# AI Text Detector (`dadhalfdev/ai-text-detector`) Actor Detect AI-generated writing in articles, social posts, and other text. It classifies content type, extracts AI-style signals like phrases, sentence patterns, em dashes, and buzzwords, then returns evidence plus a 0-100 AI likelihood score. - **URL**: https://apify.com/dadhalfdev/ai-text-detector.md - **Developed by:** [Marco Rodrigues](https://apify.com/dadhalfdev) (community) - **Categories:** Automation, Integrations - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing $20.00 / 1,000 results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. 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. Actors are written with capital "A". ## 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. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## 🤖 AI Text Detector Detect AI-generated writing signals in articles, social media posts, and other text formats. The actor classifies each input as `Social Media`, `Article`, or `Other`, then extracts structured evidence and ratings for common AI-writing tells. ### 💡 Perfect For - 📱 **Social Media Audits:** Review comments, captions, and posts for AI-like phrasing. - 📰 **Article Reviews:** Analyze articles, newsletters, and blog posts for formulaic AI writing. - 🛡️ **Moderation & QA:** Build moderation, quality-control, or editorial workflows around AI-content risk. - 📊 **Structured Exports:** Export AI-detection signals to CSV, JSON, Excel, or downstream dashboards. ### ✨ What It Detects For every input text, the actor returns: - 🏷️ `text_type`: `Social Media`, `Article`, or `Other`. - 📏 `text_length_chars` and `text_length_words`. - ➖ `em_dashes_num` and `em_dashes_rating`. - 🧩 AI verb, adjective, noun, transition, and phrase counts, evidence lists, and ratings. - 📝 `sentence_patterns_num`, `sentence_patterns_list`, and `sentence_patterns_rating`. - 🎯 `overall_ai_rating`, a 0-100 estimate of how likely the text is AI-generated. The detector looks for high-signal AI patterns such as em dash-heavy prose, phrases like `game-changer` or `in today's fast-paced world`, generic polished agreement, rhetorical contrast patterns, staccato triplets, vague buzzword stacking, and other formulaic structures. ### 🚀 How To Use 1. Add one or more texts to `input_text_list`. 2. Start the actor. 3. Export the dataset as JSON, CSV, Excel, or through the Apify API. You can process up to 30 texts per run. Each text can contain up to 30,000 characters. ### 📥 Input Example ```json { "input_text_list": [ "Flexible payment systems are essential, but true accessibility comes from supporting freelancers globally, regardless of location. Expanding payment options would make an even bigger impact.", "That’s not a feature. That’s the entire value proposition right there. Because without it, you’re just hoping your agents behave responsibly — and they won’t, because “responsible” isn’t a concept they have. They have goals. Goals and no ceiling is how you end up with a $50,000 cloud bill.\n\nBeyond budget enforcement, Paperclip handles task assignment through what it calls atomic checkout. Only one agent can hold a task at a time. That sounds obvious, but it’s genuinely hard to implement when you’re running a dozen concurrent agents, and most frameworks just… don’t do it. You end up with three agents researching the same competitor because nobody claimed the task. Paperclip treats that the way a database treats concurrent writes — with locks, guarantees, and no duplicates.\n\nEvery decision, every tool call, every status change gets logged to an..." ] } ```` ### 📤 Output Example ```json { "text": "That’s not a feature. That’s the entire value proposition right there. Because without it, you’re just hoping your agents behave responsibly — and they won’t, because “responsible” isn’t a concept they have. They have goals. Goals and no ceiling is how you end up with a $50,000 cloud bill.\n\nBeyond budget enforcement, Paperclip handles task assignment through what it calls atomic checkout. Only one agent can hold a task at a time. That sounds obvious, but it’s genuinely hard to implement when you’re running a dozen concurrent agents, and most frameworks just… don’t do it. You end up with three agents researching the same competitor because nobody claimed the task. Paperclip treats that the way a database treats concurrent writes — with locks, guarantees, and no duplicates.