Tavus has called the new product Conversational Video Interface (CVI).

According to the company, the new product provides developers with a complete set of building blocks to create interactive experiences with digital twins that can see, hear and respond with minimal delay.

Tavus claims that the digital twins created through the platform can act almost exactly like the people they represent, potentially making the lives of content creators, help desk employees and others much easier.

“Conversational replicas represent a paradigm shift in the way we interact with machines,” said Hassaan Raza, co-founder and CEO of Tavus. “Instead of conforming to the limitations of traditional interfaces, we are developing solutions that leverage humans' natural ways of communicating – through visual and verbal cues, emotional understanding, and contextual awareness.”

Tavus' new conversational video interface

Tavus claims that its CVI creates a lifelike digital twin that goes beyond simple chatbots or recorded videos.

The product uses artificial intelligence to create a dynamic replica that embodies the person's appearance, knowledge, context and background, the company said. It can see and process visual and voice information, answer questions, provide insights and have conversations just as the real person would.

“The replica draws on the expertise, experiences and unique perspective of an individual or organization to provide authentic, personalized answers, essentially acting as a proxy,” the company says.

According to a press release, the new CVI can communicate with a latency of less than one second during conversations and when performing certain tasks.

Furthermore, the company states that it can be deployed without much effort on the part of the user as it is an end-to-end developer solution. Other features of Tavus' new offering include rolling vision and a conversation pipeline designed for multiple purposes.

Additional features and security measures

It also offers room for experimentation as it can also be paired with models like ChatGPT-4o or Claude or any other large language model (LLM).

In addition, the platform offers production scalability and parallel stream management options to handle high data volumes.

As for security, the company says it has safeguards in place to ensure a person can only create one digital twin of themselves. It also boasts of SOC 2 compliance, automated content moderation, and hallucination-prevention quality controls.

“This new video interface enables more intuitive, efficient and impactful interactions. In short, CVI enables users to leverage and scale their digital image, creating a true extension of themselves that overcomes the limitations of space, time and memory. It also opens new doors for developers to create unprecedented customer experiences,” said Raza.

But while generative AI is making great strides, there are some concerns in society about its safety and potential misuse.

The world of artificial intelligence is growing rapidly and more and more products of this kind will be launched in the coming days. Proper care and increased vigilance are required to minimize the risk of online fraud, unauthorized identity fraud and more.