> For the complete documentation index, see [llms.txt](https://docs.voicemoat.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.voicemoat.com/creating-content/media-studio.md).

# Media Studio

**In short:** Media Studio turns a post into a visual. It is one page with three modes: **Template** for designed cards and carousels, **Meme**, and **Image generation**, where the whole graphic is drawn for you. Creating media is on every paid plan.

Open it from the sidebar, or reach it from Studio's **Generate visuals** and **Make a meme** buttons. Switch modes at the top of the page.

#### Start from a post or a brief

Every mode lets you start from either:

* **a post** you have already written, so the visual carries the same idea, or
* **a one-line brief** describing what you want.

#### Template: designed cards and carousels

Clean designed graphics where VoiceMoat sets the type, so the words are always spelled right.

* **One card**, or a **2 to 4 slide carousel**.
* Quote, stat, list, and cover layouts.
* A curated **theme** and a **size** for where it will be posted.
* A background from your own upload or a stock photo.
* Iterate with quick chips, and download the card as a **PNG** or the carousel as a **PDF**.

Restyling or editing text re-renders for free.

#### Meme

Pick from a large, always-current set of meme templates, and audenAI writes the caption from your post or brief, in your voice.

* Re-caption as many times as you like, for free.
* **Refine** a meme ("make it punchier") for 1 credit rather than paying for a fresh one.

#### Image generation

The whole graphic is drawn for you, words included, from your post or a one-line brief.

* Choose one image or three to pick from, and a size.
* Steer the design with a **reference image** of your own. Only upload images you have the rights to use.
* **Refine** a result for 1 credit rather than paying for a fresh draw.
* It takes around 40 seconds, and shows its progress while it works.

{% hint style="info" %}
A generated image is one flat picture with the words baked in, so there is no caption editor. To change a word, refine it.
{% endhint %}

#### What it costs

| Action                               | Credits           |
| ------------------------------------ | ----------------- |
| Meme or designed visual              | 3 (5 for a batch) |
| Refine a meme or a visual            | 1                 |
| Image generation                     | 15 (40 for three) |
| Refine a generated image             | 1                 |
| Editing text or restyling a template | free              |

If a generation fails, the credits are refunded.

#### Visuals from audenAI chat

audenAI can also make a visual straight from a post in chat: memes, designed cards, or generated images. It shows a confirm card with the price before it spends anything, and **Use this** attaches the result to your post. See Ask audenAI.

#### Who can use it

Creating media (all three modes) is available on **every paid plan**: Creator, Pro, Enterprise, and the trial. Free plans cannot. Finished visuals save to the **Media** tab of your Library automatically.

{% hint style="warning" %}
Creator can **create** media but **cannot post** media to a live post. Posting images or a PDF carousel needs Pro or above, on Twitter and on LinkedIn (threads, which are Twitter only, also need Pro or above). So a Creator user might make a graphic and then post it manually, or upgrade to post it through VoiceMoat. See Scheduling.
{% endhint %}

On Enterprise, Growth Autopilot can also attach a visual to the posts it drafts.

#### How carousels differ by platform

* On **Twitter**, a carousel is posted as a set of images (up to 4).
* On **LinkedIn**, a carousel becomes a swipeable **PDF document** post, which is how LinkedIn handles multi-slide content. LinkedIn posts take JPEG or PNG images, or one PDF document. Video and GIFs are not supported on LinkedIn.

#### Common questions

**Are the images AI-generated?** In **Image generation** mode, yes: the whole picture, text included, is drawn for you. **Template** and **Meme** are not: Template typesets your words on a designed layout, and Meme captions a real meme template.

**Which mode should I use?** Template when the words must be exact and on-brand, Meme when you want humour, Image generation when you want an illustration or scene.

**Where do finished visuals go?** They auto-save to the Media tab of your Library, so you can reuse them.