OpenAI Sora 2 is Here: Key Takeaways
Artificial Intelligence disruptor, OpenAI, Tuesday September 30, 2025 launched Sora 2 – a new version of its AI video maker app released last year.
Artificial Intelligence disruptor, OpenAI, Tuesday September 30, 2025 launched Sora 2 – a new version of its AI video maker app released last year.
The company which came to limelight after it launched ChatGPT in January 2023 described the Sora 2 release as a major leap forward in AI's ability to create realistic video.
The new social video app can generate synchronized dialogue, sound effects, and physically accurate motion, OpenAI said.
"Sora 2 can do things that are exceptionally difficult – and in some cases outright impossible – for earlier video generation models," OpenAI said, pointing to examples like capturing Olympic gymnastics routines or basketball moves.
Sora 2: Key Features
Sora 2 replaces last year's Sora and represents the latest salvo in the AI arms race that began with ChatGPT's launch. The new app is currently available by invitation (via invite code) only to users in the United States and Canada.
Sora 2 is a video-based app where users can record short videos and give them an AI twist for sharing.
The app has more of a TikTok-style algorithm, but with AI, users can be imaginative with text prompts and generate videos and images into hyperreal videos.
Unlike earlier systems that would "morph objects and deform reality" to fulfill text prompts, Sora 2 better follows real-world physics, the company said.
With the launch of Sora 2, OpenAI jumps to what the company thinks may be the GPT‑3.5 moment for video.
“Sora 2 can do things that are exceptionally difficult, and in some instances outright impossible, for prior video generation models: Olympic gymnastics routines, backflips on a paddleboard that accurately model the dynamics of buoyancy and rigidity, and triple axels while a cat holds on for dear life”, the company said.
Closer to Real World
The model is also a big leap forward in controllability, able to follow intricate instructions spanning multiple shots while accurately persisting world state. It excels at realistic, cinematic, and anime styles.
As a general purpose video-audio generation system, it is capable of creating sophisticated background soundscapes, speech, and sound effects with a high degree of realism. Users can also directly inject elements of the real world into Sora 2.
The Sora 2 video generator will initially be free with "generous limits," though usage will be constrained by the shortage of computing power needed for video generation. On the app, users can share their creations in a feed similar to TikTok or Instagram Reels.
Sora Cameo
OpenAI Tuesday also launched a new social iOS app powered by Sora 2 and called just “Sora”.
Using the app, users can create, remix each other’s generations, discover new videos in a customizable Sora feed, and bring yourself or your friends in via cameos.
“With cameos, you can drop yourself straight into any Sora scene with remarkable fidelity after a short one-time video-and-audio recording in the app to verify your identity and capture your likeness”, OpenAI said.
"A social app built around this 'cameos' feature is the best way to experience the magic of Sora 2," the company said.
Sora 2 also provides features to combat doomscrolling, disabled by default for users under 18, and promote healthier usage. It also claims to encourage users to spend more time being creative.
Sora 2 default feed also prioritises videos from friends or creators who are followed by the users. Once the app notices constant scrolling, it prompts users to start creating content.
Follow ummid.com WhatsApp Channel for all the latest updates.
Select Language to Translate in Urdu, Hindi, Marathi or Arabic
