It has been revealed that Google is planning to introduce a video rendering feature to Gemini, potentially rivaling OpenAI’s Sora.
The Gemini model, one of Google’s most significant advancements in artificial intelligence, already possesses a wide range of capabilities. It can perform various functions, from answering questions via voice chat to generating visuals. With the latest language model updates, it has become even more advanced in these areas.
Now, a newly discovered feature in Gemini has sparked excitement. This upcoming feature was found in the code uncovered by Android Authority.
The ability to create videos from text may also come
This feature is a video creation tool. After an in-depth analysis of version 16.6.23 of Google’s application, clues were found suggesting that such a feature is in development. Within the code, the term “videogen” appears, which combines “robin”, the internal codename for Gemini. Videogen is an abbreviation for video generation, indicating its purpose.
Recently, AI-powered video creation models have gained significant popularity, marking a major breakthrough in artificial intelligence. These models can now generate photorealistic videos that look indistinguishable from real footage—entirely from text prompts. OpenAI’s Sora is one of the most notable examples of this advancement. However, it seems that Google is preparing to compete with OpenAI by introducing a similar capability in Gemini.
Unfortunately, that’s all we know about Gemini’s new feature for now. Details such as its release date, functionality, and usage remain unclear. We will share more updates as soon as new information becomes available.
You May Also Like
Follow us on TWITTER (X) and be instantly informed about the latest developments…
Copy URL
