redsh

What was the prompt and how are you hosting it? :)

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.

You can see a quick intro and demo video here: https://www.sixthtone.com/news/1013961

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.

I wondered if this was possible, so I tried to build it, and I ended up making an app: Call Annie (https://apps.apple.com/us/app/call-annie/id6447928709). Feel free to try it out and let me know what you think

callannie.ai is faster and has and video characters too

callannie.ai has browser support, and video characters too

a lifesaver!

https://aigrant.org/ for AI projects

The new lean startup. 3,291 kg

nice! thanks. do you prefer the face video mode, or just audio for that?

ipad model? We have requirement on the apple chip generation of the iphone 12

yes, it's based on gpt3.5.. thanks!

maybe now it's a good time to try again :) will look at how it went, thanks for the tip

(The smallest one - that is awesome considering the size)

Telemarketers deserve much less than chatgpt3.5. Maybe, GPT-J

added the region.. it should be available now

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)

sorry about that! according to the spec the iPhone SE 2nd Gen has the A13 chip which is not the same as iPhone 12 (that has the A14 chip).

Unfortunately the newer phones have more neural network layers available and they are needed to meet the Santas Quality Certification.

I'll make it more clear in the description next release, thanks!

https://support.apple.com/kb/SP820?locale=en_US

with this App you can be Santa yourself and avoid any cigarette problems! We're also going to release the tooth fairy and elves

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

Preview of the app https://www.youtube.com/shorts/Iq6nh2SOIR0

Hi! I'm the founder of animato.ai and we released the first version of our real time AI avatar app that you can use as a virtual camera on the Mac.

You can use it to livestream or video chat with enhanced privacy and/or fun.

Glad to hear your feedback!

https://itunes.apple.com/app/1658475271

See you in Rome

Too much comfort? Do you know what you want?

Maybe you just need a new challenge? It seems you were finding some motivation in side projects. Also consider baking pizza

I strongly thing about it!