Build human-like replicas and text-to-video with APIs
Introducing Phoenix – our breakthrough replica and text-to-video model, now available via APIs. Users create their own replica with 2 minutes of footage and generate authentic videos in 25+ languages in minutes. No more recording or retakes.
🌟 Howdy hunters! I’m Hassaan, the Co-Founder and CEO of Tavus.
We’re thrilled to launch our Developer Platform in Beta, with access to our new model Phoenix. It’s the most advanced replica and text-to-video model available via end-to-end APIs.
🎥 We know that for many people, recording yourself is a huge barrier to creating more video. So we’ve been heads down focused on delivering a level of realism in our replica videos that allows users to eliminate recording. The Phoenix model requires just 2 minutes of training data to create a high-quality AI replica that looks and sounds just like you.
🤖 Phoenix generates realistic replica videos from just a script, complete with natural face (lip, cheek, nose, chin) movements and expressions synchronized with your script and generated voice. Developed by our team, the model uses a novel approach that bypasses traditional methods and constructs dynamic, three-dimensional facial scenes using neural radiance fields (NeRFs).
❓ We’re so excited to give devs access to this model via dead simple APIs and see the amazing products y’all build with them. We’ve already heard and seen some incredible use cases and can’t wait to see more. Let me know what you’re thinking of building!
🙏 Take a look at the demo video and sign up for one of our plans https://www.tavus.io/developer
We’re still in Beta so there’ll be kinks to work out. We’d love to hear your thoughts 🙌
