Can ChatGPT edit videos? It can look at one, not cut it

Not in the way a video editor does. As OpenAI's help pages stood on 15 November 2026, ChatGPT accepts a video as an attachment and may use tools to analyse it, with a warning that the analysis can be incomplete. We found no help page describing a feature that cuts, captions or exports a video. Sora, OpenAI's video generator, was discontinued on 26 April 2026. What ChatGPT is good for is the thinking round an edit: a script, the strongest lines of a transcript, a title and a caption. We make Burncaps, a tool that does the cutting and captioning, so read the rest knowing that.

or drop your video or podcast here
MP4 or MOV, or audio for subtitles.

The video never leaves your browser. On a computer, the sound is heard on your own device unless you choose our speech service or the computer is too slow to listen well; on a phone, it goes to our speech service unless you keep it on the phone. The service gets short pieces of sound, never the picture.

  • Read 15 Nov 2026
  • Written by a toolmaker, said up front
  • Video never uploaded

Live preview, rendered on this page by the same engine that captions your video.

What ChatGPT does with video, as OpenAI's help pages state it

What you might askWhat OpenAI's pages say
Attach a video fileYes, as an attachment, including on Free plans. Availability varies by platform, upload method and account, and a video counts toward your file-upload limit
Tell me what is in itChatGPT may use tools to analyse it. The page says the analysis can be incomplete or inaccurate, and may not cover the whole video or interpret its audio accurately
Transcribe what is said in itNot as an audio upload: MP4 and WebM files identified as video are not supported there. Can ChatGPT transcribe audio?
Cut it, trim it, join clips, burn in captions, change its shape, export an MP4No help page we found describes any of these. A search of the Help Center for “edit video” returned no article about editing a video in ChatGPT
Run code on the fileThe data analysis page says ChatGPT writes and runs Python for some tasks, and lists spreadsheets, PDFs and text and data files as supported. Video is not on that list
Make a new video from a promptSora's web and app experiences were discontinued on 26 April 2026 and its API on 24 September 2026
Make or change a still imageYes: the Help Center has a page on creating and editing images in ChatGPT
Show it my camera or screenLive camera and screen sharing in Voice are separate features with their own limits. They are for talking about what is shown, not for editing a file

Read on 15 November 2026 in OpenAI's Help Center: ChatGPT Image Inputs FAQ (the section on uploading videos), Uploading files and audio to ChatGPT, Data analysis with ChatGPT and What to know about the Sora discontinuation. We did not test what ChatGPT's code tool does with a video file, so this page claims nothing about it either way. If OpenAI's pages have changed since, they are the authority.

What ChatGPT is useful for in an edit

Before you film

A script, an opening line, three ways to say the same point shorter. This is writing, which is what a chat assistant is for.

From a transcript

Attach the transcript as a text file and ask for the strongest lines, with their times. OpenAI's page lists finding and extracting quotes from a document among the things ChatGPT does. You still make the cuts yourself.

When you post

A title, a description and hashtags for the finished video, rewritten for each platform.

The part that needs a tool: cutting and captioning the file

Burncaps is not a timeline editor. It does a fixed set of jobs on a talking video, in your browser, and gives you a finished MP4.

  1. Drop the video on the box at the top of this page, or tap it to choose a file on a phone. An MP4 or MOV works.
  2. Captions are burned in. It listens, writes every word as a script you can correct, and draws animated word-by-word captions into the picture, in one of 60 styles.
  3. Clean up takes out the ums. One press removes ums, repeats, false starts and long pauses from the whole video, on your device. Press it again for the video as recorded.
  4. A long recording becomes clips. From a podcast, talk or interview up to three hours long it finds the best moments and gives them back ranked, captioned and framed 9:16 on whoever is talking.
  5. Shape and privacy. Change a landscape video to Vertical 9:16, Square 1:1 or Portrait 4:5, and cover a name or a logo of your own with a blur box that stays where you put it.
  6. Press Export. The file is made on your device and saved to it.

What it does not do: join several files, lay tracks on a timeline, or follow a moving object with a blur. For those, use a timeline editor. AI video editors, sorted by job.

What it costs

Free: 2 videos every 30 days, each with captions and up to 10 clips, no watermark, no sign-up. Then try Pro free for 7 days, no card. Pro is $29 a month for unlimited clips and captions; Starter is $11.98 a month for 6 videos and up to 50 clips.

Questions, answered plainly

Can ChatGPT edit videos?

