Create Your Own AI Content Writer in PHP with the ChatGPT API

Pradeep Maurya

1 minute ago

Create Your Own AI Content Writer in PHP with the ChatGPT API

Automation is growing more vital in the modern era of content creation. AI Content Writer is one of the most powerful content generation tools available today, with OpenAI’s ChatGPT standing out as a popular choice to generate human-like writing. AI may save you a lot of time while improving the quality of your blog posts, articles, and product descriptions.

In this tutorial, we’ll walk you through the steps of building your own AI content writer with PHP and the OpenAI ChatGPT API.

Looking for a Website Developer in Delhi NCR?

Get a professionally designed and developed website tailored to your needs.
As an experienced website developer based in Delhi NCR, I offer customized solutions to build responsive, SEO-friendly, and user-friendly websites. Whether it’s for a personal blog, business site, or e-commerce store, I ensure your online presence stands out.

Let's Connect Now

What is ChatGPT?

ChatGPT built by openAI, is a strong language model that creates text that appears human and natural. It is trained on a large amount of data from many sources, allowing it to generate content on a wide range of themes, tones, and styles.

For example, if you require an article on a specific topic, you can simply tell ChatGPT, ‘Write a 500-word essay about AI in 2025,’ and it will generate content according to your specifications. This makes it a great tool for content creators who want to save time while improving their work.

Setting Up the OpenAI API

Before diving into the development, the first step is to set up the OpenAI API. Here’s how:

Create an OpenAI Account: Go to OpenAI and create an account.
Get Your API Key: Once you’ve created an account and logged in, Create your project and navigate to the API section to generate an API key. This key will allow your PHP application to communicate with OpenAI’s servers.

Generate API Key

Now copy and save this key in a safe place for future use in the project.

Create a Frontend User Input Form

The first part of your application will be a simple HTML form where users can input the following details:

Topic: The subject for which they need content.
Tone: The tone of the article (formal, casual, etc.).
Word Count: The desired length of the article.

Copy and Paste HTML code for the frontend:

PHP (index.php)


<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>AI Content Writer</title>
    <style>
        body {
            font-family: Arial, sans-serif;
            background-color: #f4f4f9;
            margin: 0;
            padding: 0;
            display: flex;
            justify-content: center;
            align-items: center;
            min-height: 100vh;
        }

        .container {
            background: #ffffff;
            box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
            border-radius: 8px;
            padding: 20px 30px;
            max-width: 600px;
            width: 100%;
        }

        h1 {
            text-align: center;
            color: #333;
            margin-bottom: 20px;
        }

        form {
            display: flex;
            flex-direction: column;
        }

        label {
            font-size: 14px;
            font-weight: bold;
            margin-bottom: 8px;
            color: #555;
        }

        input, select, button {
            font-size: 14px;
            padding: 10px;
            margin-bottom: 15px;
            border: 1px solid #ccc;
            border-radius: 4px;
            width: 100%;
            box-sizing: border-box;
        }

        input:focus, select:focus {
            border-color: #007bff;
            outline: none;
        }

        button {
            background-color: #007bff;
            color: white;
            border: none;
            cursor: pointer;
            font-weight: bold;
            transition: background-color 0.3s;
        }

        button:hover {
            background-color: #0056b3;
        }

        .content {
            margin-top: 20px;
            padding: 15px;
            background: #f9f9f9;
            border: 1px solid #ddd;
            border-radius: 4px;
        }

        .content h2 {
            color: #333;
            margin-bottom: 10px;
        }

        .content p {
            white-space: pre-wrap; /* Preserve line breaks */
            font-size: 14px;
            color: #555;
        }
    </style>
</head>
<body>
    <div class="container">
        <h4>AI Content Writer</h4>
        <form id="contentForm">
            <label for="topic">Topic:</label>
            <input type="text" id="topic" name="topic" placeholder="Enter the topic (e.g., AI in 2025)" required>

            <label for="tone">Tone:</label>
            <select id="tone" name="tone">
                <option value="formal">Formal</option>
                <option value="casual">Casual</option>
                <option value="informative">Informative</option>
            </select>

            <label for="word_count">Word Count:</label>
            <input type="number" id="word_count" name="word_count" min="100" max="2000" placeholder="Enter word count (e.g., 500)" required>

            <button type="submit">Generate Content</button>
        </form>

        <div class="content">
            <h4>Generated Content</h4>
            <p id="output"></p>
        </div>
    </div>

    <script>
        document.getElementById('contentForm').addEventListener('submit', function (event) {
            event.preventDefault();

            const formData = new FormData(event.target);
            const contentElement = document.getElementById('output');
            contentElement.textContent = 'Typing...'; // Clear previous content

            // Use the Fetch API to send a POST request
            fetch('openAI.php', {
                method: 'POST',
                body: formData,
            })
            .then(response => {
                if (response.ok) {
                    // Create an EventSource to listen for real-time content
                  
                    const eventSource = new EventSource('openAI.php?' + new URLSearchParams({
                        topic: formData.get('topic'),
                        tone: formData.get('tone'),
                        word_count: formData.get('word_count')
                    }));
                     contentElement.textContent = '';
                    eventSource.onmessage = function (event) {
                         
