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

# Image & Media

Crew includes a comprehensive suite of image and media tools — generate images, analyze photos, process audio, create QR codes, and more.

## Image Generation

Create images from text descriptions:

> "Generate a minimalist logo for a coffee shop called 'Morning Brew' — warm colors, clean design."

> "Create an illustration of a futuristic city skyline at sunset."

> "Design a social media banner for a tech conference — blue theme, 16:9 ratio."

### Options

* **Aspect ratios**: 1:1 (square), 16:9 (widescreen), 9:16 (portrait/stories), 4:3, 3:4
* **Transparent background**: For logos, icons, and stickers
* **Image editing**: Provide an existing image and describe the changes

### Image Editing

> "Take this logo and change the color scheme to blue and white."

> "Edit this photo — remove the background and make it transparent."

> "Add a holiday-themed border to this image."

## Image Analysis

Upload an image and ask Crew to analyze it:

> \[Upload photo] "What's in this image?"

> \[Upload screenshot] "Read the text in this screenshot."

> \[Upload chart] "Explain what this chart shows."

> \[Upload product photo] "Write a product description based on this photo."

### Supported Formats

JPEG, PNG, GIF, WebP (up to 20MB)

## OCR (Text Extraction)

Extract text from images and scanned documents:

> \[Upload business card photo] "Read all the contact information from this business card."

> \[Upload receipt] "Extract the items and total from this receipt."

> \[Upload scanned PDF] "Convert this scanned document to text."

Works with multiple languages and supports both images and scanned PDFs.

## ImageMagick (Image Processing)

Professional-grade image processing:

> "Resize this image to 800x600 pixels."

> "Convert this PNG to JPEG."

> "Add a watermark to this photo."

> "Remove the background from this product image."

### Available Operations

* Resize and crop
* Format conversion (PNG, JPEG, WebP, etc.)
* Watermarking
* Filters and effects
* Background removal

## QR Code

### Generate QR Codes

> "Create a QR code for our website: <https://example.com>"

> "Generate a QR code for this WiFi network: SSID 'Office-5G', password 'welcome123'."

### Read QR Codes

> \[Upload QR code image] "What does this QR code contain?"

## Text-to-Speech

Convert text to natural-sounding audio:

> "Read this paragraph aloud and send me the audio file."

> "Convert this meeting summary to speech in Spanish."

> "Create an audio version of these instructions in French."

### Features

* **30+ languages** supported
* **Male and female** voice options
* **Automatic language detection** — or specify the language
* **Output formats**: MP3, Opus
* Up to 5,000 characters per conversion

## Speech-to-Text

Transcribe audio files to text:

> \[Upload audio file] "Transcribe this recording."

> "Convert this voice memo to text."

### Supported Formats

MP3, MP4, M4A, WAV, OGG, WebM, FLAC

### Use Cases

> "Transcribe this meeting recording and create a summary with action items."

> "Convert this podcast episode to text and extract the key points."

## YouTube Summary

Summarize YouTube videos without watching them:

> "Summarize this video: \[YouTube URL]"

> "What are the key takeaways from this lecture? \[YouTube URL]"

Returns: Title, channel, duration, view count, tags, and full transcript summary.

## Social Media Analysis

Analyze posts from social platforms:

> "Analyze this TikTok: \[URL] — what's the content about?"

> "What's this Instagram post about? \[URL]"

**Supported platforms**: TikTok, Instagram, Twitter/X, Facebook

Returns: Author, engagement metrics (likes, comments, shares), caption, hashtags, and optional transcript.

## Practical Scenarios

### Content Creation Pipeline

> "Generate a product photo concept, create a social media caption, and design a matching banner image for our new product launch."

### Document Digitization

> "I have photos of 5 handwritten pages. Extract all the text using OCR and compile it into a clean DOCX document."

### Audio Content

> "Transcribe this 30-minute interview recording, create a summary, and generate a professional PDF report."

### QR Code for Events

> "Create a QR code that links to our event registration page, and generate a poster image that includes the QR code."

## Tips

* **Be descriptive for image generation**: Include style, colors, mood, and composition details
* **Use specific aspect ratios**: 1:1 for profile pictures, 16:9 for presentations, 9:16 for Instagram Stories
* **Combine tools**: Generate an image, then use ImageMagick to resize it, then include it in a PDF document
* **Batch processing**: Upload multiple images for OCR or analysis in one conversation