# Adobe Stock Keyword & Title Generator: Bulk Metadata CSV (`nerolabs/adobe-stock-keyword-generator`) Actor

Titles, 45 ranked keywords, categories and upload-ready CSV files for Adobe Stock, Shutterstock and Freepik from images. Inputs: image links, a ZIP upload, CSV or Google Sheet, dataset; keywordCount, generativeAi, bannedWords. Charged per image described. Agent-ready: x402, MCP.

- **URL**: https://apify.com/nerolabs/adobe-stock-keyword-generator.md
- **Developed by:** [Adam Pearce](https://apify.com/nerolabs) (community)
- **Categories:** AI, E-commerce, Automation
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.80 / 1,000 image describeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Adobe Stock Keyword & Title Generator: Bulk Metadata CSV

Keywording is the slowest part of selling on Adobe Stock, Shutterstock and Freepik. Give this Actor your images (links, a ZIP upload, a CSV, a Google Sheet or a dataset) and get back, for every image, a buyer-friendly **title**, a **description**, up to **49 keywords ranked by importance**, the right **Adobe Stock and Shutterstock categories**, and **upload-ready CSV files** in each agency's exact format.

It looks at each picture with Google's Gemini vision models, then applies the agency rules in code: brand, trademark, artist and AI tool names are removed, duplicates and singular/plural twins are dropped, titles are kept under 70 characters, and every image is checked for logos, recognizable people, readable text and the 4 megapixel minimum.

### Who it is for

- **Microstock contributors** uploading 50 to 500 photos, vectors or AI images a day.
- **AI image creators** selling Midjourney, Firefly or Flux work on Adobe Stock and Freepik (turn on *These are AI-generated images*).
- **Agencies and studios** keywording client shoots, and **AI agents** that generate images and then list them.

### What you get

For each image, a row like this:

```json
{
  "filename": "stock-sample-golden-retriever.jpg",
  "status": "ok",
  "title": "Golden retriever dog lying on green grass outdoors",
  "description": "A calm golden retriever lies on fresh green grass in a park, looking alert, with soft natural light.",
  "keywords": ["golden retriever", "dog", "pet", "grass", "outdoors", "animal", "canine", "lying", "..."],
  "keywordCount": 45,
  "adobeCategory": 1,
  "adobeCategoryName": "Animals",
  "shutterstockCategories": ["Animals/Wildlife", "Nature"],
  "isIllustration": false,
  "needsModelRelease": false,
  "containsLogoOrBrand": false,
  "megapixels": 2.5,
  "warnings": ["Only 2.5 MP: Adobe Stock needs at least 4 MP and Shutterstock 4 MP, so upscale before uploading."]
}
```

And four files in the run's key-value store (links in the **Summary**):

| File | Format |
|---|---|
| `adobe-stock.csv` | Filename, Title, Keywords, Category, Releases |
| `shutterstock.csv` | Filename, Description, Keywords, Categories, Illustration, Mature Content, Editorial |
| `freepik.csv` | File name; Title; Keywords; Prompt; Model (semicolon separated) |
| `all-metadata.csv` | every field, for Dreamstime, 123RF, Pond5, Etsy or your own site |

Upload your images first with the same file names, then upload the CSV in the agency's contributor portal and the titles and keywords fill in by themselves.

### How much does it cost?

1. **$0.004 per image** to this Actor (less on higher Apify plans). Only images that come back with a title and keywords are charged. Failed, duplicate, unreadable and skipped images are marked on the row and never charged.
2. **Gemini's model fee, about $0.0003 per image** on the Fast model (about $0.002 on Best), billed to your Apify account by Apify's official OpenRouter proxy. On Apify's free plan the proxy is charged at 10x.

So 500 images cost about **$2.15**. Most keywording apps charge $10 to $30 a month.

### Input tips

- **ZIP upload** is the easiest way from your computer: zip the folder, upload it in *ZIP file or image*. File names are kept.
- **CSV or Sheet columns:** `image_url` (required), `filename` (the name you upload under), `prompt` (your AI prompt: used as a hint and filled into the Freepik CSV), `context` (a hint like "Lisbon, Portugal").
- **Hint for every image** adds facts a picture cannot show (a place, an event, a collection name). It is ignored when it does not match what is seen.
- **Always include keywords** go first on every image, where Adobe weights them most.

### Good to know

- The model describes only what it sees, so check proper nouns (places, species) before you submit. Hints help.
- Logos, recognizable people and readable text are flagged, not blurred: remove them, add a release, or submit as editorial.
- This Actor does not upload anything to Adobe, Shutterstock or Freepik and never needs your login.
- Adobe Stock, Shutterstock and Freepik are trademarks of their owners. This Actor is not affiliated with them.

If this saved you an evening of keywording, a review on the Apify Store helps a lot.

# Actor input Schema

## `images` (type: `array`):

Links to your images (JPG, PNG, WEBP, TIFF, HEIC), one per line. Each image is charged once, only when its title and keywords come back. Or upload a ZIP below, or give a CSV, Google Sheet or dataset.

