TEST | OpenAI | Page 1

Hi @somber prawn. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

Sora is OpenAI’s video-generation technology that creates short, high-quality videos with synchronized audio from text prompts or images.

There are two main ways it’s offered:

Sora app / Sora 2 (consumer) – An iOS and web app for creating and sharing short clips (typically 10–20 seconds). You describe a scene (subject, setting, motion, camera style, and audio), and Sora 2 generates a realistic video with synced sound. You can also start from an image, remix others’ posts, and use features like Cameos to include approved likenesses. [Getting started; Creating videos]
Sora API / Sora 2 & Sora 2 Pro (developer) – Models exposed via the Video API (sora-2 and sora-2-pro) that let developers programmatically generate videos (with audio) from prompts or images, control resolution and duration, and manage jobs (create, check status, download, list, delete). sora-2 is optimized for speed and iteration; sora-2-pro targets higher-fidelity, production-quality output. [Video generation guide; Sora 2; Sora 2 Pro]

Across both, Sora focuses on realistic motion, 3D space, and scene continuity, while enforcing safety rules (e.g., no real people or copyrighted characters in generations). [Video API]