You can ask Claude for a video and actually get one back. Claude doesn't render video itself. What it can do is call a video generation service through a connector built on Model Context Protocol (MCP): it writes the prompt, picks the settings, starts the render and hands you the file. Connecting one takes a few minutes. The harder part is that every render costs money, and the thing deciding when to call it is a language model reading your chat.
This guide covers how it works, the three things a connector should do before it spends anything, setup in Claude and ChatGPT, and where ClipSpeed stands: our generation connector, ClipSpeed Create, is in early access, and our clipping connector is live. Model prices are published API rates as of October 2026.
ClipSpeedAI's clipping connector works in Claude today. Give it a video or live-stream link and get back vertical clips with burned-in captions and a viral score on each one.
Try ClipSpeedAI →The language model never draws a frame. It picks a tool the connector offers, fills in the inputs and waits while another service renders. If MCP is new to you, our plain-English MCP explainer covers the basics. For video generation, the loop usually runs like this:
Step 2 is where the assistant helps most, expanding a one-line idea into camera movement, lighting and sound cues. It's also where mistakes start: it picks a wrong duration or aspect ratio as confidently as the right one.
A note for ChatGPT users: OpenAI's own video model, Sora 2, has been discontinued. The Sora app went offline on April 26, 2026, and the API followed on September 24, 2026 (NBC News, API shutdown report). From inside ChatGPT, video now means a connector to another service.
Most video model APIs price by the second, so costs build quickly. On fal, Seedance 2.5 costs about $0.22 per second at 480p, $0.473 per second at 720p and $1.164 per second at 1080p (fal pricing). On the Gemini API, Veo 3.1 Standard is $0.40 per second at 720p or 1080p, audio included (Google pricing). By our math, one 10-second Seedance 2.5 clip at 720p on fal comes to about $4.73, before any retries. Our AI video cost breakdown covers the other major models.
Put an assistant in charge of calling that service and three things can go wrong:
MCP clients can ask you to confirm before a tool runs, which helps. But it's easy to click "always allow" by the third prompt, and a confirmation inside the chat is still part of the chat. If the assistant can type "the user approved" and the tool believes it, your safeguard is only as reliable as the model. Our MCP security notes go deeper on this.
Before you connect anything that can spend money, check for three things.
The first call should return a price, not a render: a maximum price for the exact settings (model, mode, duration, resolution, audio), with no provider work started and no money held. That's your chance to catch the 15-seconds-instead-of-5 mistake before it costs anything. If a connector's only tool is "generate", you see the price for the first time on your bill.
This is the check that matters most. Approval should happen outside the conversation, on a page where you're signed in to your own account, for that one quote. The assistant can hand you the link, but it can't click it for you, and nothing typed in the chat counts as consent. Then it doesn't matter whether the assistant misread you, got stuck in a loop or picked up an injected instruction. Nothing renders until a signed-in person says yes.
You want the video file itself, not a preview that only plays in someone else's viewer. Download links are often time-limited, so save the file to your own storage as soon as it's ready. Inputs matter too: a connector that only accepts references you've uploaded to your own account is safer than one that fetches any URL the assistant pastes in.
The full checklist we'd run on any connector:
| Check | Why it matters | What to ask |
|---|---|---|
| Quote first | Catches a wrong duration or resolution before money moves | Does the first call return a price without starting a render? |
| Approval outside the chat | The model, a loop or an injected instruction can't approve spending | Where is approval given, and can the AI give it? |
| Safe retries | A dropped connection shouldn't mean a second charge | Does the generate call take a request key so a repeat is recognized? |
| Refunds on failure | Renders do fail, and you shouldn't pay for those | Are failed generations refunded, and in full? |
| Revocable sign-in | You can cut off access without changing your password | Is it OAuth or an API key you can revoke? |
| Downloadable output | The video ends up in your storage, not only theirs | Do you get the video file, and how long is the link valid? |
A connector is a server URL plus a sign-in. Apps differ in where you paste the URL, not in how the connector behaves.
On claude.ai, open Settings, go to Connectors, choose Add custom connector, paste the server URL and approve the sign-in prompt. If the option is missing, your Claude plan may not include custom connectors. In Claude Code, one command adds a connector with an API key:
claude mcp add --transport http clipspeed-create https://api.clipspeed.ai/mcp/create --header "Authorization: Bearer <API_KEY>"ClipSpeed Create only shows its generation tools on accounts with early access. Use https://api.clipspeed.ai/mcp instead to add the clipping connector. Claude is the client we've verified end to end with the clipping connector, and our ClipSpeedAI MCP guide walks through it step by step. Setup for Claude Desktop, Cursor, Windsurf and other clients is on our connect page.
Whether your ChatGPT account can add a custom MCP connector by URL is controlled by OpenAI, and the option isn't present in every account. What you need is a setting that accepts a server URL; picking from a catalog of approved apps isn't the same thing. On our side, the connector uses the same standard MCP OAuth sign-in for ChatGPT as for Claude, but we haven't verified the ChatGPT flow end to end, so we list it as rolling out.
The guardrails above don't depend on the client: if the quote and approval live on the service's side, they work whichever assistant is asking.
