Model · Video

Sora 2

OpenAI's video model that made short clips with matching speech and sound from a description or a still image. It was never downloadable, and OpenAI shut it down: the Sora app closed in April 2026 and the API on 24 September 2026. Listed for reference only.

Go to Sora 2’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
Only ever offered through OpenAI's app and API.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: The terms don't say clearly
OpenAI terms not re-read for this entry (the Sora tool entry reads them as assigning output ownership). Moot now the model is shut down.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost: No free plan.
Plans below.
How you use it: Maker's own API, Phone app, In your browser
Historical: launched with an iOS app and later an API. All routes now closed.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: No setup
Historical; the app needed no setup.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: OpenAI
No company address read in this pass, so no country.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: No longer available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A video, from a description (main use)
A video, by bringing a photo to life
A video, a soundtrack or sound for a video

text to videoimage to video

Inputs text and image; outputs video with audio (dialogue, effects, background sound).

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

Plan	Price	Includes
sora-2 API (per second)	$0.10 per seconds of video
sora-2-pro API (per second)	$0.30 per seconds of video

Prices shown as '$' only; USD assumed. No per-resolution split shown.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Real faces and voices: Copies a real face (characters / cameo (one-time video and audio recording)), checks the person's consent
Copies a real voice (characters / cameo (one-time video and audio recording)), checks the person's consent
App feature that put you or others into scenes after a recording; closed with the app.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Limits: note: API output 720x1280 or 1280x720; clip lengths not stated on the model page.
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Sora

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, Fotor, Genmo, getimg.ai, Google Flow

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.