\n\nEvery decision, every tool call, every status change gets logged to an...", "text_type": "Article", "text_length_chars": 12032, "text_length_words": 1974, "em_dashes_num": 16, "em_dashes_rating": 78, "ai_verbs_num": 2, "ai_verbs_list": [ "utilize", "unveil" ], "ai_verbs_rating": 10, "ai_adjectives_num": 0, "ai_adjectives_list": [], "ai_adjectives_rating": 0, "ai_nouns_num": 6, "ai_nouns_list": [ "realm", "landscape", "tapestry", "testament", "beacon", "complexities" ], "ai_nouns_rating": 18, "ai_transitions_num": 2, "ai_transitions_list": [ "Moreover", "In conclusion" ], "ai_transitions_rating": 14, "ai_phrases_num": 2, "ai_phrases_list": [ "in today's fast-paced world", "game-changer" ], "ai_phrases_rating": 72, "sentence_patterns_num": 6, "sentence_patterns_list": [ "That’s not just for debugging, though it’s excellent for debugging.", "That’s not a perfect solution.", "No software solution to alignment is.", "The “Bring Your Own Agent” Architecture (This Is Key)", "The only requirement for an agent to work with Paperclip: it must respond to an HTTP heartbeat signal.", "It’s not a perfect solution." ], "sentence_patterns_rating": 86, "overall_ai_rating": 84 } ``` ### ⚙️ Parameters | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `input_text_list` | array of strings | Yes | List of texts to analyze for AI-generated writing signals. | # Actor input Schema ## `input_text_list` (type: `array`): Provide a list of texts to analyze. ## Actor input object example ```json { "input_text_list": [ "Well said. The right payment method isn’t one-size-fits-all, it should align with the project’s needs. Platforms that offer flexibility along with security definitely make collaboration smoother for both freelancers and clients.", "Flexible payment systems are essential, but true accessibility comes from supporting freelancers globally, regardless of location. Expanding payment options would make an even bigger impact.", "I hope to see the day we no longer celebrate World Parkinson’s Day. My father was diagnosed with Parkinson’s in his early 50’s and fought it for over 30 years. It slowly stripped him of the things he loved in life. I left my job for over a year to care for him until his death in 2022. Thank you for continuing the fight to identify and develop disease modifying treatments for patients like my father. ", "Turning two years of midnight thoughts into a structured verdict on exponential vs. linear growth is a massive use case for LLMs. That 'splitting seven ways' insight is the common trap for high-performers. Focus is the only real lever.", "Will have to check it out. Looks incredible. How you transitioned your digital work to prints and physical is inspiring. 🔥", "Today is Father's Day in Portugal 🇵🇹\n2+ years of being 50% parenting, 50% freelancing.\nExhausting. But I get to spend quality time with my daughter every single day. \nSomething I won't be able to experience ever again. She grows fast, and I'm watching it in real-time ❤️" ] } ``` # Actor output Schema ## `overview` (type: `string`): Table view using the dataset 'ai\_text\_detector' view. ## `results` (type: `string`): All items from the default dataset without view transformation. # 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 '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "input_text_list": [ "Well said. The right payment method isn’t one-size-fits-all, it should align with the project’s needs. Platforms that offer flexibility along with security definitely make collaboration smoother for both freelancers and clients.", "Flexible payment systems are essential, but true accessibility comes from supporting freelancers globally, regardless of location. Expanding payment options would make an even bigger impact.", "I hope to see the day we no longer celebrate World Parkinson’s Day. My father was diagnosed with Parkinson’s in his early 50’s and fought it for over 30 years. It slowly stripped him of the things he loved in life. I left my job for over a year to care for him until his death in 2022. Thank you for continuing the fight to identify and develop disease modifying treatments for patients like my father. ", "Turning two years of midnight thoughts into a structured verdict on exponential vs. linear growth is a massive use case for LLMs. That 'splitting seven ways' insight is the common trap for high-performers. Focus is the only real lever.", "Will have to check it out. Looks incredible. How you transitioned your digital work to prints and physical is inspiring. 🔥", "Today is Father's Day in Portugal 🇵🇹\n2+ years of being 50% parenting, 50% freelancing.\nExhausting. But I get to spend quality time with my daughter every single day. \nSomething I won't be able to experience ever again. She grows fast, and I'm watching it in real-time ❤️" ] }; // Run the Actor and wait for it to finish const run = await client.actor("dadhalfdev/ai-text-detector").