OpenAI is preparing to release Sora 2, a new version of its text-to-video model, aiming to compete with Google's Veo 3 . Sora, which shipped on December 9, 2024, has already been integrated into Microsoft's Bing Video Creator .
Sora is an AI model that creates video from text, capable of generating videos up to a minute long while maintaining visual quality and adherence to the user's prompt . It can create complex scenes with multiple characters, specific types of motion, and accurate details of the subject and background . The model has a deep understanding of language, enabling it to accurately interpret prompts and generate compelling characters that express vibrant emotions .
Google, on the other hand, has already announced Veo 3, which allows users to add sound effects, ambient noise, and even dialogue to their creations, generating all audio natively . Veo 3 also features improved prompt adherence, meaning more accurate responses to your instructions . Furthermore, Veo 3 is available via the Gemini API in Google AI Studio and to Google AI subscribers in the Gemini app .
While Sora has the ability to create realistic and imaginative scenes from text instructions , there are still challenges regarding physics and complex actions over long durations . OpenAI has taken measures to address potential abuses, such as the creation of extreme violence, sexual content, or material that violates intellectual property .
The release of Sora 2 is expected to bring improvements in these areas and offer a more comprehensive video creation experience. However, OpenAI may not have the technological infrastructure to compete with Veo 3, at least until late 2026 .
The battle between Sora 2 and Veo 3 is expected to intensify competition in the field of AI-driven video creation, offering users more choices and capabilities .