Here's the flow in ClipSpeed Create for a product b-roll shot. Tool names are the server's current ones and may change during early access.
quote_ai_video returns a maximum price and an approval link. No provider work starts and no credit is reserved.generate_ai_video only runs for an approved quote. Until the quote is approved, it returns the approval link instead of spending. The assistant also sends its own request key, so retrying with the same key can't start a second render.get_ai_generation reports status and, once the render is done, a short-lived download link. Save the file straight away.If a generation fails, the credits are refunded in full. Image-to-video and reference-to-video follow the same steps, except that references must be files you've uploaded to your ClipSpeed account, not arbitrary URLs.
ClipSpeed Create is in early access: only accounts given access see its tools. It brings generation from ClipSpeed's AI Creator workspace into the chat. Every generation is quoted up front as a maximum price, paid from ClipSpeed creation credits, and runs only after the account owner approves it. Its list_ai_generator_models tool shows which models your account can quote from chat.
AI Creator itself puts eight models side by side in one workspace: Seedance 2.5, Kling 3.0 Turbo, MiniMax H3 Max, Veo 3.1 and Gemini Omni 1.1 Flash for video, plus Nano Banana Pro, GPT Image 2.5 Flare and GPT Image 2.5 Sunburst for images.
Pick the model that fits the job. Seedance 2.5 makes 4 to 30 seconds in one pass (ByteDance Seed), good for ads and multi-shot stories. Veo 3.1 can output up to 4K and native 9:16 for hero shots (Google). Kling 3.0 Turbo is fast and cheap for talking-head variants, Gemini Omni 1.1 Flash edits clips from instructions, and Nano Banana Pro makes thumbnails and start frames with legible text. Our Seedance 2.5 guide goes deeper.
| Clipping connector | ClipSpeed Create | |
|---|---|---|
| Server | https://api.clipspeed.ai/mcp | https://api.clipspeed.ai/mcp/create |
| Status | Live, verified in Claude | Early access, enabled per account |
| What it does | Finds the best moments in your videos and live streams, cuts vertical or landscape clips, burns in captions, scores each clip | Brings AI Creator generation into the chat |
| Spending | Uses your ClipSpeed clipping plan | Each generation quoted, then approved by the account owner on a signed-in page |
| Example skills | /podcast-to-shorts, /livestream-to-shorts, /post-ready-pack, /caption-style-match | /ugc-product-review, /product-broll, /hook-variants, /faceless-hand-drawn |
Skills are ready-made workflows; the full list is on the MCP page.
Assistants write good video prompts, but they fill gaps with guesses. A few habits keep those guesses off your bill:
Generation is for shots you can't film: a product on a set you don't have, a three-second hook, an illustrated explainer for a faceless channel. Clipping is for footage you already have. If you record podcasts, streams or tutorials, the clipping connector turns them into captioned vertical shorts. The two fit together: clip the long recording, then generate the opener or b-roll the footage is missing. Our generation vs clipping comparison goes further.
Video from Claude or ChatGPT comes through an MCP connector: the assistant writes the prompt and runs the steps, and a separate service renders. Setup is easy; spending is what needs care. Judge any connector on three things: a quote before anything is spent, an approval the AI can't give for you, and a file you download and keep.
ClipSpeed Create is built that way. It's still in early access, but you can use AI Creator's eight models on the web at /app. The clipping connector on our MCP page is live in Claude today, and the quickest way to try it is on your own footage.
Can Claude or ChatGPT generate video on their own?
Claude doesn't render video. It writes prompts and calls tools, so the video comes from a service connected through MCP. OpenAI has discontinued Sora 2: the app went offline on April 26, 2026 and the API on September 24, 2026. If you want video from inside ChatGPT, a connector to another service is the route.
What is an MCP connector for AI video?
It's a server that tells your assistant which video tools it can call, such as getting a price, starting a generation, checking status and fetching the file. You add it once by URL, sign in, and then ask for video in plain language. Our MCP explainer covers how the protocol works.
How do I stop an AI assistant from spending credits without asking?
Use a connector that quotes every generation first and requires approval outside the chat, on a page where you are signed in. Don't rely on a yes typed in the chat, which the model can produce itself, or on a client that is set to "always allow" the tool. ClipSpeed Create only runs a generation after the account owner approves the quote on a signed-in ClipSpeed page.
Does ClipSpeed work in ChatGPT?
Our connector uses the same standard MCP OAuth sign-in for ChatGPT as for Claude, but we haven't verified the ChatGPT flow end to end, so we list it as rolling out. Whether your ChatGPT account can add a custom connector by URL is controlled by OpenAI, and the option isn't in every account. Claude is the client we've verified with the clipping connector.
Can anyone use ClipSpeed Create?
Not yet. ClipSpeed Create (https://api.clipspeed.ai/mcp/create) is in early access and its generation tools only appear on accounts that have been given access. It brings generation from ClipSpeed's AI Creator into the chat, with every generation quoted first and approved by the account owner on a signed-in ClipSpeed page. AI Creator on the web has eight models: Seedance 2.5, Kling 3.0 Turbo, MiniMax H3 Max, Veo 3.1 and Gemini Omni 1.1 Flash for video, plus Nano Banana Pro, GPT Image 2.5 Flare and GPT Image 2.5 Sunburst for images. The clipping connector at /mcp is live now.
Who owns a video I generate through a connector?
That depends on the terms of the service and the model provider. In the US, the Copyright Office says purely AI-generated material isn't copyrightable, while human-authored elements and arrangement can be. Our commercial use guide covers the rest. This is not legal advice; check current terms before commercial use.
Published by ClipSpeedAI · AI video generation and AI clipping in one place — create with Seedance, Veo, Kling and Nano Banana, then cut it into captioned shorts.