New App Lets You Talk Face-to-Face with ‘Photorealistic’ AI Human

D-ID, the company which produced the technology for Deep Nostalgia, has launched a beta version of a new web app that enables users to talk face-to-face with a “photorealistic” artificially intelligent (AI) human.

The company’s web app, which is called “chat.D-ID,” gives a synthetic human face and voice to AI-powered ChatGPT.

In the future, D-ID will allow almost any individual’s photo to be uploaded as the face of a digital human on the app.

ChatGPT’s API operates as the brain of chat.D-ID, while D-ID’s streaming text-to-video technology provides the audio and visual components of the photorealistic synthetic human that users can have a face-to-face conversation with by speaking and listening instead of writing and reading responses.

When a user opens the web app of chat.D-ID, they are greeted by an avatar called “Alice.” They can either choose to type their question or say their query by clicking the microphone icon in the app. According to D-ID, users can ask Alice almost any question that they want.

From a Single Photo to a Digital Human

The chat.D-ID app is still in beta with Alice as the only available face and voice, but D-ID tells TechCrunch that it plans to start adding other digital characters as options.

Eventually, users will also have the ability to upload any photo of their choice to serve as their personal ChatGPT human face. However, no celebrities or public figures will be allowed.

In the coming weeks, the chat.D-ID web app will let users generate a character, such as Dumbledore from Harry Potter, and choose the right human face for their conversation.

“The app is an easier way to use the power of AI and converse with ChatGPT,” D-ID CEO Gil Perry tells TechCrunch.

“We are wired to communicate with faces, we understand the situation better when we do. We feel more comfortable and we can observe complex information better when we’re in what feels like a real scenario. Video is more effective than text, so the app increases the power of large language models by adding a face.”

Last year, D-ID launched the platform Creative Reality Studio which lets users create their own AI-generated presenter in a video from a single photograph and reduce the cost and effort required for video production.

Image credits: All photos by D-ID.