--- title: Make AI Content Extractor slug: Twfdcm7QGCp_9QKZ3GGrY image: https://make-cxp-documentation.ams3.digitaloceanspaces.com/apps-center-icons/PREVIEW_make-ai-extractors.png docTags: createdAt: 2025-06-17T21:28:39.004Z --- :::hint{type="warning"} **Make AI Content Extractor** is available on **paid plans**. To use it, upgrade to a paid plan. While this app is in beta, functionality and pricing may change. ::: Make AI Content Extractor is a built-in app that extracts structured text and metadata from files like PDFs, Word documents, images, and audio recordings—directly within your Make scenarios. It also converts unstructured inputs into a clean format suitable for AI apps, all without relying on third-party services. Make AI Content Extractor ensures consistent output that integrates seamlessly with AI modules and AI-based automations, making it ideal for tasks like pulling invoice fields from a scanned PDF, transcribing a voice note, or analyzing WhatsApp image attachments. # Key benefits - **No external accounts**: No need to connect or manage a separate account. Everything works within your existing Make environment. - **Privacy focused**: Your data is never stored or used for AI training. - **Instant setup**: Start using the app immediately in your scenarios. There is no need to create any connection. - **Structured output**: No matter the file type or layout, the app returns your data in the same, perfectly organized format every time. AI providers for each module | Module | Provider | | ------------------------------------------------------------------------- | --------- | | [Extract text from a document](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Extract information from an invoice](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Extract information from a receipt](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Generate a caption for an image](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Generate captions for an image (advanced)](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Describe an image](docId:-Jf9oHeMg72RRdb9cHwXv) | OpenAI | | [Extract text from an image](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Generate image tags](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Detect objects in an image](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Transcribe an audio file](docId:-Jf9oHeMg72RRdb9cHwXv) | Microsoft | | [Translate an audio file](docId:-Jf9oHeMg72RRdb9cHwXv) | OpenAI | # Credit usage The Make AI Content Extractor app has a specific credit usage for each module. You can find the details below. ::::VerticalSplit{layout="left"} :::VerticalSplitItem Extract text from a document ::: :::VerticalSplitItem This module uses **10 credits** for each page processed. **Example**: If you extract text from a document with 3 pages, it costs 30 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Extract information from an invoice ::: :::VerticalSplitItem This module uses **10 credits** for each operation. **Example**: If you extract information from two invoices, the module will complete two operations and use 20 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Extract information from a receipt ::: :::VerticalSplitItem This module uses **10 credits** for each operation. **Example**: If you extract information from two receipts, the module will complete two operations and use 20 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Generate a caption for an image ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you generate captions for two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Generate captions for an image (advanced) ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you generate multiple captions for two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Describe an image ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you describe two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Extract text from an image ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you extract text from two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Generate image tags ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you generate tags for two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Detect objects in an image ::: :::VerticalSplitItem This module uses **2 credits** for each operation. **Example**: If you detect objects in two images, the module will complete two operations and use 4 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Transcribe an audio file ::: :::VerticalSplitItem This module uses **20 credits **for each minute of audio processed. **Example**: If you transcribe an audio file with 3.5 minutes, it costs 70 credits. ::: :::: *** ::::VerticalSplit{layout="left"} :::VerticalSplitItem Translate an audio file ::: :::VerticalSplitItem This module uses **20 credits **for each minute of audio processed. **Example**: If you translate an audio file with 3.5 minutes, it costs 70 credits. ::: :::: :::hint{type="info"} For more detailed information about credits, refer to the [Credits](https://help.make.com/credits) documentation. ::: # Make AI Content Extractor modules All modules support two ways to upload a file: **Via a publicly accessible URL** You can paste a publicly accessible URL directly into the module to extract information from the file. **Mapping a file from your cloud storage** If your file is stored on a cloud service like Google Drive, OneDrive, or similar, first use a module to download the file (e.g., Google Drive - Download a File). Next, add a required Make AI Content Extractor module and choose to extract by file. You can use the following types of modules to build your scenarios. :::hint{type="warning"} The current features and functionality are still in **beta** and are actively being improved. As such, **pricing is subject to change** and will be updated as the app evolves. ::: ## Document ::::ExpandableHeading ### Extract text from a document Extracts text from any type of document. **When to use it?** Use the Extract text from a document module when you need to extract content from tables, multi-column layouts, or text-heavy documents. | **Field** | **Description** | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Document source** | Select how you want to provide the content for extraction:
- File
- URL
**Supported formats**: `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX`, `HTML`.

