Tavus, a leading generative AI video research company, announced a transformative new product, Conversational Video Interface (CVI). Extending the Tavus platform, CVI now gives developers the world’s first complete set of building blocks required to create interactive visual experiences with digital twins that speak, see, and hear just like the humans they represent. An early tester of CVI, Delphi is now using Tavus to power its new Video Clone feature.
Thanks to less than one second of latency, Tavus Conversational Replicas, built on CVI, can be used for everything from hotel check-in kiosks with a digital human, to engaging in mock conversations for sales training, negotiation, or presentation practice. Imagine a world where users can interact with an AI human at the DMV to renew a driver’s license or talk with their favorite celebrity or expert through a digital twin. The use cases are endless.
“Conversational Replicas represent a paradigm shift in the way we interact with machines,” said Hassaan Raza, Co-founder and CEO of Tavus. “Rather than adapting to the limitations of traditional interfaces, we are creating solutions that leverage the natural ways humans communicate – through visual and verbal cues, emotional understanding, and contextual awareness. This new video interface will enable more intuitive, efficient, and impactful interactions. In short, CVI allows users to leverage and scale their digital likeness, creating a true extension of themselves that overcomes the limitations of space, time, and memory. It also opens new doors for developers to create unparalleled customer experiences.”
Empowering Developers to Scale Human Abilities
As consumers feel more isolated and detached with the saturation of digital products and services, they seek connectedness. Tavus provides developers with all the tools they need to easily build innovative, immersive, and highly engaging conversational video experiences that mimic real-life interactions. With CVI, the company delivers robust, well-documented, and intuitive APIs while handling all of the intricacies associated with AI video research. As a result, developers can create powerful, scalable, and realistic experiences out of the box.
The Tavus CVI is the world’s leading conversational solution because it’s:
- The fastest in existence: Communicate with less than one second of latency between statements and responses.
- The only end-to-end developer solution: Deploy without any deep engineering work.
- The facilitator of the most realistic conversations: Deliver the nuances of a realistic face-to-face interaction with an AI agent that can see, hear, and respond like a real person, complete with rolling vision, end-of-turn detection, interruptibility, and a purpose-built conversational pipeline and fine tuned LLM.
- The easiest to train: Leverage Tavus’ expertise in creating high-fidelity, realistic digital replicas with just two minutes of video.
Other reasons developers want to build with Tavus’ CVI include:
- A developer-first modular build: Use Tavus’ optimized building blocks, or bring your own services. Tavus makes it easy to integrate your own solution, like connecting your own LLM or models like GPT-4o or Claude.
- Scalable and manageable: Handle high traffic with ease using Tavus’ production scalability and parallel stream management.
- Safe and secure: Benefit from safety checks that ensure users can only make a digital twin of themselves while relying on comprehensive security protocols, including SOC 2 compliance. Tavus also supplies automated content moderation and anti-hallucination quality checks.
“There are a lot of components within a conversation. It’s incredibly complicated for an AI system to power a Digital Clone that can carry on a natural, live conversation over video,” said Dara Ladjevardian, Co-founder and CEO of Delphi. “Tavus tackles this challenge beautifully. We chose to partner with them because they have developed the world’s first conversational solution with under a second of latency. Their research and technology delivers an incredibly realistic, interactive experience. This is critical to our ability to deliver authentic personalized mentorship experiences with expert clones on our platform. The customer-centric nature of Tavus is also night and day above the rest – they’re a key trusted partner to Delphi.”
The Next Frontier
A pioneer in asynchronous AI video generation, Tavus continues to push the envelope, seeking to create a new human-computer interface that seamlessly takes advantage of new hardware advances, AI research, and LLMs (memory, scalability, speed, knowledge, intelligence, and agentic capabilities) to mirror the nuances and intricacies of human interaction.
Tavus’ CVI creates a lifelike digital twin that goes beyond simple chatbots or pre-recorded videos, leveraging AI to create a dynamic replica that embodies the person’s likeness, knowledge, context, and background. It can see and process visual and voice information, answer questions, provide insights, and engage in conversations, just as the real individual would. The replica draws upon a person or company’s expertise, experiences, and unique perspective to deliver authentic, personalized responses, essentially acting as a proxy.
Because Conversational Replicas function in real time, use rolling vision for context, and are given a persona, they closely mimic the experience of conversing face-to-face with humans. This is a huge step beyond text-based or even audio-based chatting.
SOURCE: BusinessWire