Conversational Replicas by Tavus - Build with real-time digital twins that speak, see & hear

With CVI, developers can now build live video conversations with digital twins – that actually feel real. It's the only end-to-end conversational pipeline with less than a second of latency. Check out a live demo on our website

Add a comment

Replies

Best
Holy Smokes! I just did the live demo on your website and the AI replica saw the tattoo on my arm and made a remark about it! This is insane! Your team has taken this to a whole new level! Amazing JOB! Cheers!
Thats AWESOME!!! What a cool experience- glad you were able to experience the magic 🤩
Try out our free plan and test more cool conversations :)
Honestly till you guys showed up, all the other companies in this space were just playing games. They were keeping everything exclusive and little innovation could occur. Several shut me down after PROMISING we could use their APIs because our product Creatoor AI got a lot of traction fast. I’m so happy and thankful to be one of the first companies and use-cases using your tech. And we’re DEFINITELY going to find a way to integrate this new amazing one as well hahaaaa
Building in public is always the way to go :) and yikes, I'm really sorry you had that experience! Super exciting to see the growth of Creatoor AI- would be amazing to work together. Happy to support however we can, and make sure the product works amazing for you and your use case🚀
Thanks so much for the comment Olumide. We are laser focused on serving developers and providing a gold standard experience, so we really appreciate this! We've built with product dev teams in mind - keeping things modular and flexible. We are also big on co-building. Happy to chat when you are ready!
🐐🐐
Super cool to see such low latency with CVI! This could really change how we engage with digital twins. Great work ! Looking forward to the live demo!
Thank for your support!! You can try our demo with Carter here Enjoy!
So glad you liked it- and definitely be sure to checkout the demo. It's mind blowing!
It has been such a joy working on the machine learning side of the Conversational Video Interface for Tavus! Lots of work has gone in to making the performance splendid and many many details feel seamless. As Tavus is a developer platform, I cannot to see what new applications engineers will come up with. Particularly, I hope to see video-native applications emerge, in addition to AI apps that will go text->audio->video. Enjoy everyone!
really excited about what the future holds here- and can't wait to see what developers (and you) build with the APIs :)
I like the concept but some of "Carter's" responses felt prerecorded ...
Hey Gabor- none of Carter's responses are pre-recorded :) It is using an LLM in the background and always generating each response. You can try this out by changing the LLM!
it’s all generated, from the LLM, TTS, and Phoenix Replica model. I’ll be giving a talk about how it all works next week. Stay tuned.
Ok gotcha. When I tried it it sometimes did prompt refusal - e.g. "Let's not talk about your coding question, let's talk about you"
Ah- the Carter LLM is prompted to try to stay on topic and get to know the person speaking to it. However you could prompt the LLM as you choose!
Ah gotcha, thank you!
This is pretty groundbreaking, ! The CVI sounds like a game-changer for interactive AI. Can't wait to see how makers utilize this tech to create some surreal experiences. The potential for digital twins in industries is massive. Let's start shaping the future of conversation! 🚀
Appreciate your support, 🤩 It's builders like y'all that are shaping the future. Glad we can be a part of it
Incredible work on Conversational Replicas! I'm super excited to experiment with Taivu's video AI features. Keep up the fantastic work!
Thanks Tanay! We're super excited to have you experiment- excited to hear your feedback from the free demo 🚀
Digital twins! This is such a game-changer. Huge kudos to Tavus for leading the way in video AI, you're setting a high bar for innovation.
Thank you for your support!! Have you seen our live demo yet?
pushing the boundary on AI video since 2020, and this is only the start! Thanks for the support Amy- excited for what the future holds here 🚀
The latency and accuracy is crazy. Can't wait to test this out. Congrats Tavus team!
its a whole different world- it's insane! Thanks for the support, Paul. It takes a village! 🙏