Guide
ChatGPT can't make videos with OpenAI's own model since Sora shut down
Updated
Not on its own any more. OpenAI closed the Sora app in April 2026 and the Sora API in September, so ChatGPT now helps you write and plan a video you make elsewhere.
In short
- ChatGPT can't make a video with OpenAI's own model as of November 2026, because OpenAI discontinued Sora.
- OpenAI closed the Sora web and app on April 26, 2026, and the Sora API on September 24, 2026.
- ChatGPT still writes scripts and shot lists, and it can look at a video you upload, though OpenAI says it may miss parts.
- Apps inside ChatGPT can do more: VEED says its GPT makes a video from a prompt, and Adobe says its app cuts a video you upload.
- If you film yourself talking, Cutroom's Magic Editor turns that one clip into a finished vertical video with no prompt-writing.
Can ChatGPT make videos?
No, not with OpenAI's own video model. Sora was that model, and OpenAI has shut it down. ChatGPT's own overview page lists writing, images, coding and voice, but no video.
So the honest answer depends on what you mean by making a video. Here's what ChatGPT does with each part of the job, as of November 2026.
What ChatGPT does for a video, November 2026
From OpenAI's help pages and the app makers' own pages, checked 12 November 2026.
| Job | Can ChatGPT do it? | How |
|---|---|---|
| Make a video from a prompt | Not by itself | Sora is closed; a third-party GPT such as VEED's can |
| Write the script | Yes | Ask for a script of a set length |
| Plan the shots | Yes | Ask for a shot list or a storyboard in words |
| Look at a video you upload | Partly | OpenAI says it may not analyse the whole video |
| Cut the video you filmed | Only through an app | Adobe's app in ChatGPT, by Adobe's own account |
Job: Make a video from a prompt
- Can ChatGPT do it?
- Not by itself
- How
- Sora is closed; a third-party GPT such as VEED's can
Job: Write the script
- Can ChatGPT do it?
- Yes
- How
- Ask for a script of a set length
Job: Plan the shots
- Can ChatGPT do it?
- Yes
- How
- Ask for a shot list or a storyboard in words
Job: Look at a video you upload
- Can ChatGPT do it?
- Partly
- How
- OpenAI says it may not analyse the whole video
Job: Cut the video you filmed
- Can ChatGPT do it?
- Only through an app
- How
- Adobe's app in ChatGPT, by Adobe's own account
What happened to Sora
Sora was OpenAI's video model, and for a while it was how ChatGPT users made videos from a prompt. OpenAI closed it in two steps in 2026.
Many pages that rank for this question were written before that, so they still tell you to open Sora. That advice no longer works.
- The Sora web and app experiences closed on April 26, 2026, according to OpenAI's help page.
- The Sora API, which developers used to build video into their own apps, closed on September 24, 2026.
- OpenAI says you can still export what you made at sora.chatgpt.com/sunset, and that it deletes the data after any final export window.
- OpenAI also says any ChatGPT or Sora credits you bought can still be used for Codex, its coding tool.
How Cutroom's Magic Editor edits a video like this
Jacob is the AI editor inside Cutroom's Magic Editor: it edits your video for you, then changes it when you ask in a chat.
The 4 styles, as example edits
Steps
Three steps, four angles
Skit
Hook, hard stop, demo card
Verdict
The tester's verdict
Poster
Typography does the talking
Hover or tap an example to play it, without sound. These are example edits of each style; the presenters in them are generated with AI.
- Your take: one video of you talking, up to 3 minutes
- Your style: one of 4: Steps, Skit, Verdict or Poster
- Your files: screenshots, a screen recording or a logo, if you have them
- Your goal: what the video is for, in a few words, if you like
- Jacob makes it: normally 10 to 15 minutes, and you get an email
- Your edit: ask Jacob for changes in a chat, then export
Then you ask Jacob, for example
- “Make this about 10 seconds shorter”
- “Put a clip on the strongest sentence”
- “Change the music to something calmer”
Each change is a new version, and going back is free. First cut 250 credits, each change 40, questions free, export 30 credits per started minute.
What ChatGPT still does for a video
ChatGPT is still useful before and after you film. It's good at the words, and apps you connect to it can handle some of the editing.
- It writes a script to a set length, such as a 30-second video with one hook and three points.
- It turns a script into a shot list, so you know what to film and in what order.
- It writes captions, a title and a description once you paste in what you said.
- It can look at a video you upload, on the Free plan too, but OpenAI warns the analysis may be incomplete or miss the audio.
