Turn rough footage into finished video.
Point your agent at the footage. It writes the edit. CueFrame renders it — the same way, every time.
npx -y cueframe installDetects the agents on your machine and wires CueFrame into each. No API key — your agent opens a browser to authorize on first call.
On Claude Code you can instead paste its skill. On ChatGPT, add api.cueframe.ai/v1/mcp as a connector. Building a pipeline? It's three REST calls.
$20.00 to start, no card. Your agent signs in from the browser, so there are no keys to paste.
No footage. Just a brief.
Every frame is a real render. Every shot came from licensed stock. Click a card to read the prompt behind it.
Change one line, not the whole video.
The edit is plain data. Read it, version it, change one line. A change costs a re-render, not a re-edit. Run it again untouched and the same video comes back. That's the point.
A new shape for a new platform. Same footage, same type, same timing — nothing was re-cut.
The recipe changed, so the number did. The shot behind it never moved.
Checking an edit is free. Previews cost pennies. You pay when you render, and a short costs $0.50. Next week's episode reuses the same edit, so you never start over. And it exports to Premiere or Final Cut whenever you want.
Ask for the video you want.
“▍”
Upload
Point CueFrame at your footage, a file or a URL. It transcribes the audio and finds the speakers for you.
Compose
Your agent writes the edit as data: which clips, where the captions sit, your brand.
Render
One call turns it into finished video. Any aspect ratio, up to 4K.
Building a pipeline instead? The same three steps are three REST calls — get an API key or read the setup guide.
- The camera follows whoever's talking — a moving frame, not a static crop.
- Text and captions behind the speaker — composited from the footage, no masking.
- Every aspect ratio from one edit — never re-edited per platform.
Any video up to a minute renders for $0.50.
Rendering bills by the output minute, rounded up. A three-minute cut is $1.50. 4K counts double, 720p half. Transcription costs pennies. No subscription and no seats — just prepaid credits that don't expire, and you start with $20.00 free, no card.
Questions, answered.
Do I need to know video editing?
No. You describe the video you want; your agent writes the edit and CueFrame does the editor's work — framing, captions, pacing, brand. If you can review a draft, you can ship video.
What do I upload?
Real footage: a talk, a podcast recording, a product walkthrough, a founder update. A file or a URL. CueFrame transcribes it and finds the speakers so the edit can follow them.
Which AI tools does this work with?
Run npx -y cueframe install and it wires CueFrame into every agent it finds on your machine — Claude Code, Cursor, Codex, VS Code, Windsurf, Zed, Gemini CLI, Copilot CLI and more. Claude Desktop and ChatGPT can't be wired from the command line (neither reads a local MCP config), so add api.cueframe.ai/v1/mcp as a custom connector instead. There's a plain REST API too.
What does a video cost?
Rendering bills by output minute, rounded up to the next whole minute: anything up to a minute costs $0.50, a three-minute cut $1.50. 4K counts double, 720p half. Transcription is pennies per minute, and you start with $20.00 in free credits — no card.
Will the same edit always produce the same video?
Yes. The edit is data, and rendering it is repeatable — pin the edit and you get the same video back. Writing the edit is the creative part, so an agent may draft it differently run to run; but once it's written, nothing re-rolls. Change one line and only that one thing changes.
Can I open the edit in Premiere or Final Cut?
Yes — export the timeline any time and finish by hand. No lock-in.