Israeli AI startup D-ID has launched the Creative Reality Studio platform for creating narrator videos from a single image.
Users need to upload a photo of the presenter or select one of the available options. They can then insert the text they want to read or send a finished audio track of the speech.
The developers said that the platform supports 119 languages. Users can customize the voice, as well as set its mood.
Based on the specified parameters, Creative Reality Studio’s algorithms generate a video in which the synthesized speaker will realistically read the specified text.
According to the developers, the video generation time is half the length of the video. However, while testing the technology, journalists noticed that it took several minutes to create a 60-second speech.
The company is confident that their service will be in demand in such sectors as corporate training and education, internal and external communications, marketing and sales.
“We use our AI to create presenters and mentors that replicate people and make content more engaging and effective,” said D-ID CEO Gil Perry.
In order to avoid creating deepfakes, the developers have set a number of restrictions. Users cannot upload swear words, racist remarks, or photos of famous people. The rules of the platform also prohibit the creation of videos of political content.
In case of non-compliance with the terms of use, the company may suspend the violator’s account and remove his video from the library.
A 14-day trial is available for new accounts. After two weeks, users can subscribe for $49 per month and generate FullHD videos with a total duration of 15 minutes.
Recall that in March 2022, D-ID and MyHeritage taught photography to talk.
In October 2021, an Israeli startup developed the Speaking Portraits tool, which brings a person to life in a portrait shot.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER