Loading lesson…
Sora 2 moved from consumer-only to API in 2026. 60-second 1080p video from a prompt, callable from code.
Sora launched in 2024 as a consumer demo. In 2026 OpenAI opened an API. Developers can now generate 1080p video up to 60 seconds from a text prompt, an image, or another video — programmatically.
from openai import OpenAI client = OpenAI() response = client.videos.generate( model="sora-2", prompt="A librarian places a book on a shelf, soft afternoon light.", duration_seconds=10, resolution="1080p", aspect_ratio="16:9", ) print(response.video_url)A minimal Sora 2 API call (syntax current as of April 2026)8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-latest-sora-2-api-creators
What is the main idea of "Sora 2 API — video generation, programmable"?
Which concept is most central to "Sora 2 API — video generation, programmable"?
Which use of AI fits this topic best?
What should a careful learner remember about "Know the ethics line"?
You want to use AI after this lesson. What is the safest next step?
How should AI output about Sora 2 be treated?
Name one way to verify an AI answer about Sora 2.
Which action would help you apply "Sora 2 API — video generation, programmable" responsibly?