Glif
AgentsWorkflowsModelsLearnAPIDocs
Sora mark

Sora 2

A powerful OpenAI text-to-video media generation model capable of producing high-fidelity videos with synced audio from text prompts, and optionally from reference images. It automatically resizes reference images to match the selected aspect ratio.

Use this model

Speed

Price

Inputs

TextImage

Outputs

VideoAudio

Lab

OpenAI

Sora 2 sample outputs

Captured directly from our eval suite. Click any tile to inspect the full render.

Action sequence test

“A hooverboarder performing an ollie trick in a city skate park, smooth camera following motion, golden hour lighting”

EngineId: openaiSora2

•

Duration: 8

•

AspectRatio: 16:9

Comic book history style test

“A 4-panel comic book style history of the world, from the beginning of time to the present day, with a focus on the most important events and figures in history.”

EngineId: openaiSora2

•

Duration: 8

•

AspectRatio: 16:9

iPhone handheld shot test

“An entity called Gliffy walks down an alleyway, filming himself with a phone.”

EngineId: openaiSora2

•

Duration: 8

•

AspectRatio: 16:9

Miniature diorama img2video

“Tilt-shift miniature diorama of a trebuchet in a medieval siege camp”

EngineId: openaiSora2

•

Duration: 8

•

AspectRatio: 16:9

More from the Sora family

Explore other options from the same family.

Sora mark

Sora 2 Pro

OpenAI

Launch your first agent today

Build without code. Share without limits.

Create an Agent

Resources

  • Guide/Docs
  • API
  • Chrome Extension
  • Contact Us

Company

  • Jobs
  • Brand
  • Legal
  • Privacy Policy
  • Security

Social

  • X (Twitter)
  • YouTube
  • TikTok
  • Instagram
  • LinkedIn

Community

  • Discord

© 2023-2025 Spellcasters, Inc.