## `zipFile` (type: `string`):

Upload a ZIP of your images (or one image), or paste a link to one (Dropbox, a Google Drive file link, your own site). File names inside the ZIP are kept, so the CSVs match your uploads.

## `fileUrl` (type: `string`):

A public CSV, Excel, JSON or Google Sheet with one image link per row. Optional columns: filename (the name you upload under), prompt (the AI prompt, used as a hint and filled into the Freepik CSV) and context (a hint like a place name). Other columns are kept. Used when no images or ZIP are given.

## `datasetId` (type: `string`):

An Apify dataset with image links, for example the output of an AI image generator Actor. Used when no images, ZIP or file are given.

## `imageField` (type: `string`):

For a file or dataset: the column with the image link. Leave empty to detect it (image_url, image, url, images).

## `platforms` (type: `array`):

Which upload CSV files to write. Each is saved in the run's key-value store and linked in the Summary.

## `generativeAi` (type: `boolean`):

Turn on for images made with Midjourney, Firefly, Flux and similar tools. The title and keywords then describe what is shown without mentioning AI (Adobe and Shutterstock label AI content themselves), and people are treated as fictional, so no model release warning.

## `keywordCount` (type: `integer`):

How many keywords to keep, most important first. Adobe Stock allows 49 and weights the first 10 most; Shutterstock allows 50.

## `titleMaxLength` (type: `integer`):

Adobe Stock recommends titles under 70 characters (200 is the hard limit).

## `context` (type: `string`):

Optional. Something the image cannot show, used for every image, for example 'Lisbon, Portugal' or 'Christmas collection'. Ignored when it does not match what is seen.

## `mustIncludeKeywords` (type: `array`):

Optional. Keywords put first on every image, for example a series or location name.

## `bannedWords` (type: `array`):

Optional. Extra words to strip from titles and keywords. Famous brands, trademarks, artist names and AI tool names are already removed.

## `language` (type: `string`):

Language for titles and keywords. Adobe Stock and Shutterstock want English.

## `model` (type: `string`):

Fast (Gemini Flash Lite) costs about $0.0003 per image of model fee, billed to your Apify account by Apify's OpenRouter proxy. Best (Gemini Flash) notices more detail, about $0.002 per image. Same Actor price.

## `fileFormat` (type: `string`):

Leave on auto unless the file is detected wrongly.

## `sheetName` (type: `string`):

For an Excel file: which sheet to read.

## `keepOriginalFields` (type: `boolean`):

Copy the other columns of a file or dataset row onto the output row.

## `concurrency` (type: `integer`):

How many images are described at the same time.

## `maxItems` (type: `integer`):

Stop after this many images.

## Actor input object example

```json
{
  "images": [
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-lake-sunrise.jpg",
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-golden-retriever.jpg",
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-wooden-table.jpg"
  ],
  "platforms": [
    "adobe",
    "shutterstock",
    "freepik",
    "generic"
  ],
  "generativeAi": false,
  "keywordCount": 45,
  "titleMaxLength": 70,
  "language": "English",
  "model": "fast",
  "fileFormat": "auto",
  "keepOriginalFields": true,
  "concurrency": 8
}
```

# Actor output Schema

## `results` (type: `string`):

One row per image: title, description, ranked keywords, Adobe and Shutterstock categories, release, brand and size warnings. Your original columns are kept.

## `adobeCsv` (type: `string`):

Upload-ready Adobe Stock CSV: Filename, Title, Keywords, Category, Releases.

## `shutterstockCsv` (type: `string`):

Upload-ready Shutterstock CSV: Filename, Description, Keywords, Categories, Illustration, Mature Content, Editorial.

## `freepikCsv` (type: `string`):

Upload-ready Freepik (Magnific) CSV, semicolon separated: File name, Title, Keywords, Prompt, Model.

## `allCsv` (type: `string`):

Every field in one sheet, for Dreamstime, 123RF, Pond5, Etsy or your own site.

## `summary` (type: `string`):

Images described, CSV links, model cost, most used keywords, brand, release and size warnings.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "images": [
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-lake-sunrise.jpg",
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-golden-retriever.jpg",
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-wooden-table.jpg"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("nerolabs/adobe-stock-keyword-generator").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "images": [
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-lake-sunrise.jpg",
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-golden-retriever.jpg",
        "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-wooden-table.jpg",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("nerolabs/adobe-stock-keyword-generator").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "images": [
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-lake-sunrise.jpg",
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-golden-retriever.jpg",
    "https://nerolabs-samples.nerolabs.workers.dev/stock-sample-wooden-table.jpg"
  ]
}' |
apify call nerolabs/adobe-stock-keyword-generator --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,nerolabs/adobe-stock-keyword-generator"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/MES607hUYKiVtsuau/builds/AdAuG2xUT5K3ORTyd/openapi.json