                        if (event.data === '[DONE]') {
                            eventSource.close();
                        } else {
                           const content = JSON.parse(event.data);
                         
    
        contentElement.innerHTML += content; // Append the cleaned content
        
                        }
                    };

                    eventSource.onerror = function () {
                        console.error('Error connecting to the server1.');
                        eventSource.close();
                    };
                }
            })
            .catch(error => {
                console.error('Error connecting to the server:', error);
            });
        });
    </script>
    
    
</body>
</html>

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

<!DOCTYPE html>

<head>

<title>AI Content Writer</title>

<style>

body {

font-family: Arial, sans-serif;

background-color: #f4f4f9;

margin: 0;

padding: 0;

display: flex;

justify-content: center;

align-items: center;

min-height: 100vh;

}

.container {

background: #ffffff;

box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);

border-radius: 8px;

padding: 20px 30px;

max-width: 600px;

width: 100%;

}

h1 {

text-align: center;

color: #333;

margin-bottom: 20px;

}

form {

display: flex;

flex-direction: column;

}

label {

font-size: 14px;

font-weight: bold;

margin-bottom: 8px;

color: #555;

}

input, select, button {

font-size: 14px;

padding: 10px;

margin-bottom: 15px;

border: 1px solid #ccc;

border-radius: 4px;

width: 100%;

box-sizing: border-box;

}

input:focus, select:focus {

border-color: #007bff;

outline: none;

}

button {

background-color: #007bff;

color: white;

border: none;

cursor: pointer;

font-weight: bold;

transition: background-color 0.3s;

}

button:hover {

background-color: #0056b3;

}

.content {

margin-top: 20px;

padding: 15px;

background: #f9f9f9;

border: 1px solid #ddd;

border-radius: 4px;

}

.content h2 {

color: #333;

margin-bottom: 10px;

}

.content p {

white-space: pre-wrap; /* Preserve line breaks */

font-size: 14px;

color: #555;

}

</style>

</head>

<body>

<h4>AI Content Writer</h4>

<label for="topic">Topic:</label>

<option value="formal">Formal</option>

<option value="casual">Casual</option>

<option value="informative">Informative</option>

</select>

<label for="word_count">Word Count:</label>

<button type="submit">Generate Content</button>

</form>

<h4>Generated Content</h4>

</div>

document.getElementById('contentForm').addEventListener('submit', function (event) {

event.preventDefault();

const formData = new FormData(event.target);

const contentElement = document.getElementById('output');

contentElement.textContent = 'Typing...'; // Clear previous content

// Use the Fetch API to send a POST request

fetch('openAI.php', {

method: 'POST',

body: formData,

})

.then(response => {

if (response.ok) {

// Create an EventSource to listen for real-time content

const eventSource = new EventSource('openAI.php?' + new URLSearchParams({

topic: formData.get('topic'),

tone: formData.get('tone'),

word_count: formData.get('word_count')

}));

contentElement.textContent = '';

eventSource.onmessage = function (event) {

if (event.data === '[DONE]') {

eventSource.close();

} else {

const content = JSON.parse(event.data);

contentElement.innerHTML += content; // Append the cleaned content

}

};

eventSource.onerror = function () {

console.error('Error connecting to the server1.');

eventSource.close();

};

}

})

.catch(error => {

console.error('Error connecting to the server:', error);

});

</script>

</body>

</html>

Backend: PHP Script for OpenAI Integration

Now that we have the frontend in place, let’s focus on the backend. The openAI.php script handles the interaction between your application and OpenAI’s API.


<?php

$apiKey = "YOUR_OPENAI_API_KEY";

// Ensure the proper headers for SSE
header("Content-Type: text/event-stream");
header("Cache-Control: no-cache");
header("Connection: keep-alive");
header("Access-Control-Allow-Origin: *");
header("Access-Control-Allow-Methods: POST, GET, OPTIONS");
header("Access-Control-Allow-Headers: Content-Type");


// Check if the request method is GET
if ($_SERVER['REQUEST_METHOD'] === 'GET') {
    // Get the data from the form submission
    $topic = htmlspecialchars($_GET['topic'] ?? 'Default Topic');
    $tone = htmlspecialchars($_GET['tone'] ?? 'neutral');
    $wordCount = intval($_GET['word_count'] ?? 200);

    // Prepare the messages for OpenAI API request
    $messages = [
        ['role' => 'system', 'content' => 'You are a professional content writer.'],
        ['role' => 'user', 'content' => "Write a {$tone} article about '{$topic}' in approximately {$wordCount} words."]
    ];

    // Prepare the OpenAI API request payload
    $data = [
        'model' => 'gpt-4', // You can change to a different model if required
        'messages' => $messages,
        'max_tokens' => $wordCount * 4,
        'temperature' => 0.7,
        'stream' => true, // Enable streaming
    ];

    // Initialize the cURL session
    $ch = curl_init('https://api.openai.com/v1/chat/completions');
    curl_setopt($ch, CURLOPT_POST, true);
    curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, false);
    curl_setopt($ch, CURLOPT_HTTPHEADER, [
        'Authorization: Bearer ' . $apiKey,
        'Content-Type: application/json',
    ]);