**Limitation**:
- For PDF and TIFF, up to 2,000 pages can be processed.
- The maximum file size is 500 MB.
- Image dimensions must be between 50 x 50 and 10,000 x 10,000 pixels.
- If your PDFs are password-locked, you must remove the lock before submission. | | **File** | Select or map the file you want to extract data from.
- **File name:** Enter (map) the name of the file you want to extract.
- **Data:** Enter (map) the file data. | | **Document URL** | Enter the publicly accessible URL for the document. | | **Page Ranges** | Enter specific page numbers or ranges to extract information from.

For example: `1,3-6`. | | **Limit** | Enter the maximum number of pages to extract. Leave this field empty to return all pages in the document.

If **Page Ranges** is defined, this field will be ignored. | :::hint{type="info"} To see the available languages, refer to the [Microsoft Learn Language support](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/ocr?view=doc-intel-4.0.0\&preserve-view=true\&tabs=read-print%2Clayout-print%2Cgeneral#read-model) page. ::: **Example** This example shows the output (extracted information) generated from the provided `.pdf` file: ![](https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-Ryi5cw4iqwCpABT-no_yh-20250821-135851.png) :::: ::::ExpandableHeading ### Extract information from an invoice Extracts the details from an invoice. **When to use it?** Use Extract information from an invoice when you need specific invoice fields such as vendor name, line items, totals, tax, due date and feed them directly into an accounting tool, spreadsheet, or approval workflow | **Field** | **Description** | | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Invoice source** | Select how you want to provide the invoice file:
- File
- URL
**Supported formats**: `PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX`, `HTML`.

**Limitation**:
- For PDF and TIFF, up to 2,000 pages can be processed.
- The maximum file size is 500 MB.
- Image dimensions must be between 50 x 50 and 10,000 x 10,000 pixels.
- If your PDFs are password-locked, you must remove the lock before submission. | | **File** | Select or map the file you want to extract data from.
- **File name:** Enter (map) the name of the file you want to extract.
- **Data:** Enter (map) the file data. | | **Invoice URL** | Enter the publicly accessible URL for the invoice. | :::hint{type="info"} To see the available languages, refer to the [Microsoft Learn Language support](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/prebuilt?view=doc-intel-4.0.0\&tabs=languages%2Cthermal#invoice) page. ::: **Example** This example shows the output (extracted invoice details) generated from the provided invoice: ![](https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-19CYG4IMLlmCjzgkdw7z6-20250822-113514.png) :::: ::::ExpandableHeading ### Extract information from a receipt Extracts the details from a receipt. **When to use it?** Use when you need structured data from a receipt such as merchant name, date, items, total. Same idea as the invoice module but optimized for retail/point-of-sale receipt formats and log it in an expense tracker or reimbursement workflow | **Field** | **Description** | | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Extract by** | Select how you want to provide the receipt:
- File
- URL
**Supported formats**:
`PDF`, `JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`, `DOCX`, `XLSX`, `PPTX`, `HTML`.

**Limitation**:
- For PDF and TIFF, up to 2,000 pages can be processed.
- The maximum file size is 500 MB.
- Image dimensions must be between 50 x 50 and 10,000 x 10,000 pixels.
- If your PDFs are password-locked, you must remove the lock before submission. | | **File** | Select or map the file you want to extract data from.
- **File name:** Enter (map) the name of the file you want to extract.
- **Data:** Enter (map) the file data. | | **Receipt URL** | Enter the publicly accessible URL for the receipt. | :::hint{type="info"} To see the available languages, refer to the [Microsoft Learn Language support](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/language-support/prebuilt?view=doc-intel-4.0.0\&tabs=languages%2Cthermal#receipt) page. ::: **Example** This example shows the output (extracted receipt details) generated from the provided receipt: ![](https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-BrEl_fVsEt_D4J1X19zpe-20250822-113748.png) :::: ## Image :::ExpandableHeading ### Generate a caption for an image Generates a one-sentence caption describing an image's content. **When to use it?** Use this module when you need a single, one-sentence description of an image, such as auto-generating alt text for accessibility or labeling images before storing them in a CMS. | **Field** | **Description** | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Image source** | Select how you want to provide the image.
- File
- URL
**Supported formats**: `JPEG/JPG`, `PNG`, `GIF`, `BMP`, `WEBP`, `ICO`, `TIFF`, `MPO`.

**Limitation**: Images must be less than 20 MB and have dimensions between 50 x 50 and 16,000 x 16,000 pixels. | | **File** | Select or map the file you want to caption.
- **File name:** Enter (map) the name of the file you want to caption.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to caption. | | **Gender neutral caption** | Select whether to generate captions using gender-neutral terms.

