# Convert PDF resumes to Markdown for AI screening

**Use case:** 

Turn a PDF resume into clean Markdown that keeps every section in reading order: contact, summary, experience, education, skills and certifications. Feed it to ChatGPT, Claude or your own LLM to score candidates, pull out fields or match them to a job. The example parses a one-page sample CV in about 20 seconds.

## Input

```json
{
  "documentUrls": [
    "https://api.apify.com/v2/key-value-stores/gZUDoFSN6sExqUTEm/records/sample-cv.pdf"
  ]
}
```

## Output

```json
{
  "source_url": {
    "label": "Source URL",
    "format": "string"
  },
  "candidate_markdown": {
    "label": "Resume Markdown",
    "format": "string"
  }
}
```

## How it works

### 1. Sign up on Apify or log in

The Resume & CV Parser: PDF to Markdown & JSON Actor is ready to run with the inputs already set for "Convert PDF resumes to Markdown for AI screening". [Sign up or log in](https://console.apify.com/create-task-from-example/6IPON95HR8SwGhHeL) and you'll land in Apify Console with a copy of this exact task.

### 2. Start the "Convert PDF resumes to Markdown for AI screening" task

The Resume & CV Parser: PDF to Markdown & JSON Actor will start running based on the input automatically. You can also change all the input fields, like resume / cv pdf urls, to match your specific use case.

### 3. Receive the "Convert PDF resumes to Markdown for AI screening" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as source url and resume markdown.

### 4. Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also [run the "Convert PDF resumes to Markdown for AI screening" task via API](https://apify.com/panix/resume-cv-json-parser.md).

## FAQ

### Why Markdown instead of fixed JSON fields?

Every resume uses different sections. The resume to Markdown task keeps them all, so an LLM can pull out exactly the fields you need, such as skills or years of experience, without losing what a fixed schema leaves out.

### How do I turn the Markdown into JSON fields?

Send candidate_markdown to an LLM with your schema, for example name, email, skills and last job, in n8n, Make, Zapier or your own code. The resume to Markdown task gives the model clean, ordered text.

### Which files does the resume to Markdown task accept?

The resume to Markdown task reads PDF resumes up to 50 MB from public links, in any language, and scanned pages get OCR. Save Word files and images as PDF first.

### How much does the resume to Markdown task cost?

The resume to Markdown task costs $0.015 per resume on the Apify Free plan and $0.0135 on Starter, less on Scale and Business, plus $0.004 per run. Broken links and unreadable files are free.

## About this Actor

This example demonstrates how to use [Resume & CV Parser: PDF to Markdown & JSON](https://apify.com/panix/resume-cv-json-parser.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/panix/resume-cv-json-parser.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

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 full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/panix/resume-cv-json-parser.md

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`).
