- Openai should soon publish the SORA 2 AI video model
- Sora 2 will face strong competition from the Google Veo 3 model
- Veo 3 already offers features that Sora does not do, and Openai will have to improve both what Sora can do and how easy it is to use possible customers
Openai seems to finalize the plans to publish Sora 2, the next iteration of his video text model, based on references identified in the Openai servers.
Nothing has been officially confirmed, but there are signs that Sora 2 will be a major upgrade targeting the Google VEO 3 video model. It is not only a race to generate prettier pixels; It is about the sound and the experience of producing what the user imagines when writing an prompt.
Sora d’Openai impressed a lot when he made his debut with his high quality images. However, they were silent films. But, when Veo 3 made his debut this year, he presented short clips with cooked and synchronized environmental speech and audio. Not only could you look at a man pouring coffee in slow motion, but you can also hear the sweet lighting of liquid, the ceramic ball and even the buzzing of a dinner around the digital character.
To bring out Sora 2 as more than a simple option for Veo 3, Openai will have to understand how to sew credible voices, sound effects and ambient noise in even better versions of his visuals. It is delicate audio, especially the lips, is delicate. Most AI video models can show you a face saying words. The magic tip gives the impression that these words came from this face.
It is not that Veo 3 is perfect for matching sound in the image, but there are examples of videos with an audio coordination surprisingly tight, background music that corresponds to mood and effects that correspond to the intention of the video.
Admittedly, a maximum of eight seconds per video limits the scope of success or failure, but fidelity to the scene is necessary before considering the duration. And it is difficult to deny that it can make videos that look like real cats that jump high dives in a swimming pool. Although Sora 2 can extend to 30 seconds or more with regular quality, it is easy to see it attract users looking for more space to create AI videos.
Sora 2 film mission
Sora d’Openai can extend up to 20 seconds or more high quality videos. And as it is integrated into Chatgpt, you can be part of a wider project. This flexibility is important to help Sora stand out, but audio absence is notable. To compete directly with Veo 3, Sora 2 will have to find his voice. Not only find it, but gently weave it in the videos it produces. Sora 2 could have an excellent audio, but if he cannot exceed the Way without seam of VEO 3 connects with his visuals, this might not have any importance.
At the same time, making Sora 2 too good could cause your own problems. With each new generation of AI video model, there is more concern to blur the line with reality. Sora and Veo 3 do not allow both of the invites involving real people, violence or content protected by copyright. But the addition of audio offers a whole new dimension of control over the origin and the use of realistic voices.
The other big question is pricing. Google A Veo 3 behind the Gemini Advanced Pay Wall, and you really have to subscribe to the $ 250 a month Ai Ultra if you want to use Veo 3 all the time. OPENAI could bring together access to Sora 2 in the Chatgpt Plus and pro third parties in a similar way, but if it can offer more at the level, it is likely to extend its user base.
For the average person, the AI video tool in which it turns will depend on this price, as well as the ease of use, as much as the features and the quality of the video. There is a lot to do with Openai if Sora 2 will be more than a silent blip in the AI race, but it seems that we will discover how good it can be in competition soon.
