🗣
Make Spoken Audio From Text
Creates an audio file from text, using text-to-speech.
Creates an audio file from text, using text-to-speech.
Gets text from the provided PDF file. Input Rich text, File, Image, URL, Evernote note, PDF, Text Result Text, Rich text
Prompts to share the input using action extensions and sharing extensions provided by other apps.
Splits the input document by creating a PDF for each page.
Creates images from the pages in the PDF passed into the action.
Scans a QR code or bar code using the camera, and returns the text/URL that is found.
Passes the specific location to the next action (or as a magic variable). Result Location Requires Access to your location
Converts the rich text passed as input to Markdown text (comparable to Aaron Swartz's html2text script).
Takes the inputted Markdown and turns it into rich text, which can then be converted to other formats.
Converts the rich text passed as input to HTML text.
Takes the inputted HTML and turns it into rich text, which can then be converted to other formats.
Makes a PDF out of the input. The resulting PDF can optionally include a quarter-inch margin for better printing.
Gets images from the result of the previous action. For example, this action can get the album art of a song, or all the images on a web page.
Given a list of images, this action returns the images that match the given criteria.
Extracts information from an image, including album, width, heigh, date taken, media type, photo type, whether it’s a screenshot, location, duration, frame rate, orientation, camera make, camera model, metadata dictionary, whether it’s hidden, whether it’s a favorite, its name, and more.
Converts the images passed into the action to the specified image format.
Reverses the direction of images either horizontally or vertically.
Turns an image clockwise by a particular number of degrees.
Prompts to share the input using action extensions and sharing extensions provided by other apps.
Returns text from the previous action's output. For example, this action can get the name of a photo or song, or the text of a web page.
Shows the definition of the word passed into the action.
Transcribes what you say aloud into text and passes the result to the next action.
Searches text passed into the action for matches to a regular expression.
Separates text passed into the action into a list.
Replaces some text passed into the action with other text.
Gets the text that matched a particular capture group or all of the capture groups from the output of a Match Text action.
Changes the case of the text passed into the action to UPPERCASE, lowercase, or Title Case.
Autocorrects the spelling of text passed into the action.