> For the complete documentation index, see [llms.txt](https://docs.arcade.software/kb/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.arcade.software/kb/ai-video/ai-video/sharing-and-exporting.md).

# Sharing & Exporting

## Publishing your video

### How do I publish, share, or export my video?

Click Publish to render and publish your video. Publishing exports the video as an MP4 (1080p at 30fps by default). Once published, the button becomes Share and you can copy a shareable link — the link isn't available until the video has been published.

### Is the preview the same quality as the export?

No. The shared preview link is a lower-quality version for quick review. The published MP4 is the high-resolution version.

### Can I get back to an earlier version?

Yes. Your exports are kept as a history, so you can revisit or re-download a previous version rather than losing earlier work.

### Can Claude or another AI tool review my exported AI video?

Not through Arcade's MCP connector — its video tools (`create_video`, `preview_video`) are for generating new videos, not analyzing existing ones.

If you share the video file or its link directly with an AI assistant that has browsing or file-viewing capability, it can typically sample individual frames (for example by seeking the video to specific timestamps) to review the visuals. Most AI tools can't yet "watch" a video continuously the way a person can, so a full review of pacing, voiceover, and audio generally requires a text transcript or captions file alongside the video.

{% hint style="info" %}
For the most reliable AI review of a video's narration, include a transcript or captions file — this gives the AI tool something it can actually read, rather than relying only on sampled frames.
{% endhint %}

## Managing your videos

### Where do my generated videos live?

In your Arcade library, alongside your other content.

### Can I organize my videos into folders?

Yes, with Projects. Create a Project from the Projects tab, then move any video into it — from the video's own `...` menu, choose `Move to...` and pick the Project. Use Projects to group videos by team, client, or campaign.

### Can I duplicate a video?

Yes. Open the video's `...` menu (next to its title in the editor, or from its card in your library) and choose `Duplicate` — useful for trying a different direction without losing the original.

### How do I delete a video I've generated?

Open the `Videos` tab from the sidebar — this is your library of generated videos, separate from the Media Library panel inside the Arcade editor. Find the video, open its `…` menu, and select `Delete`.

{% hint style="info" %}
You can't delete a generated video from the Media Library panel's Videos tab — that panel only lets you favorite it or add it as a step. Deleting the video itself happens from the `Videos` dashboard, as described above.
{% endhint %}

### Why is there a "Made with Arcade" watermark on my video?

The watermark in the bottom-right corner is applied automatically on the free plan. On paid accounts it's removed automatically.

### How do I share feedback or request changes?

Rate any generation with thumbs up or down. If you rate it thumbs-down, Arcade asks what could be better and can take another pass to improve the video based on your feedback. You can also reach out on our support channel.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.arcade.software/kb/ai-video/ai-video/sharing-and-exporting.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
