OpenAI’s much-anticipated text-to-video generator, Sora, is set to become available to the public in the coming months, offering users the ability to generate hyperrealistic scenes based on a simple text input.
Initially designed for visual artists, designers, and filmmakers, Sora will soon be accessible to a wider audience, allowing anyone to create stunning videos with just a few keystrokes. OpenAI has announced plans to further improve the tool by incorporating audio into the generated scenes, adding an extra layer of immersion and realism.
One of the most exciting features of Sora is that users will have the ability to edit the content in the videos it produces, giving them full control over the final product. The tool was trained using publicly available or licensed data, including content from Shutterstock, ensuring a diverse range of visuals can be created.
However, these cutting-edge capabilities come at a cost. OpenAI has revealed that Sora is “much more expensive” to power compared to other AI tools, due to the complexity of generating video content. Despite this, the company has stated its commitment to making the tool accessible at similar costs to DALL-E, their AI text-to-image model.
With its impending release, Sora is expected to revolutionize the way content creators approach video production, offering a new level of creativity and convenience in the digital space. Stay tuned for updates on the official launch of Sora and get ready to bring your ideas to life like never before.
“Zombie enthusiast. Subtly charming travel practitioner. Webaholic. Internet expert.”