You stay the director
The Editor Assistant proposes and you decide. Every edit it makes is visible, explained and undoable in one click.
Vibe editing
The AI Video Editor You Direct by Chat
GPT-Video is an AI video editor that you direct by chat. Upload a video, then type the edit you want to the Editor Assistant, such as a cut or bigger captions, and it applies the change to the clip on screen. Every change can be undone. Assistants that support MCP, such as Claude and ChatGPT, can connect to it through the GPT-Video MCP server.
ChatGPT made writing conversational. Vibe editing does the same for video: describe the edit in plain language, and GPT-Video plans it, applies it through a real editing pipeline and lets you undo any step. You direct, it executes.
GPT-Video
Cut this podcast into 10 vertical clips with captions
Split-screen this with gameplayTurn this story into a fake chatCaption it in my brand styleFind the 3 most viral moments
cut for you
captions on
reframed 9:16
ready to post
The pipeline
From raw video to finished clip
Six steps run behind every request. Each one is a separate stage that you can inspect.
Import Step 1
Drop in a file — a podcast episode, an interview, last night's stream VOD. No project setup, no timeline: the source video is the only thing you bring.
Transcription Step 2
Every word is transcribed with speech recognition and timestamped. From here on, the whole recording is searchable text, for you and for the Editor Assistant.
Clip selection Step 3
The engine scores candidate segments for hooks, payoffs and self-contained stories, and shows its reasoning. Every suggestion explains why it scored, so you can judge it with context.
Auto reframe Step 4
Face detection tracks the people on camera, and the vertical crop follows them. Widescreen footage becomes 9:16 without keyframing a single move.
Animated captions Step 5
Word-by-word captions are generated from the transcript and rendered into the video, appearing in sync with the audio.
Export Step 6
Each clip renders as a finished vertical 9:16 MP4 with captions burned in, ready for you to post on TikTok, Reels and Shorts. Want a change first? Say it in chat and it is applied, and you can undo it.
Why it works
Why vibe editing
Less busywork
Describe the edit once instead of doing it step by step. Scrubbing, cropping and captioning become a review pass.
No black boxes
Clip suggestions come with their reasons and every change is a named, reversible step. You always know what happened to your video and why.
ChatGPT and Claude
Can ChatGPT or Claude edit video?
As of October 2026, OpenAI's help pages say ChatGPT accepts video files as attachments and may use tools to analyze them, and that the analysis can be incomplete or inaccurate. They do not describe cutting a video or exporting an edited file.
As of October 2026, Claude's upload page lists documents and images, and video is not on the list. Claude can connect to outside tools through a remote MCP connector.
A chat on its own gives you text back. To get a video back, the assistant needs an editor to do the work. GPT-Video offers an MCP server for this: an assistant can find clips and export them as MP4 files, and the full edition also reaches the Editor Assistant. You upload the video file, tools that spend credits ask you first, and the rendering runs on GPT-Video.
FAQ
How do I edit a video with AI by typing a prompt?
Upload your video file to GPT-Video, then type the change you want in the chat with the Editor Assistant, for example a cut or bigger captions. The assistant applies it to the clip on screen, you review it, and you can undo any change. When you are happy, you export the clip as an MP4 file.
What is vibe editing?
Vibe editing means editing by describing what you want in plain words instead of working a timeline. You ask for a change, the tool plans the steps and applies them, and every change can be undone. In GPT-Video you do it in a chat with the Editor Assistant.
Can ChatGPT edit videos?
Not on its own, as far as OpenAI's help pages show. As of October 2026 they describe ChatGPT analyzing video attachments, and say the analysis can be incomplete. ChatGPT can direct a connected editor such as GPT-Video through MCP, where OpenAI allows custom MCP servers for your plan.
Can Claude edit videos?
Not on its own, as far as Anthropic's help pages show. As of October 2026, Claude's upload page lists documents and images, not video. Claude can connect to an editor through a remote MCP connector, and GPT-Video offers one.
Can I edit video with ChatGPT or Claude using GPT-Video?
Yes, through the GPT-Video MCP server. Add its address to the assistant, then ask for the edit in chat. The assistant can find clips and export them as MP4 files, and tools that spend credits ask you first. ChatGPT's own plan rules decide whether you can add a custom server. The MCP page has the setup for each assistant.
Do I keep control of the edit?
Yes. The Editor Assistant never publishes or overwrites anything on its own: it proposes clips with the reasoning behind each one, applies the changes you ask for, and every step can be undone in one click.
How much editing time does it save?
The slowest parts of short-form editing, such as finding moments in hours of footage, reframing and captioning, run automatically. Your time goes to judgment calls: pick the clips, tweak what matters, then post the exported files yourself.
What about output quality?
Clips go through a video rendering pipeline: face-tracked vertical reframing, word-by-word animated captions and encoded MP4 exports. You direct the edit in chat, and the pipeline renders it.
What formats does it export?
Vertical 9:16 MP4 with captions rendered in, the native format for TikTok, Instagram Reels and YouTube Shorts. Fake text and split screen videos render the same way.
Direct your first edit
Create an account and try it on your own footage.
Plans from $19 a month. Cancel any day, keep the month.