For example, terms such `person` and `child` will be used instead of `woman` or `man` and `boy` or `girl` in English. | **Example** This example shows the output (image caption) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-iCaIB0G3TLraUwb2z30ZY-20250822-113818.png" size="90" width="834" height="616" position="center" darkWidth="834" darkHeight="616" showCaption="false"} ::: :::ExpandableHeading ### Generate captions for an image (advanced) Generates up to 10 captions describing different parts of an image. Each caption will be a separate bundle and processed individually in the rest of the scenario. **When to use it?** Use this module when you need multiple captions describing different parts of the same image, and each caption needs to be processed individually by the rest of the scenario. | **Field** | **Description** | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Image source** | Select how you want to provide the image.
- File
- URL
**Supported formats**: `JPEG/JPG`, `PNG`, `GIF`, `BMP`, `WEBP`, `ICO`, `TIFF`, `MPO`.

**Limitation**: Images must be less than 20 MB and have dimensions between 50 x 50 and 16,000 x 16,000 pixels. | | **File** | Select or map the file you want to caption.
- **File name:** Enter the name of the file you want to caption.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to caption. | | **Gender neutral caption** | Select whether to generate captions using gender-neutral terms.

For example, terms such `person` and `child` will be used instead of `woman` or `man` and `boy` or `girl` in English. | **Example** This example shows the output (image captions) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-Bcs1bKawPmhsSsTdjKu1t-20250822-113916.png" size="80" width="882" height="747" position="center" darkWidth="882" darkHeight="747" showCaption="false"} ::: :::ExpandableHeading ### Describe an image Describes an image in detail. **When to use it?** Use this module when you need a detailed, paragraph-level description of an image, especially when you want to guide the output with a custom prompt, such as focusing on specific features or writing in a particular style. | **Field** | **Description** | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Image source** | Select how you want to provide the image.
- File
- URL
**Limitation**: Images must be less than 4 MB and have dimensions smaller than 33 megapixels. | | **File** | Select or map the file you want to describe.
- **File name:** Enter (map) the name of the file you want to caption.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to caption.
****
The file size of the image must be less than 20 MB. The dimensions of the image must be less than 33 megapixels. | | **Prompt** | Enter custom instructions to guide how the AI should describe the image. For example, specify the writing style of the image description or provide background context. | | **Temperature** | Adjust how creative or predictable the response is. Lower values make the output more focused, while higher values make it more diverse. Must be lower than or equal to 1. | | **Top p** | Limit the response to the most likely words. A lower value makes the output more focused by narrowing the range of possible words. Must be lower than or equal to 1. | **Example** This example shows the output (image description) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-9iiNs2AMNq1RRxto22tV8-20250822-114101.png" size="80" width="765" height="784" position="center" darkWidth="765" darkHeight="784" showCaption="false"} ::: :::ExpandableHeading ### Extract text from an image Extracts printed or handwritten text from an image. **When to use it?** Extract text from an image module is intended for simple text extraction (e.g. license plates), not structured content like tables. For structured content like tables or multi-column layouts, use [Extract text from a document](docId\:ySVlREkDtol8_oZG0fbqG) module. | **Field** | **Description** | | ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Image source** | Select how you want to provide the image.
- File
- URL
**Supported formats**: `JPEG/JPG`, `PNG`, `GIF`, `BMP`, `WEBP`, `ICO`, `TIFF`, `MPO`.

**Limitation**: Images must be less than 20 MB and have dimensions between 50 x 50 and 16,000 x 16,000 pixels. Supported formats include | | **File** | Select or map the file you want to describe.
- **File name:** Enter (map) the name of the image you want to extract text from.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to extract text from. | | **Limit** | Enter the maximum number of text blocks to return.
Leave this empty to return all recognized text blocks in the image. | **Example** This example shows the output (text) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-knKhjcmflEGe9HaqEDsYs-20250822-114145.png" size="74" width="800" height="772" position="center" darkWidth="800" darkHeight="772" showCaption="false"} ::: :::ExpandableHeading ### Generate image tags Generates a list of words related to the image. **When to use it?** Use this module when you need a list of keywords that describe an image's content, such as auto-populating searchable metadata for a product catalog or media library. | **Field** | **Description** | | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Image source** | Select how you want to provide the image.
- File
- URL
**Supported formats**: `JPEG/JPG`, `PNG`, `GIF`, `BMP`, `WEBP`, `ICO`, `TIFF`, `MPO`.