- VEED says its GPT, for ChatGPT Plus users, writes the script, adds a voiceover and creates the video, which you then finish in VEED's editor.
- Adobe says its app in ChatGPT can make a quick cut, a highlight reel or a resized version of a video you upload.
Making a video from your own clip instead
For a lot of people, the video they need is them talking to camera. In that case you don't need a video model at all. You need the clip edited.
Cutroom's Magic Editor turns one clip of you talking into a finished vertical video. Jacob, its AI editor, makes the whole edit, and you change it by asking in a chat.
- You ask ChatGPT for a 30-second script with three points, then film it on your phone in one go.
- You upload the clip and a few product photos and press "Make my video". It normally takes 10 to 15 minutes, and you get an email when your first cut is ready.
- Jacob cuts the ums and the false starts, sets each numbered point as a big word and puts your photos on the words they belong to.
- Then you ask for changes in plain words, like "Make this about 10 seconds shorter". A message that changes the video costs 40 credits; a question is free, up to 20 a day.
- It doesn't make a video from a prompt or create new speech. It takes your own clip, up to 3 minutes, and returns one vertical MP4 at 1080 by 1920.
- Cutroom is not affiliated with OpenAI, Anthropic or Google.
A ChatGPT script, filmed once and edited
The script came from ChatGPT; the clip was filmed in one go and drawn here as Jacob's first edit in the Steps style.
Drawing of an example clip, not a customer video
Before · the clip as filmed
A 35-second phone video of a houseplant shop owner reading three care tips that ChatGPT wrote for her
“Okay, so, three ways to keep a fiddle-leaf fig alive. One, um, water it only when the top two inches of soil are dry. Two, give it the brightest window you have. … (pause) Three, don't, uh, don't keep moving it around.”
struck through = what Jacob cuts
After · Jacob's first edit, Steps style
“Three ways to keep a fiddle-leaf fig alive. One, water it only when the top two inches of soil are dry. Two, give it the brightest window you have. Three, don't keep moving it around.”
- On “One”: the word one set big under a floating window
- On “dry”: your product photo of a soil moisture meter cut in on the word
- On “window”: your photo fig-by-the-window.jpg in the floating window
- On “Three”: the word three set big as the last window opens
- Under the whole video: calm music under your voice
window: fig-by-the-window.jpg
Then you ask Jacob
- “Make this about 10 seconds shorter”v2the same three tips with the slow parts tightened, about 10 seconds shorter
- “Make the key words stand out more”v3one, two and three set bigger in your accent colour
Which tool to use for your video
Pick by what you start with: an idea in words, a video you already have, or a clip of you talking.
Which tool to use
Choose ChatGPT on its own if you need the script, the shot list or the captions, and you'll film and edit the video yourself.
Choose VEED's GPT in ChatGPT if you want a video generated from a prompt and you have ChatGPT Plus.
Choose Adobe's app in ChatGPT if you already have a video and want a quick cut, a highlight reel or a resize.
Choose Cutroom's Magic Editor if you film yourself talking and want the finished vertical video, then changes by chat. Your first video is free.
Questions people ask
- Is Sora still in ChatGPT?
- No. OpenAI closed the Sora web and app on April 26, 2026, and the Sora API on September 24, 2026. You can still export what you made at sora.chatgpt.com/sunset, OpenAI says.
- Can ChatGPT make a video for free?
- Not with OpenAI's own model. On the Free plan ChatGPT can write a script and look at a video you upload. VEED says its video GPT is for ChatGPT Plus users.
- Can ChatGPT edit a video I upload?
- Not by itself. ChatGPT can look at an uploaded video, but OpenAI's help page doesn't describe it handing back an edited file. Apps such as Adobe's say they can cut or resize it inside ChatGPT.
- Can ChatGPT write a video script?
- Yes, and it's one of the most useful things it does for video. Give it the length, the topic and who it's for, then ask for a hook and a clear ending.
- What should I use now that Sora is gone?
- It depends on the video. For a video made from a prompt, a text-to-video tool such as VEED's GPT fits. For a video of you talking, an AI editor that edits your own clip fits better.
- Does Cutroom make videos from a prompt?
- No. Cutroom edits a clip you film of yourself talking: Jacob cuts it, adds captions and puts your photos and b-roll on the right words. Cutroom is not affiliated with OpenAI, Anthropic or Google.
Got a script from ChatGPT? Film it once and let Jacob make the edit. Your first video is free.