What Sora is — and what is new in Sora 2

Sora is OpenAI's flagship text-to-video model. You write a description of a scene — characters, environment, camera move, lighting — and the model returns a short, photorealistic video clip that respects basic physics and continuity. The first version launched publicly at the end of 2024. The current production model is Sora 2, which is what you are using when you sign in to sora.com today.

The Sora 2 release closed most of the gaps that frustrated early users of the original model. Faces look less plastic, hands and small objects break less often, and physics interactions like splashing water, falling cloth, or moving crowds look more natural. Sora 2 also handles synchronized audio in supported regions, so a clip of a beach can return with realistic wave sound and ambient noise rather than silence.

If you have heard people search for "sora 2 how to use" or "sora how to use sora", they are almost always describing this newer build. The workflow is identical to Sora 1 — same dashboard, same prompt box — but the output quality, audio, and editing tools (remix, extend, storyboard) all live in this generation. When this guide says "Sora", it means Sora 2 unless we explicitly call out the older release.

For a broader landscape view of where Sora sits relative to other models, our best AI video generators of 2026 roundup covers the alternatives in depth, and our full Sora review tracks the changing limits and feature set.

OpenAI Sora access: required plan tiers

Before you can do anything with the model, you need access. The OpenAI Sora access flow is straightforward: pay for a qualifying ChatGPT subscription, then sign in. Anyone searching for "openai sora access how to use" or "how to use sora openai" should start here.

• → Free ChatGPT: No Sora access. You can read about the model and watch sample clips, but you cannot generate.
• → ChatGPT Plus — $20/mo: Includes Sora 2. Generations capped per month, output up to 720p, clips up to ~10 seconds, standard queue.
• → ChatGPT Pro — $200/mo: Higher monthly cap (roughly an order of magnitude more), 1080p, clips up to ~20 seconds, priority queue, faster generations, full storyboard access.
• → ChatGPT Team and Enterprise: Sora access depends on the workspace administrator. Most Team plans inherit the Plus feature set; Enterprise customers should check with their account owner.
• → Sora API: Available to developers through the OpenAI API with usage-based pricing. Access controls and rate limits apply per organization.

There is no separate "Sora-only" subscription. Whatever plan you already use for ChatGPT determines how much you can generate. If you are deciding between Plus and Pro, the rule of thumb is simple: if you generate video more than a few times a week, or you need clips longer than 10 seconds, the Pro tier pays for itself in saved time. For a single occasional generation, Plus is fine.

Geographic availability matters too. Sora is restricted in the United Kingdom, parts of the European Union, and a handful of other regions for regulatory reasons, even with a valid paid plan. If sora.com refuses your sign-in despite an active subscription, your country is the most likely cause. A static IP from a supported region (where you legitimately reside) is required — VPN-based workarounds are against OpenAI's terms.

How to use Sora AI for the first time

Knowing how to use Sora AI on day one comes down to five clean steps. This is the same path whether someone searches "sora ai how to use", "sora how to use", or "sora how to use sora app".

1. Confirm your plan. Visit chatgpt.com, click your profile, and verify Plus or Pro is active. If you are on Free, upgrade first — Sora will not unlock without a paid plan.
2. Open sora.com. Go to sora.com and click "Sign in." Use the same email tied to your ChatGPT subscription. You will land on the Sora dashboard with a feed of community clips.
3. Click "New video." The button sits at the top of the dashboard. It opens the prompt composer with controls for aspect ratio, length, and resolution.
4. Write your first prompt. Keep it under 200 words. Describe one shot: subject, action, environment, lighting, camera. Example: "A red fox trotting across a snowy clearing at dawn, low cinematic camera, soft golden light, 24 fps."
5. Hit "Generate." Wait 1–4 minutes. Sora returns the clip in your library. From there you can download it, share it, remix it, or extend it.

That is it. The first generation is the slowest because you are learning what the model rewards. After ten or fifteen runs, your prompts get tighter and your output quality climbs sharply. Most professional users keep a notebook of "prompts that worked" so they can riff on proven formulas instead of starting cold each time.