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 '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "input_text_list": [ "Well said. The right payment method isn’t one-size-fits-all, it should align with the project’s needs. Platforms that offer flexibility along with security definitely make collaboration smoother for both freelancers and clients.", "Flexible payment systems are essential, but true accessibility comes from supporting freelancers globally, regardless of location. Expanding payment options would make an even bigger impact.", "I hope to see the day we no longer celebrate World Parkinson’s Day. My father was diagnosed with Parkinson’s in his early 50’s and fought it for over 30 years. It slowly stripped him of the things he loved in life. I left my job for over a year to care for him until his death in 2022. Thank you for continuing the fight to identify and develop disease modifying treatments for patients like my father. ", "Turning two years of midnight thoughts into a structured verdict on exponential vs. linear growth is a massive use case for LLMs. That 'splitting seven ways' insight is the common trap for high-performers. Focus is the only real lever.", "Will have to check it out. Looks incredible. How you transitioned your digital work to prints and physical is inspiring. 🔥", """Today is Father's Day in Portugal 🇵🇹 2+ years of being 50% parenting, 50% freelancing. Exhausting. But I get to spend quality time with my daughter every single day. Something I won't be able to experience ever again. She grows fast, and I'm watching it in real-time ❤️""", ] } # Run the Actor and wait for it to finish run = client.actor("dadhalfdev/ai-text-detector").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "input_text_list": [ "Well said. The right payment method isn’t one-size-fits-all, it should align with the project’s needs. Platforms that offer flexibility along with security definitely make collaboration smoother for both freelancers and clients.", "Flexible payment systems are essential, but true accessibility comes from supporting freelancers globally, regardless of location. Expanding payment options would make an even bigger impact.", "I hope to see the day we no longer celebrate World Parkinson’s Day. My father was diagnosed with Parkinson’s in his early 50’s and fought it for over 30 years. It slowly stripped him of the things he loved in life. I left my job for over a year to care for him until his death in 2022. Thank you for continuing the fight to identify and develop disease modifying treatments for patients like my father. ", "Turning two years of midnight thoughts into a structured verdict on exponential vs. linear growth is a massive use case for LLMs. That '\''splitting seven ways'\'' insight is the common trap for high-performers. Focus is the only real lever.", "Will have to check it out. Looks incredible. How you transitioned your digital work to prints and physical is inspiring. 🔥", "Today is Father'\''s Day in Portugal 🇵🇹\\n2+ years of being 50% parenting, 50% freelancing.\\nExhausting. But I get to spend quality time with my daughter every single day. \\nSomething I won'\''t be able to experience ever again. She grows fast, and I'\''m watching it in real-time ❤️" ] }' | apify call dadhalfdev/ai-text-detector --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=dadhalfdev/ai-text-detector", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AI Text Detector", "description": "Detect AI-generated writing in articles, social posts, and other text. It classifies content type, extracts AI-style signals like phrases, sentence patterns, em dashes, and buzzwords, then returns evidence plus a 0-100 AI likelihood score.", "version": "0.1", "x-build-id": "SV5gjqAb2nQcAzhxK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dadhalfdev~ai-text-detector/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dadhalfdev-ai-text-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dadhalfdev~ai-text-detector/runs": { "post": { "operationId": "runs-sync-dadhalfdev-ai-text-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dadhalfdev~ai-text-detector/run-sync": { "post": { "operationId": "run-sync-dadhalfdev-ai-text-detector", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "input_text_list" ], "properties": { "input_text_list": { "title": "List of Texts", "minItems": 1, "maxItems": 30, "uniqueItems": true, "type": "array", "description": "Provide a list of texts to analyze.", "items": { "type": "string", "maxLength": 30000 } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```