Tags: AI video generation

OpenAI announced Sora 2, its second‑generation video‑synthesis AI that can generate videos with synchronized dialogue and sound effects, marking the company’s first foray into audio‑enabled video generation. The launch also introduced a new iOS social app that lets users insert themselves into AI‑generated videos through a feature called “cameos.” Sora 2 demonstrates visual consistency improvements, the ability to follow complex multi‑shot instructions, and more realistic physical movements such as gymnastics routines and triple axels. OpenAI describes the release as a “GPT‑3.5 moment for video,” positioning it as a major step forward from the original Sora model. Read more

OpenAI announced the release of Sora 2, an advanced audio‑video generation model, alongside a new social app called Sora. The app lets users create short videos, add their own likeness through a “cameos” feature, and share them on a TikTok‑style feed. Sora includes parental controls, algorithmic personalization options, and a free launch with paid generation during high demand. The service initially rolls out in the United States and Canada, with plans to expand. OpenAI emphasizes safety measures and user consent for AI‑generated likenesses. Read more

OpenAI introduced Sora 2, an AI system that creates realistic video and synchronized audio, alongside a TikTok‑like social app that lets users generate and share videos featuring their own likenesses. The rollout includes parental controls, watermarking, and strict policies that prevent the creation of deepfakes of public figures without consent. While OpenAI touts the technology as a step toward useful world simulators, it also acknowledges the potential for misinformation and emphasizes built‑in safeguards such as metadata signals and content moderation. Read more

OpenAI has launched Sora 2, an AI video generation model paired with an invite‑only iOS app that lets users create short videos from text prompts. The new platform adds a "cameo" feature that enables users to insert their own face and voice into generated scenes, while offering synced audio, improved physics, and a TikTok‑style feed for remixing and sharing. Robust safeguards—including explicit opt‑in, identity verification, parental controls, and moderator review—aim to mitigate deepfake and disinformation risks. Sora 2 enters a crowded market alongside offerings from Google, Runway and Meta. Read more

OpenAI unveiled Sora, an AI‑powered video generation app built on the new Sora 2 model. Currently limited to iOS users in the United States and Canada, the app requires an invitation and lets early adopters invite four friends. Sora offers a "cameo" feature that lets users grant permission for their likeness to appear in generated clips, designating them as co‑owners who can delete or restrict further edits. The app also includes a Remix function for re‑imagining trending videos, while blocking the creation of pornographic content and videos of public figures unless explicit consent is provided. Read more

Luma AI has introduced Ray3, its first reasoning-based video generation model, now available to users. By allocating more computing time to analyze prompts, Ray3 can handle longer, more complex action sequences than typical AI video tools, which usually produce clips of five to ten seconds. The model includes a visual annotation interface that shows its decision‑making process, a draft mode that creates low‑resolution drafts in about 20 seconds, and the ability to upscale to high‑fidelity 16‑bit HDR video in two to five minutes. Ray3 joins a growing field of generative video tools from companies like Midjourney and Google’s Veo 3, while also raising ongoing concerns about AI‑generated media and artist lawsuits. Read more

Envato announced that all paid plans will provide unlimited AI video generations through its Elvato service until September 30. The lowest‑priced tier, at $16.50 per month (or £12.50), now includes unrestricted access to Veo 3 and Kling models, as well as other video‑gen engines. A free account still allows five videos per month. Generated videos carry a lifetime commercial license, and speech‑enabled videos automatically use Google Veo 3. Envato’s CMO Noelle Kim framed the change as a move to remove barriers for creators. Read more