    // Handle the stream of data
    curl_setopt($ch, CURLOPT_WRITEFUNCTION, function ($ch, $chunk) {
        $lines = explode("\n", $chunk);
        
        foreach ($lines as $line) {
            $line = trim($line);
            if (empty($line) || strpos($line, 'data:') !== 0) continue;
            $data = json_decode(substr($line, 5), true);
            if (isset($data['choices'][0]['delta']['content'])) {
                $content = $data['choices'][0]['delta']['content'];
                
                // Convert markdown content to HTML
              //  $htmlContent = markdown_to_html($content);

                // Output the HTML content
                echo "data: " . json_encode($content, JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE) . "\n\n";
                ob_flush();
                flush();
            }
        }
        return strlen($chunk);
    });

    // Execute the cURL request
    curl_exec($ch);

    // Close the cURL connection
    curl_close($ch);

    // Finalize the stream by sending a [DONE] message
    echo "event: close\n";
    echo "data: [DONE]\n\n";
    ob_flush();
    flush();
    exit;
}

?>

<?php

$apiKey = "YOUR_OPENAI_API_KEY";

// Ensure the proper headers for SSE

header("Content-Type: text/event-stream");

header("Cache-Control: no-cache");

header("Connection: keep-alive");

header("Access-Control-Allow-Origin: *");

header("Access-Control-Allow-Methods: POST, GET, OPTIONS");

header("Access-Control-Allow-Headers: Content-Type");

// Check if the request method is GET

if ($_SERVER['REQUEST_METHOD'] === 'GET') {

// Get the data from the form submission

$topic = htmlspecialchars($_GET['topic'] ?? 'Default Topic');

$tone = htmlspecialchars($_GET['tone'] ?? 'neutral');

$wordCount = intval($_GET['word_count'] ?? 200);

// Prepare the messages for OpenAI API request

$messages = [

['role' => 'system', 'content' => 'You are a professional content writer.'],

['role' => 'user', 'content' => "Write a {$tone} article about '{$topic}' in approximately {$wordCount} words."]

];

// Prepare the OpenAI API request payload

$data = [

'model' => 'gpt-4', // You can change to a different model if required

'messages' => $messages,

'max_tokens' => $wordCount * 4,

'temperature' => 0.7,

'stream' => true, // Enable streaming

];

// Initialize the cURL session

$ch = curl_init('https://api.openai.com/v1/chat/completions');

curl_setopt($ch, CURLOPT_POST, true);

curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($data));

curl_setopt($ch, CURLOPT_RETURNTRANSFER, false);

curl_setopt($ch, CURLOPT_HTTPHEADER, [

'Authorization: Bearer ' . $apiKey,

'Content-Type: application/json',

]);

// Handle the stream of data

curl_setopt($ch, CURLOPT_WRITEFUNCTION, function ($ch, $chunk) {

$lines = explode("\n", $chunk);

foreach ($lines as $line) {

$line = trim($line);

if (empty($line) || strpos($line, 'data:') !== 0) continue;

$data = json_decode(substr($line, 5), true);

if (isset($data['choices'][0]['delta']['content'])) {

$content = $data['choices'][0]['delta']['content'];

// Convert markdown content to HTML

// $htmlContent = markdown_to_html($content);

// Output the HTML content

echo "data: " . json_encode($content, JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE) . "\n\n";

ob_flush();

flush();

}

return strlen($chunk);

});

// Execute the cURL request

curl_exec($ch);

// Close the cURL connection

curl_close($ch);

// Finalize the stream by sending a [DONE] message

echo "event: close\n";

echo "data: [DONE]\n\n";

ob_flush();

flush();

exit;

}

Are you want to get implementation help, or modify or extend the functionality?

A Tutorialswebsite Expert can do it for you.

Hire an Expert

Stream Data to Frontend in Real-Time

Here, I’m sending real-time AI-generated content to the user interface via the Server-Sent Events (SSE) method. This enables you to see the article in progress. SSE ensures that content is streamed piece by piece as the model generates it, providing a more seamless user experience.

View Demo

Conclusion

Building an AI content writer using PHP and OpenAI’s ChatGPT API can save time while producing high-quality, human-like content. This AI tool is easy to integrate into any website or application thanks to its simple user interface, real-time streaming, and minimal backend code.

Also Read: Create Dynamic Image Slider Using PHP and MySQL

Whether you’re creating blogs, articles, or marketing copy, an AI content writer can help you improve your workflow and create more interesting material.

Thanks for reading 🙏, I hope you found How to Create Your Own AI Content Writer in PHP with the ChatGPT API tutorial helpful for your project. Keep learning! If you face any problems – I am here to solve your problems.

Pradeep Maurya

Pradeep Maurya is the Professional Web Developer & Designer and the Founder of “Tutorials website”. He lives in Delhi and loves to be a self-dependent person. As an owner, he is trying his best to improve this platform day by day. His passion, dedication and quick decision making ability to stand apart from others. He’s an avid blogger and writes on the publications like Dzone, e27.co