Although we usually say that we “talk” with ChatGPT, the truth is that what we do write to the chatbot and read its responses. This nuance may sound like that, like a minor detail, but the truth is that it is not completely. Services like WhatsApp and the like, and earlier SMS, as well as email and so on, have made text communication much more common now than it was 20 or 30 years ago, but still, for many people the most comfortable system for Communicating is verbal, especially to have conversations like the ones that many chatbots propose to us.
On the other hand, and as I predicted when OpenAI opened the ChatGPT API, We have seen all kinds of proposals appear that try to add some added value to what chatbot technology already offers, in a progression that we can be sure will continue at least in the short term. Forefront’s personalities and Poe’s custom chatbots are just two examples of an ecosystem that is expanding by the second, making the offer not only more abundant, but also much more diverse and therefore interesting.
This, which is good for users, forces the creators of these implementations to try harder, in the search for original proposalswith which to stand out from this growing competition, whether it is offering access from different channels, integrating several chatbots into a single service, adding their functions to other applications and services, etc., something that, in turn, serves to substantially extend the ChatGPT scope, derivatives and the like.
One of the most recent and interesting examples that I have found in this regard is an app for iOS, which is also available through the web, although in a more limited way. Her name is Call Annie and she offers us to make a video call to a chatbot who, as you can tell, is called Annie. As you can see in the images above the previous paragraph, but only if you have an iPhone 12 or higher, you will be able to talk to this artificial intelligence-based assistant, and have a conversation that provides a reasonably natural experience.
Call Annie web interface.
To this end, Call Annie combines several technologies. The basic one, of course, is the generative AI model that generates responses from our prompts, but in addition to this we also find another AI, responsible for converting our voice to text. And, on the other hand, also those responsible for animating the model, initially created with Midjourney, so that its response, which is transformed with a text-to-speech solution, synchronizes it with the facial expressions of the animation. The set, therefore, has a most interesting technical invoice.
As I said before, the video conferencing function through the app is only available for iPhone 12 and above, since the animation of the image is made by Neural Engine. However, for those who have previous models, the same function that we can find through the web is offered, in which the conversation is exclusively through voice.
In this regard, by default Annie speaks in English, although you can speak to her in Spanish, which also makes it a very interesting option to practice the language. It is true, of course, that you can ask him to answer you in Spanish, but since his text-to-speech solution is designed exclusively for English, the result will be a bit… disconcerting.