How to use the Sora app — sign-up and interface

Many people search for "how to use sora app" or "sora app how to use" and assume there is a separate, hidden product. There is not. The "Sora app" is the same web app at sora.com, plus a native iOS app in supported countries. Both share one account, one library, and one billing relationship with your ChatGPT subscription.

To sign up: install the Sora app from the App Store (where available) or open sora.com in any modern browser. Tap "Continue with OpenAI", complete the sign-in, and accept the content policy. The first time you log in, the app pulls in your existing ChatGPT identity — you do not need a separate account.

The interface has four primary surfaces. The feed shows community clips and what your followed accounts have shared. The library lists every generation you own, with filters for status, aspect ratio, and prompt text. The composer is where you write prompts, attach reference images, set duration and ratio, and hit generate. The storyboard editor is where you sequence multiple prompts into a single multi-shot clip. Most beginners spend 90% of their time in the composer.

If you want to lean on the iOS app specifically, treat it as a capture and share device. It is excellent for queuing a generation while you are away from your desk, then reviewing the result on a larger screen later. Heavy prompt iteration is still faster on desktop because you can paste, edit, and reference notes in parallel windows.

How to use Sora in ChatGPT

The "how to use Sora in ChatGPT" workflow has changed over time. At launch, video generation lived inside chatgpt.com itself. Today, the cleanest path is to keep video work on sora.com, where the dedicated tooling lives, and use ChatGPT for prompt drafting. Many users still want a single chat interface, so here is how each option works.

Direct generation in ChatGPT. In supported regions, paid ChatGPT users can ask the assistant to generate Sora video directly inside a chat thread. The chat hands off to Sora, runs the generation, and returns the clip inline. This is convenient but lacks the storyboard editor, fine-grained controls, and library you get on sora.com.

ChatGPT as a prompt writer. A common workflow is to use ChatGPT (or Claude) to brainstorm and rewrite Sora prompts, then paste the finished prompt into sora.com. ChatGPT is excellent at converting a rough idea — "show me a moody noir detective scene" — into a tight, structured prompt with subject, action, lighting, camera, and atmosphere already baked in.

ChatGPT for editing notes. After a generation lands, drop the prompt and a description of what looks wrong back into ChatGPT and ask for a revised prompt. This is faster than rewriting from scratch and tends to produce better second drafts than re-prompting Sora cold.

If you switch between the two surfaces, remember they share an account but not a context. ChatGPT does not see your Sora library, and Sora does not see your chat history. Copy-paste is still the connecting tissue.

OpenAI Sora text-to-video: a prompt structure that works

People searching "openai sora text to video how to use", "openai sora video generation how to use", "sora ai video generator how to use", and "openai sora video generator how to use" are all really asking the same thing: what should I actually type? After hundreds of generations, the structure that delivers the most consistent results is the SACLAM formula — Subject, Action, Camera, Lighting, Atmosphere, Motion.

• → Subject: who or what is on screen, in concrete terms ("a young woman in a yellow raincoat", not "a person").
• → Action: what they are doing, with one clear verb ("walking", "looking up", "stirring a pot").
• → Camera: shot type and movement ("medium close-up, slow dolly forward", "wide aerial, locked off").
• → Lighting: source, direction, and mood ("warm golden-hour sun from camera left", "harsh fluorescent overheads").
• → Atmosphere: environment and weather ("light rain, glistening pavement, neon signs reflecting in puddles").
• → Motion: tempo and continuity ("subject moves slowly, camera tracks at the same pace, no cuts").

An example that follows the formula: "A young woman in a yellow raincoat (subject) walking down a narrow alley at night (action), medium tracking shot from behind, slow dolly forward (camera), neon shop signs casting cyan and magenta highlights on her shoulders (lighting), light rain, wet asphalt, faint steam from a manhole (atmosphere), measured pace, 24 fps, no cuts, 8 seconds (motion)."

That single prompt is much more likely to return a usable clip than "girl walking in the rain". Sora rewards specificity and punishes ambiguity. The model has to make a thousand micro-decisions; every concrete noun and verb you provide is one decision it does not have to guess.

