# Generate Text, Images, Audio, & Videos

{% embed url="<https://youtu.be/1dWhGlHRQRQ>" %}

This guide walks through the process of generating four types of AI content in a single MindStudio agent:

1. Text
2. Image
3. Audio
4. Video

You’ll also learn how to structure your prompts, connect blocks, and display all content together using a unified layout.

## Content Types Supported in MindStudio

MindStudio supports generation of:

* **Text**: Articles, emails, scripts, summaries, and more.
* **Image**: AI-generated visuals from prompts.
* **Audio**: Text-to-speech conversion using voice models.
* **Video**: Short clips based on prompt descriptions.

Each content type has its own dedicated block, model settings, and display method.

## Building the Full Content Generator

We’ll create an agent that takes a **single topic** input and produces:

* A long-form article
* A relevant cover image
* Audio narration of the article
* A related short video

### Step 1: Collect User Input

* Add a **User Input** block.
* Use **Long Text**.
* Variable name: `topic`
* Label: “What would you like your long-form article to be about?”

### Step 2: Generate the Article

* Add a **Generate Text** block.
* Prompt:

  ```
  Write a long-form article about the following topic:
  <topic>{{ topic }}</topic>

  Make sure to use markdown formatting.

  <example>
  # Title  
  A compelling hook for the article.  
  ## Section Header  
  Multiple paragraphs about the section.  
  - Key takeaway 1  
  - Key takeaway 2  
  ## Conclusion  
  </example>
  ```
* Save the output to variable: `text`

### Step 3: Generate an Image Description

* Add another **Generate Text** block.
* Prompt:

  ```
  Based on the following content, write a simple image prompt for an AI image model:
  <content>{{ text }}</content>
  ```
* Save to variable: `image_description`

### Step 4: Generate the Image

* Add a **Generate Image** block.
* Use `{{ image_description }}` as the image prompt.
* Output variable: `image`
* Use your preferred model (e.g., Ideogram V2)
* Optional: Set aspect ratio (e.g., `16:10`)

### Step 5: Generate Audio from Text

* Add a **Text to Speech** block.
* Input: `{{ text }}`
* Output variable: `audio`
* Choose a model and voice (e.g., ElevenLabs → Callum, Turbo 2.5)

### Step 6: Generate a Video Prompt

* Add another **Generate Text** block.
* Prompt:

  ```
  Based on the following content, write a simple video prompt for an AI video model:
  <content>{{ text }}</content>
  ```
* Save to variable: `video_description`

### Step 7: Generate the Video

* Add a **Generate Video** block.
* Use `{{ video_description }}` as the prompt.
* Output variable: `video`
* Select a video model (e.g., Ray 2)

## Step 8: Display the Final Output

Add a **Display Content** block and use the following syntax:

```markdown
![Cover Image]({{ image }})

<audio controls>
  <source src="{{ audio }}" type="audio/mpeg">
</audio>

{{ text }}

<video controls>
  <source src="{{ video }}" type="video/mp4">
</video>
```

Alternatively, copy snippets from **QuickHelp** in the editor for image, audio, and video.

## Final Output

When previewed:

* The agent will collect a topic.
* AI will generate a markdown-formatted article.
* An image, audio narration, and video will be produced from the article.
* All outputs are combined into a clean, unified display.

## Summary

To generate rich AI media in MindStudio:

1. Use content-specific generation blocks.
2. Structure prompts clearly and use variables throughout.
3. Save outputs to variables.
4. Use the **Display Content** block with proper syntax to render media.

This pattern allows for powerful, engaging AI experiences from just a single input. Experiment with other media types, models, and formatting to further customize your AI agents.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://university.mindstudio.ai/1-core-building-principles/generate-text-images-audio-and-videos.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.