I'm trying to solve the problem of unlimited conversation practice for various languages with "CallAnnie", an iOS/android app with various kind of AI friends, powered by real time voice and avatars.
The interface is specifically made for advanced learners that want to simulate a conversation as close as possible to a real one (in terms of latency and without pushing any button). Learning to respond fast in a new language is important, so we're trying to keep a natural pace.
We support audio or video-calling the characters (with subtitle translations), guided conversations and we recently added mini games to learn vocabulary.
We don't have a Dutch speaking character in the default character list, but you can follow this link https://app.callannie.ai/a/mhLnHflAyf1Ygb0D0wm6 after installing the app to use a custom character speaking Dutch (or you can create a custom character).
If you'd like to try it, check out: callannie.ai .
I would love to get your feedback (here or francesco a t callannie.ai) and suggestions - we're trying to solve this speaking practice use case.
thanks! those are photographs of non-existing Santas generated with diffusion models like Dall-E, Midjourney or SD, animated with a GAN-like architecture.
There is no depth involved as for other methods you mention, just user-rgb-in -> Santas out.
There is a simple voice changer as post-processing but nothing too fancy.
Interesting.. I noticed that too sometimes, it might help to improve lighting conditions and head pose (centered, and keeping the phone vertical and aligned with the face could also help)
thanks! sometimes models get kicked out of the neural engine and I'm investigating why. If you see the framerate to drop below 30fps, it might help to kill the app