All clients
Browser sign-in, no key

Make videos in ChatGPT

Connect Idea to Motion to ChatGPT and you can ask for a video the same way you ask for anything else. ChatGPT writes the script, plans each scene and writes the animation code; we synthesize the voiceover, time it to the words, render the animation and hand back an MP4. ChatGPT adds it through Developer mode as a custom connector and signs in over OAuth, so the only thing you copy is the server URL.

  1. 1In ChatGPT on the web, open Settings → Apps & Connectors → Advanced settings and turn on Developer mode.
  2. 2Back in Apps & Connectors, click Create. Name it, paste the URL below, choose OAuth, tick “I trust this application” and click Create.
  3. 3Sign in with your account and approve access.
  4. 4In a new chat, open the + menu → Developer mode and switch the connector on, then ask for a video.

01Connect ChatGPT

Generate a connection key if this client needs one, then add the server.

Pick your app

Chat apps

Editors & IDEs

Terminal

Set up ChatGPT

Connects with a browser sign-in — no key needed.

Docs
  1. 1. In ChatGPT on the web, open Settings → Apps & Connectors → Advanced settings and turn on Developer mode.
  2. 2. Back in Apps & Connectors, click Create. Name it, paste the URL below, choose OAuth, tick “I trust this application” and click Create.
  3. 3. Sign in with your account and approve access.
  4. 4. In a new chat, open the + menu → Developer mode and switch the connector on, then ask for a video.
https://api.ideatomotion.com/mcp

No key needed — ChatGPT signs in through your browser.

  • Developer mode is on ChatGPT Plus, Pro, Business, Enterprise and Edu, on the web.
  • ChatGPT signs in through your browser and keeps the connection — there is nothing to paste but the URL.

Where the connection lives

The exact names ChatGPT reads, and what happens when one of them is wrong.

There is no file to edit. ChatGPT stores the connector against your account and runs the OAuth exchange itself, so the same connection follows you to every device you sign in on.

Stored in
Your ChatGPT account, not a file
Format
None — you paste the server URL
Your key
Not needed; you sign in and approve in the browser
Staying connected
Access tokens last an hour and the connector renews them on its own

02Connect your voice

Narration is synthesized on your own ElevenLabs, Cartesia or Sarvam AI key. Silent motion graphics need none.

Your voice key

Idea to Motion generates the voiceover on your own text-to-speech account. Add an ElevenLabs, Cartesia or Sarvam AI key — it's stored encrypted and never shown again. Rendering is blocked until a key is connected.

Loading…

What ChatGPT can actually do

Where the line between your assistant and the platform falls, and why it falls there.

Ask for a video in a ChatGPT conversation the same way you ask for anything else — the tool calls run inline and you approve the plan right there in the chat.

  • It writes the content — a narrated script, a silent shot list, or a keep-and-drop cut plan for a video you upload — and hands it back for approval. Nothing is produced until you say yes.
  • It directs every scene, then writes a self-contained Remotion component for each one. Submitted code is validated and run in a sandbox before it is accepted, so a mistake comes back as a tool error it can fix rather than a broken video.
  • It renders stills of its own scenes on our servers and looks at them, which is why it can correct a card sitting across someone's face without you screenshotting anything.
  • We do the parts a language model should not be doing: voice synthesis, word-level timing, captions, music, assembly and the final render.
  • There is deliberately no export tool. Exporting spends money and picks a quality tier, so it stays a click you make on the platform — and a video you have already paid for re-exports for free.
All 31 MCP tools

A worked example

Type it into a normal conversation once the connector is enabled.

“Make a 40-second vertical explainer of how compound interest works, for a finance Reel.”

What comes back

  1. 1It opens a picker: the looks play as short clips, the narrator voices have samples you can hear, and you choose. Clients that cannot draw a panel get the same list as text.
  2. 2It writes the script and shows it to you. Tell it what to change and it rewrites — the video does not start until you approve.
  3. 3It directs and writes each scene, checking stills as it goes. This is the long part, and it is mostly quiet: a scene submission legitimately holds its request open while the server renders.
  4. 4The finished video appears in your projects here. Watch it, ask for adjustments in the same conversation, then export it from the platform.

Troubleshooting ChatGPT

The ways this goes wrong, and most of them go wrong silently.

There is no Create button in Apps & Connectors

Custom connectors that can take actions live behind Developer mode, and the switch only exists on Plus, Pro, Business, Enterprise and Edu plans in ChatGPT on the web — the mobile and desktop apps do not show it, and a free plan never will. On a Business or Enterprise workspace an admin may also have to allow custom connectors before the option appears for you.

The connector is created but ChatGPT never calls it

Creating it is not the same as using it. In each new conversation open the + menu, choose Developer mode and switch the connector on; a chat started without that is an ordinary chat and will happily describe a video instead of making one. Asking for a video by name of the product also helps ChatGPT reach for the tools rather than answering from memory.

Sign-in opens and then returns to ChatGPT with an error

The approval page needs a live Idea to Motion session in the same browser. Sign in on this site first, then create the connector again — ChatGPT re-registers itself on every attempt, so a failed one leaves nothing behind to clean up. Pop-up blockers and private windows are the usual reason the sign-in tab never reaches the approval screen.

ChatGPT asks you to confirm every single step

Developer mode treats every action as a write and asks before each one, and a video is a few dozen of them. Approving with the option to remember the choice for this conversation keeps it moving; nothing is posted or charged on your behalf at any step — exporting and publishing only happen when you ask for them.

The tools work but it cannot produce the voiceover

Narration and transcription run on your own ElevenLabs, Cartesia or Sarvam AI key rather than ours, so a narrated or recorded video needs one connected — step 2 on this page, or the set_voice_key tool from inside ChatGPT. Silent motion graphics need no voice key at all, so "make it a silent motion graphic instead" is a valid way past this.