D-ID, the company behind Deep Nostalgia, lets you create AI-generated videos from a single image

0
9

Israeli AI company D-ID, which provided technology for projects like Deep Nostalgia, is launching a new platform where users can upload a single image and text to generate video. With this new site, called Creative Reality Platform, the company focuses on sectors such as corporate training and education, internal and external communication of companies, product marketing and sales.

The platform is quite easy to use: users can upload an image of a presenter or select one of the pre-made presenters to start the video creation process. Paid users have access to premium presenters that are more “expressive” because they have better facial expressions and hand movements than the standard. After that, users can type the text from a script or simply upload an audio clip of someone’s speech. Users can then select a language (the platform supports 119 languages), voice and styles such as happy, sad, excited and friendly.

The company’s AI-based algorithms will generate a video based on these parameters. Users can then distribute the video anywhere. The company claims that the algorithm only takes half the video duration to generate a clip, but in our tests, it took a few minutes to generate a one-minute video. This may change depending on the presenter type and language you’ve selected.

ALSO READ  Firefly Aerospace reaches orbit for the first time

“The COVID-19 pandemic has accelerated the need for digital content around the world. A major problem for organizations is the creation of educational content. Reading documents and going through presentations can be dry and boring. In addition, they have to spend thousands of dollars to hire actors and make educational videos. So we use our AI to create presenters and educators to impersonate people and make the content more engaging and effective,” Gill Perry, the CEO of D-ID told TBEN in an interview.

Perry pointed to many use cases for this technology, ranging from a multilingual message from a CEO to employees to personalized needs for an organization’s users.

D-ID launched the studio in mid-August to test to fix bugs before the public launch. And while its main focus is to cater to businesses of all sizes, the company sees A lot of interest from makers on the platform.

Making offensive deepfake videos is a risk. That’s why the Israeli company has put in place guardrails, such as filtering swear words and racist comments, as well as image recognition to avoid using famous people’s faces. It uses the Microsoft Azure text moderation API to remove sexual comments and offensive language in video scripts. D-ID said the platform’s terms of use prohibit users from making political videos. If any of these rules are violated, the company may suspend the violator’s account and remove the video from the library.

ALSO READ  Wordle 471 Answer for Today: Here's Wordle Answer for October 4

D-ID raised $25 million in March in its Series B financing led by Macquarie Capital, totaling $47 million to date. Until now, the company relied on others to use its API to create content—Deep Nostalgia being a prime example—with clients such as Modelez, Warner Bros. and the India-based short video app Josh. Now the company is expanding its profitable products by launching a PowerPoint plugin along with this self-service platform. The plugin adds an interactive presenter to the deck, so users don’t just have to read slides. They can choose between different avatars, voices and languages ​​just like the self-service platform. But there is currently no provision to have a custom presenter.

At launch, users can sign up for a free 14-day trial account and shoot up to five minutes of AI-generated 720p video. After that, they can pay $49 per month to access 15 minutes of full HD AI-generated video, a PowerPoint plugin, and email support.

D-ID co-founders Eliran Kuta, Gil Perry and Sella Blondheim

Users can also upload their own audio clips for voice cloning. In addition, the company is working on a tool that will allow users to upload their own footage to train the AI ​​to be more expressive so that it can better imitate the person in the video. All these features are limited to the enterprise tier of the company.

ALSO READ  Meta to make it easier to switch between Facebook, Instagram accounts soon

While the company faces competition from companies like Rephrase.ai and Soul Machines in AI-generated video, it claims that there are hardly any companies that claim to generate high-quality videos from a single image.

Perry said D-ID doesn’t want to limit itself to corporate training, communications and marketing videos. It also has ambitions to enable real-time translation of video calls and clone presenters – making an avatar appear on video instead of you as you dictate the audio.

The company is also considering becoming a major player in web3/metaverse development. “Since we have expertise in generating videos from a single image. We’re thinking about ways to create digital avatars for the metaverse,” said Perry.