Not in the way a video editor does. OpenAI's help pages say ChatGPT accepts a video as an attachment and may use tools to analyse it, and that the analysis can be incomplete or inaccurate. We found no help page describing a feature that cuts, captions or exports a video (read 15 November 2026).

Can I upload a video to ChatGPT?

Yes. OpenAI's help page says ChatGPT can accept video files as attachments, including on Free plans, that availability varies by platform, upload method and account, and that a video counts toward your file-upload limit (read 15 November 2026).

Can ChatGPT watch a video and tell me what is in it?

It may use tools to analyse an uploaded video. OpenAI's help page says the analysis can be incomplete or inaccurate, and may not cover the whole video or accurately interpret its audio (read 15 November 2026).

Can ChatGPT make a video?

Sora was OpenAI's video generator. OpenAI's help page says its web and app experiences were discontinued on 26 April 2026 and its API on 24 September 2026.

Can ChatGPT add captions to a video?

No OpenAI help page we found describes it (read 15 November 2026). Burncaps does: drop the video and it burns animated word-by-word captions into it in your browser, free for 2 videos every 30 days with no watermark and no sign-up.

Can ChatGPT cut a long video into short clips?

No OpenAI help page we found describes it (read 15 November 2026). ChatGPT can read a transcript you attach and point to strong lines. Burncaps finds the best moments of a recording up to three hours long and gives them back as ranked, captioned 9:16 clips.

What can ChatGPT do to help me edit a video?

The writing round it: a script, the strongest lines of a transcript you attach as a text file, and a title, description and hashtags for the finished video. The cutting and captioning are done in a video tool.

Is Burncaps a full video editor?

No. It is not a timeline editor. It burns captions into a talking video, takes out ums and long pauses with one press, changes the shape, covers a spot with a blur box and cuts a long recording into captioned 9:16 clips. It does not join several files or lay tracks on a timeline.

Is my video uploaded when I use Burncaps?

No. Burncaps opens the video in your browser and never receives it. On a computer, the sound is heard on your own device unless you choose our speech service or the computer is too slow to listen well; on a phone it goes to our speech service unless you keep it on the phone (short pieces of sound, never the picture, to Microsoft's speech recognition in the EU, which by Microsoft's terms for the service stores none of it).

Burncaps facts, checked 15 November 2026

What it is: a browser tool that burns animated word-by-word captions into a talking video, or finds the best moments of a talk, podcast or interview and gives them back as ranked, captioned 9:16 clips.

Price: free for 2 videos every 30 days, each one recording with its captioned video and up to 10 clips, no watermark and no sign-up; then the free 7-day Pro trial, no card (your email only); then Pro, $29 a month, gives unlimited clips and captioned videos, or Starter, $11.98 a month, gives 6 videos every 30 days, each fully captioned, and up to 50 clips.

Privacy: the video never leaves your browser. The sound goes only to our speech service, on a phone unless you switch it off, on a computer if you choose it or if it is too slow to listen well. Because the video never reaches us, we cannot keep it or train AI on it, and we train no AI on anything you make.

Files: MP4 or MOV in, MP4 out. Captions on the whole video: up to ten minutes on Free, up to three hours on a paid plan, on a phone or a computer. On iPhones, a whole video over ten minutes has been tested in the iPhone simulator on a Mac (16 minutes at 1080p), not yet on a real iPhone. Clips: up to three hours, on a phone or a computer. SRT, VTT, ASS and text files are free without limit for recordings up to ten minutes; a longer recording, up to three hours, gives its script and those files (the first ten minutes free, all of it with one of your free videos, in the trial or on a paid plan).

Clips: about one clip for every two minutes of talk, up to 30, ranked, the ones we would post first circled, each showing the words it opens and ends on and the reason it was chosen; each cut to 9:16 with ums and dead air removed, an opening card and captions, framed on whoever is talking. Every clip of the whole recording is found and shown, free and with no sign-up; each free video exports up to 10 of them; Starter exports up to 50 clips every 30 days from its 6 videos, and the 7-day trial and Pro export every clip, unlimited.

Languages and styles: captions in the language spoken, twelve Indian languages heard on your device, translation into more than 60 languages, 60 caption styles.

After it listens: correct any word (one click changes it everywhere), add or cut words, one to six words at a time, position, size, text and highlight colours, and names this browser remembers, all free and without listening again.

Made by: Jordan Labs Ltd, UK company no. 17358646.

Against other tools: sixteen caption tools compared, from the vendors' own pages.