The Sora text-to-video artificial intelligence will be made public later this year


“Sora” is an AI model from OpenAI which can turn text prompts into jaw-dropping 60-second videos and, now, OpenAI says it will become publicly available later on in 2024.
OpenAI first showed off “Sora” earlier this year, ironically on the same day that Google announced Gemini 1.5.
The text-to-video AI model caught attention for its ability to create stunning videos based on text prompts, with some examples almost indistinguishable from actual video captures.
As it stands, OpenAI has said that “Sora” is limited to 60-second videos, but the results have been pretty incredible.
So far, though, the only output we’ve seen has been from OpenAI, as the model hasn’t been publicly available.
That’s soon to change, though.
In an interview with The Wall Street Journal, OpenAI’s Mira Murati confirmed that “Sora” is coming “definitely this year” and potentially in “a few months.”The interview also confirmed that OpenAI aims to allow users to “edit” output by directly asking to fix issues in the videos.
The model also won’t work with audio for the time being.
Where “Sora” got its training data was also a core part of the interview, with Murati confirming that “publicly available” video and licensed video from Shuttershock was used to train the model, but many specific questions, such as if YouTube videos were used, were left unanswered.
More on AI:Follow Ben: Twitter/X, Threads, and Instagram

OpenAI has developed an AI model called “Sora” that can transform text prompts into stunning 60-second videos. According to OpenAI, this model will be made available to the general public later in 2024.

Strangely, the day that Google unveiled the Gemini 1.5 coincided with OpenAI’s initial unveiling of “Sora.”. The text-to-video artificial intelligence model gained notice for its amazing ability to produce videos using text prompts; in fact, some of the examples were nearly identical to real video captures.

Although OpenAI has stated that “Sora” is currently only available for 60-second videos, the outcomes have been really amazing. To date, however, the model has not been made publicly available, so the only results we have seen come from OpenAI. However, that will soon alter.

“Sora” will launch “definitely this year” and possibly in “a few months,” according to OpenAI’s Mira Murati, who spoke with The Wall Street Journal about this. “.

The interview verified that OpenAI’s goal is to enable users to “edit” output by asking the system directly to correct problems in the videos. Moreover, the model is currently unable to function with audio.

An important aspect of the interview was finding out where “Sora” got its training data. Murati confirmed that the model was trained using licensed video from Shuttershock and “publicly available” video, but many specific questions, like whether YouTube videos were used, were left unanswered.

Additional Information on AI:.

Observe Ben on Instagram, Threads, Twitter/X, and Twitter.

Leave a Reply

scroll to top