**Limitation:** Images must be less than 20 MB and have dimensions between 50 x 50 and 16,000 x 16,000 pixels. | | **File** | Select or map the image you want to receive tags from.
- **File name:** Enter (map) the name of the image you want to receive tags from.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to receive tags from. | | **Limit** | Enter the maximum number of returned tags.
Leave this field empty to return all recognized tags for the image. | **Example** This example shows the output (image tags) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-2heF5KjxyYZ7KfGZHcFlx-20250822-114220.png" size="78" width="814" height="749" position="center" darkWidth="814" darkHeight="749" showCaption="false"} ::: :::ExpandableHeading ### Detect objects in an image Detects different objects in an image, including their approximate location within the image. **When to use it?** Use this module when you need to identify what objects appear in an image and where they are located, such as checking shelf layouts, flagging missing components, or triggering actions based on what's present. | **Field** | **Description** | | ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Image source** | Select how you want to provide the image.
- File
- URL
**Supported formats**: `JPEG/JPG`, `PNG`, `GIF`, `BMP`, `WEBP`, `ICO`, `TIFF`, `MPO`.

**Limitation**: Images must be less than 20 MB and have dimensions between 50 x 50 and 16,000 x 16,000 pixels. | | **File** | Select or map the image you want to detect objects from.
- **File name:** Enter (map) the name of the image you want to detect objects from.
- **Data:** Enter (map) the file data. | | **Image URL** | Enter a public URL to the image you want to detect objects from. | | **Ignore duplicate objects** | Select whether you want to ignore duplicate objects in the output. | | **Limit** | Enter the maximum number of returned tags.
Leave this empty to return all recognized objects on the image provided. | **Example** This example shows the output (objects in an image) generated from the provided image URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-ZBlBb5goO9y8SRtzO37L3-20250822-114300.png" size="70" width="818" height="732" position="center" darkWidth="818" darkHeight="732" showCaption="false"} ::: ## Speech :::ExpandableHeading ### Transcribe an audio file Transcribes an audio file. **When to use it?** Use this module when you need a text transcript of a spoken audio recording, such as a meeting, voice note, or customer call, optionally with speakers identified separately. | **Field** | **Description** | | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Audio source** | Select how you want to provide the audio.
- File
- URL
**Supported formats**: `WAV`, `MP3`, `OPUS/OGG`, `FLAC`, `WMA`, `AAC`, `ALAW` in `WAV` container, `MULAW` in `WAV` container, `AMR`, `WebM`, `SPEEX`.

**Limitation**: Audios must be less than 2 hours long and 300 MB in size. | | **File** | Select or map the audio file you want to transcribe.
- **File name:** Enter (map) the name of the audio file you want to transcribe.
- **Data:** Enter (map) the file data. | | **Language** | Select one or more expected languages for the audio. | | **Profanity filter mode** | Select how the transcription handles profane language. | | **Channels** | Enter (map) the indices of audio channels to transcribe separately.

Up to two channels are supported unless diarization is enabled. By default, this tool merges all input channels into a single channel and then performs the transcription. If this isn't desirable, channels can be transcribed independently without merging. | | **Diarization** | Enable this to let the tool identify and distinguish between different speakers. If you enable diarization, you can also set the expected maximum number of speakers. | **Example** This example shows the output (audio transcript) generated from the provided audio URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-dn3b-FESg5OFCfOuiYCFf-20250822-114329.png" size="76" width="852" height="834" position="center" darkWidth="852" darkHeight="834" showCaption="false"} ::: :::ExpandableHeading ### Translate an audio file Translates an audio file to English. **When to use it?** Use this module when you need spoken audio in a non-English language converted directly to English text, without a separate transcription step. | **Field** | **Description** | | ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Audio source** | Select how you want to provide the audio.
- File
- URL
**Supported formats**: `FLAC`, `MP3`, `MP4`, `MPEG`, `MPGA`, `M4A`, `OGG`, `WAV`, `WebM`.

**Limitation**: Audios must be less than 25 MB in size. | | **File** | Select or map the audio file you want to translate.
- **File name:** Enter (map) the name of the audio file you want to translate.
- **Data:** Enter (map) the file data. | | **Audio** **URL** | Enter a public URL to the audio you want to translate. | | **File name** | The file name is taken from the URL by default. If the original name is missing a supported audio extension (like `.mp3` or `.wav`) or causes an error, please enter a new name to help our AI correctly identify the file type. | | **Prompt** | Enter a prompt to guide the model's style or specify how to spell unfamiliar words. This is limited to 224 tokens. | | **Temperature** | Enter the randomness of the translation. It controls the randomness of the response and the likeliness of the AI selecting less probable words or phrases. For translations, we recommend the default value of 0.

Must be lower than or equal to 1. | **Example** This example shows the output (translation) generated from the provided audio URL: ::Image[]{src="https://api.archbee.com/api/optimize/4CkrlJIBl1di_p1x71ery-mU9P_jhbfXWwVLXP2nZa8-20250822-114409.png" size="80" width="846" height="690" position="center" darkWidth="846" darkHeight="690" showCaption="false"} ::: # Templates You can look for Make AI Content Extractor templates in [Make's template gallery](https://www.make.com/en/templates), where you'll find thousands of pre-created scenarios.