Announcing our seed round. Read more.
Logo

Tavus Launches World's Fastest Conversational Video Interface Powered by Cartesia

October 22, 2024

"Cartesia’s Sonic model is a game-changer for our Conversational Video Interface. Its ultra-low latency of 90ms and high-quality voice generation have enabled us to create truly immersive real-time conversations with AI digital twins. The natural voices and voice design capabilities have elevated our product to new heights."

Hassaan Raza, Co-Founder and CEO, Tavus

Tavus is a generative AI video research company that enables developers to build digital twin video experiences through easy-to-use APIs. They’re revolutionizing the way we interact with AI by creating the world's fastest Conversational Video Interface (CVI) for AI digital twins. Their technology enables real-time, immersive conversations with AI replicas, opening up new possibilities in marketing automation, eCommerce,, corporate training, customer engagement, and entertainment. 

When Cartesia met the Tavus founders, they were already pushing the limits of AI performance. Tavus had previously faced challenges with auto-scaling and network delays in their existing setup.

Partnering with Cartesia has been a game-changer. Cartesia's Sonic model, with its consistent sub-90ms latency, has enabled Tavus to simplify their infrastructure while meeting their stringent performance requirements. Users have praised the quality, with some specifically requesting Cartesia as their preferred text-to-speech engine.

Read their CEO, Hassaan's announcement here Developers can easily integrate Tavus's technology using their comprehensive API documentation.

Tavus Launch

The Challenge

Tavus set out to build a platform that could facilitate natural, real-time video conversations with AI digital twins. This ambitious goal required overcoming several technical challenges:

  1. Achieving ultra-low latency for seamless interactions
  2. Generating high-quality, natural-sounding voices in real-time
  3. Creating convincing AI replicas that could see, hear, and respond naturally
  4. Developing a scalable system to handle multiple concurrent users

The Solution: Cartesia's Sonic Model

Tavus chose Cartesia's Sonic model as the cornerstone of their voice generation system. Sonic's state space model capabilities aligned perfectly with Tavus's need for high-quality, low-latency voice generation:

  1. Ultra-Low Latency: Sonic's sub-90 ms latency enables Tavus to achieve end-to-end response times of less than 1 second, creating truly conversational experiences.
  2. Natural Voice Quality: Sonic's advanced voice generation produces lifelike speech, essential for creating convincing AI digital twins.
  3. Voice Design and Cloning: Sonic's instant voice cloning and design features allow Tavus to create unique voices for each AI replica, enhancing the personalization of their platform.
  4. Multilingual Support: With support for multiple languages, Sonic enables Tavus to expand their platform globally.
  5. Scalability: Cartesia's infrastructure easily handles Tavus's need for multiple concurrent users, ensuring smooth performance during peak usage.

Results

By integrating Cartesia's Sonic model, Tavus has achieved remarkable results:

  • Sub-1 Second Latency: The CVI now operates with less than 1 second end-to-end latency, creating a natural conversational flow.
  • Enhanced Realism: Users report that conversations with AI digital twins feel incredibly lifelike and immersive.
  • Expanded Use Cases: Tavus has successfully deployed their technology in various sectors, including education, corporate training, and entertainment.
  • Scalability: The platform effortlessly handles multiple concurrent users, paving the way for widespread adoption.

Tavus continues to push the boundaries of AI interaction, with plans to expand their CVI technology into new markets and use cases.

"What Tavus is doing with AI-human interaction is mind-blowing. Their team has an uncanny knack for pushing boundaries, and we're stoked to be powering their Conversational Video Interface with Sonic. Watching their digital twins engage in natural, real-time conversations feels like stepping into the future. It's an exciting journey, and we're honored to be along for the ride."

Karan Goel, CEO, Cartesia