{"componentChunkName":"component---src-components-public-workflows-single-workflow-index-tsx","path":"/ready-made-workflow-library/transcribe-images-in-bulk","result":{"pageContext":{"result":{"workflow":{"id":70,"name":"Transcribe images in bulk","status":"DRAFT","started_at":"1645534649460","frequency":"","created_at":"1645542209165","updated_at":"1645542209165","description":"Extract text from a list of images using AI and OCR, perfect for transcribing menus, signs or image based pdf documents.","meta_title":"Transcribe a list of images using OCR at scale - Hexomatic workflow","meta_description":"

Do you have a list of images containing important text you need to capture?

\n

With Hexomatic you can provide a list of image URLs, and extract the text for each using AI and OCR, perfect for transcribing menus, signs or image based pdf documents in a convenient CSV or Google Sheet format - no 3rd party services or manual checking required

\n

This workflow taps into our AI OCR automation which can detect and recognize text at scale.

","image":"https://storage.googleapis.com/hexomatic-automation-icons/public-workflows-illustrations/Transcribe%20images%20in%20bulk.jpg","categories":[{"id":2,"name":"Marketing"}],"steps":[{"id":285,"setting":"{\"automation_id\":47,\"dynamic_settings\":{\"keys\":[{\"key\":null,\"settings\":{\"type\":\"Structured data\",\"columns\":[],\"storage\":null,\"jsonKeys\":[],\"inputType\":\"MANUAL_ADD_TYPE\",\"uploadedFiles\":[],\"workflowUploadId\":null},\"inputValue\":[\"https://cdn.pixabay.com/photo/2014/09/14/23/12/chalkboard-445958_1280.jpg\"]}]},\"output_keys_data\":[\"_data_input\"],\"predefined_settings\":null,\"integration_settings\":null,\"output_keys_data_with_types\":\"{\\\"_data_input\\\":\\\"any\\\"}\"}","index":0,"created_at":"1631606440232","updated_at":null,"automation":{"id":47,"name":"Data input","url":"input","meta_title":"Data Input | Hexomatic","meta_description":"Use our data input automation as a starting point for your workflow. Provide a list of URLs or text files as input for scraping recipes or automation.","short_description":"Provide your workflow with a text or file-based input","long_description":"Provide a list of URLs, text, or TXT/CSV files inside your workflow as input for scraping recipes or automation.\n
The Data Input automation enables you to provide data as a starting point for your workflow.\n
**We currently support four types of data inputs:**\n> * File upload - Lets you upload CSV, TXT, IMAGE, PDF, AUDIO or JSON files.\n> * File URL - Lets you specify the URL of a CSV and TXT file.\n> * Manual paste - Lets you copy paste a list of URLs or keywords and iterate through each in your workflow. You can also paste blocks of text.\n
\n\n**You can then add additional automations to perform different work tasks for each URL, Keyword or data provided in the data input.**\n> * Supported image formats include: .jpeg, .png8, .png24, .png, .gif, .bmp, .webp, .raw, .ico, .jpg.\n> * Supported audio formats include: WAV, MP3, FLAC.","long_description_details":" ","has_source":null,"icon_url":"https://storage.googleapis.com/hexomatic-automation-icons/data-input.svg"}},{"id":286,"setting":"{\"source\":{\"source_csv\":false,\"source_txt\":false},\"automation_id\":91,\"dynamic_settings\":{\"keys\":[{\"key\":\"_data_input\",\"settings\":{\"language\":\"en\"},\"inputValue\":null}]},\"output_keys_data\":[\"_data_input\",\"_text_from_image\"],\"predefined_settings\":null,\"integration_settings\":null,\"output_keys_data_with_types\":\"{\\\"_data_input\\\":\\\"any\\\",\\\"_text_from_image\\\":\\\"text\\\"}\"}","index":1,"created_at":"1631606440232","updated_at":null,"automation":{"id":91,"name":"AI Image OCR","url":"ai-optical-character-recognition-ocr","meta_title":"Image Text Extractor | AI Image Text Extractor","meta_description":"Extract texts from images via Google Vision AI! A number of formats are supported, including .jpeg, .png8, .png24, .png, .gif, .bmp, .webp, .raw, .ico, .jpg.","short_description":"Extract texts from images via Google Vision AI.","long_description":"This automation taps into Google Vision AI, and can detect and extract texts on autopilot. A number of formats are supported, including .jpeg, .png8, .png24, .png, .gif, .bmp, .webp, .raw, .ico, .jpg.","long_description_details":"It is often necessary to make digital data editable. For example, invoices, receipts or bank statements are usually in image format. In these cases, OCR software can come to rescue.\n
Our Hexomatic AI Image OCR automation taps into Google Vision AI, and can detect and extract texts on autopilot. A number of formats are supported, including .jpeg, .png8, .png24, .png, .gif, .bmp, .webp, .raw, .ico, .jpg.\n
**Different ways to use our AI Image OCR automation:**\n
\n> * Via Data input automation (using the List of inputs option) to extract texts from a list of image URLs.\n> * Via Data input automation (using the Upload file / CSV file option) to extract texts from a list of image URLs in a local CSV file.\n
\n\n**How to use our AI Image OCR automation via Data input:**\n
Step 1: Create a blank workflow and select Data input as the starting point.\nStep 2: Open the AI Image OCR automation, selecting Data input as the source. Then, select the language from the list.\nStep 3: Click continue to run or schedule the workflow.","has_source":null,"icon_url":"https://storage.googleapis.com/hexomatic-automation-icons/text-from-image.svg"}}],"tags":["Marketing"]},"prevPath":"/ready-made-workflow-library/scrape-yelp-search-results","nextPath":"/ready-made-workflow-library/find-b2b-leads-from-google-maps"}}},"staticQueryHashes":["3915125517"]}