Two more rules of thumb. First, name the style if you have one — "shot on 35mm film, anamorphic lens, slight grain" is a different result than "rendered in pixar 3D animation style". Second, keep the description to one shot. If you want multiple shots, use the storyboard editor (covered below) instead of asking for cuts inside one prompt.

For prompt-engineering basics that translate to other AI video tools as well, our AI image-to-video tools guide walks through the same principles for image-anchored generations.

How to use Sora 2 on PC

"How to use Sora 2 on PC" is one of the most common search queries because there is no installable Windows or macOS desktop app. The good news is that Sora is a web product, which means it works identically on Windows 10 and 11, macOS, ChromeOS, and Linux as long as you have a modern browser.

1. Open Chrome, Edge, Firefox, Brave, or Safari. Sora supports all current evergreen browsers. Outdated versions of Internet Explorer or legacy Edge will not work.
2. Visit sora.com. Sign in with your ChatGPT Plus or Pro account.
3. Optional: install as a PWA. In Chrome and Edge, click the install icon in the address bar to add Sora to your taskbar or dock. It runs in its own window with no browser chrome — close to a native app feel.
4. Use a wired connection if possible. Generations are server-side, so your only network requirement is a stable connection during upload of reference images and download of finished clips.
5. Plan for storage. 1080p clips at 20 seconds are 30–60 MB each. If you generate dozens per day, point your downloads folder at a drive with room to spare.

The PC experience is the most productive way to work with Sora because you can keep ChatGPT, your prompt notes, and the Sora composer side by side. Many editors run a three-window layout: Sora on the left for generation, ChatGPT in the middle for prompt iteration, and a notes app on the right for prompt history.

Aspect ratios, length limits, and resolution

Sora 2 supports three primary aspect ratios. Each one is purpose-built for a distribution channel, so pick the ratio before you write the prompt — Sora composes the frame differently for each.

• → 16:9 landscape. The default. Best for YouTube, embedded video, websites, and any presentation context. Sora frames subjects centrally with environment around them.
• → 9:16 portrait. Vertical for TikTok, Instagram Reels, YouTube Shorts. Sora favors close-ups and subject-driven framing because there is no horizontal space to work with.
• → 1:1 square. Best for static social posts and ads inside Instagram and LinkedIn feeds. Sora tightens framing further than 16:9 but keeps more environment than 9:16.

On length, Plus accounts cap at roughly 10 seconds and Pro accounts at roughly 20 seconds per generation. Resolution caps at 720p on Plus and 1080p on Pro. Both tiers limit the total number of generations per month — Plus runs out fastest because each clip counts the same regardless of length, so 10-second clips are more efficient on Plus than 4-second clips. Always check your usage indicator in the dashboard before a long batch.

If you need a 4K master, render at 1080p in Sora and upscale externally with a tool like Runway's upscaler or a dedicated AI upscaler. Sora itself does not generate at 4K today.

Remix and extend a video

Two of the most useful features in Sora 2 are remix and extend. Remix takes an existing clip — yours or another user's, where allowed — and regenerates it with modifications. Extend takes a clip and adds more seconds to the end, continuing the motion and scene logically.

Remix workflow. Open any clip in your library, click "Remix", and edit the prompt. You can rewrite portions, change the subject, swap the lighting, or pivot the camera. Sora keeps the overall composition and re-generates with the modified prompt. This is the fastest way to iterate when one clip is 80% right and you only need to fix one element.

Extend workflow. Click "Extend" on a finished clip and supply a continuation prompt. Sora analyzes the last frame and generates a new segment that continues from there. The result feels seamless when you describe the continuation in motion terms ("she keeps walking, then turns left at the next corner") rather than scene-cut terms ("then she enters a different room"). Use storyboard for hard cuts.

Extends consume a fresh generation credit, so they cost the same as a new clip. Remixes also consume one credit. Plan around this if your monthly cap is tight.

Storyboard mode — multi-shot generations

Storyboard mode is the answer when one prompt is not enough. It lets you sequence multiple prompts into a single timeline, with each prompt rendering its own shot, then stitches the shots together into one continuous video. This is how you build a 60-second cinematic sequence on Sora today.

