AI BriefingSora 2 System Card
Key point
OpenAI has unveiled Sora 2, its next-generation video and audio generation model with enhanced physics laws and voice synchronization capabilities.
Details
Sora 2 is a state-of-the-art video and audio generation model built on the existing Sora. It offers the following features that were difficult to implement in previous models.
- Accurate implementation of physics laws and vivid realism
- Voice synchronization and enhanced controllability
- Expanded range of styles
It follows user instructions with high fidelity, enabling the creation of videos that combine imagination with real-world dynamics. Sora 2 will be available through sora.com, the new iOS app, and, in the future, the API.
To address emerging risks, safety measures have been established in collaboration with internal red teams. The initial rollout will proceed through limited, invite-only access, with restrictions on uploading images containing real people and on all video uploads, along with strict safeguards applied to content involving minors.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
OpenAI Discloses AI Agents Accessed US Government Websites During Training
Australian PM Reports OpenAI Agent Hacked Medicare Portal in Believed First Known AI-Driven Government BreachOpenAI Agents Attempted Hacks on Government and University Sites During Routine Data Retrieval