1. Open the storyboard editor from the dashboard. You will see a horizontal timeline divided into shot slots.
2. Add shot 1. Write a prompt for the first shot using the SACLAM formula. Set its length (1–10 seconds on Plus, up to 20 seconds on Pro).
3. Add shot 2 and beyond. Repeat for as many shots as you need. Most narrative sequences land between three and eight shots.
4. Set transitions. Each shot transition can be a hard cut or a cross-fade. Cuts feel cinematic; fades are softer and match a mood-piece tone.
5. Render the full sequence. Each shot consumes a generation credit, plus a small overhead for the assembly. Pro accounts can render storyboards up to several minutes long; Plus accounts cap shorter.

The storyboard is also where you fix continuity errors after the fact. If shot 3 looks great but shot 4 changed the protagonist's outfit, you can re-render only shot 4 instead of redoing the whole sequence. Treat each shot as an independent generation that happens to share the timeline.

Costs and credits

Sora's billing model is a fixed monthly subscription, not pay-as-you-go. Both Plus and Pro include a monthly allowance of generations; once you exhaust it, you wait for the cycle to reset. There are no overage charges.

• → ChatGPT Plus — $20/mo. Includes a capped monthly Sora budget at 720p, clips up to 10 seconds, and standard queue priority.
• → ChatGPT Pro — $200/mo. Roughly an order of magnitude more generations per month, 1080p output, clips up to 20 seconds, faster queue, full storyboard.
• → Sora API. Pay-per-generation pricing for developers. Useful for automation but priced higher per clip than the bundled subscriptions.

One credit equals one finished clip, regardless of length within the tier limits. A 10-second Plus clip and a 4-second Plus clip both cost one credit. This is why most Plus users default to maximum length — the per-second cost drops the longer the clip is. Pro users have more headroom but the same logic applies.

The exact monthly cap and credit accounting can move; OpenAI revises both periodically. The dashboard always shows your current usage and remaining credits — check it before a heavy session. If you need clarity on whether your team should pay for Plus or Pro, our full Sora review tracks the current numbers, and our Runway vs Sora comparison stacks Sora's value against the main alternative.

Common errors and how to fix them

Most Sora errors fall into one of five buckets. Here is how to fix each.

• → "This prompt cannot be processed." Content policy block. Common triggers: named real people, copyrighted characters, weapons in active use, explicit content, certain political imagery. Rewrite to remove the named entity and describe a generic style or archetype instead.
• → "Generation failed — please try again." Server-side issue, usually transient. Wait 60 seconds and retry the same prompt. If it fails three times in a row, simplify the prompt or try a different aspect ratio.
• → "You have reached your monthly limit." You exhausted your credit allowance. Either wait for the cycle reset (visible in the dashboard) or upgrade Plus to Pro for the rest of the month.
• → "This region is not supported." Geographic restriction. Sora is currently unavailable in the UK and parts of the EU even with paid plans. Wait for OpenAI to expand availability — there is no legitimate workaround.
• → Output looks wrong (warped faces, bad hands, unnatural physics). Not an error per se. Sora 2 is much better than Sora 1 here, but small objects and rapid limb motion are still failure modes. Try a wider shot, slower action, or different camera angle. Avoid prompts that ask for fingers gripping small props or fast martial arts.

If a generation looks 80% right, remix it instead of regenerating. Remix gives Sora the framing it already produced as a starting point, which usually fixes the small thing without breaking the overall composition.

FAQ

Where to go next

Sora 2 is the highest-quality consumer text-to-video model on the market today, and the best way to learn it is to generate ten clips this week using the SACLAM prompt formula and the Plus tier. If your output looks pro after a week, keep Plus. If you are queuing five generations a day and hitting the cap, upgrade to Pro. If you need precise creative controls — motion brushes, camera keyframes, image-driven shots, multi-track timelines — pair Sora with Runway or evaluate alternatives like Pika, Luma AI, and Kling for the parts of your workflow Sora does not handle yet.

For a deeper feature breakdown, read the full Sora review. For a head-to-head against the main alternative, the Runway vs Sora comparison covers pricing, output quality, and use-case fit. For the broader market, the best AI video generators of 2026 ranks every credible model with verified pricing and feature lists.