Webinar

November 3rd, 2021 12:00 PM EDT
Automation for Field Services & DistributionNovember 3rd, 2021 12:00 PM EDT
Learn how creating a digital workforce can improve your supply chain processes!

Detect Face

Detect facial attributes in the image

Arguments

Argument Type Default value Description
image_filestr, NoneNone
image_urlstr, NoneNone
face_attributesstr, NoneNone
face_landmarksboolFalse
recognition_modelstrrecognition_02
json_filestr, NoneNone
param image_file:
 filepath of image file
param image_url:
 URI to image, if given will be used instead of image_file
param face_attributes:
 comma separated list of attributes, for example. "age,gender,smile"
param face_landmarks:
 return face landmarks of the detected faces or not. The default value is False
param recognition_model:
 model used by Azure to detech faces, options are "recognition_01" or "recognition_02", default is "recognition_02"
param json_file:
 filepath to write results into
return:analysis in json format

Read more about face_attributes at Face detection explained:

  • age
  • gender
  • smile
  • facialHair
  • headPose
  • glasses
  • emotion
  • hair
  • makeup
  • accessories
  • blur
  • exposure
  • nouse

Detect Language

Detect languages in the given text

Arguments

Argument Type Default value Description
textstrnull
json_filestr, NoneNone
param text:A UTF-8 text string
param json_file:
 filepath to write results into
return:analysis in json format

Find Entities

Detect entities in the given text

Arguments

Argument Type Default value Description
textstrnull
languagestr, NoneNone
json_fileNone
param text:A UTF-8 text string
param language:if input language is known
param json_file:
 filepath to write results into
return:analysis in json format

Init Computer Vision Service

Initialize Azure Computer Vision

Arguments

Argument Type Default value Description
regionstr, NoneNone
use_robocloud_vaultboolFalse
param region:identifier for service region
param use_robocloud_vault:
 use secret stored into Robocorp Vault

Init Face Service

Initialize Azure Face

Arguments

Argument Type Default value Description
regionstr, NoneNone
use_robocloud_vaultboolFalse
param region:identifier for service region
param use_robocloud_vault:
 use secret stored into Robocorp Vault

Init Speech Service

Initialize Azure Speech

Arguments

Argument Type Default value Description
regionstr, NoneNone
use_robocloud_vaultboolFalse
param region:identifier for service region
param use_robocloud_vault:
 use secret stored into Robocorp Vault

Init Text Analytics Service

Initialize Azure Text Analyticts

Arguments

Argument Type Default value Description
regionstr, NoneNone
use_robocloud_vaultboolFalse
param region:identifier for service region
param use_robocloud_vault:
 use secret stored into Robocorp Vault

Key Phrases

Detect key phrases in the given text

Arguments

Argument Type Default value Description
textstrnull
languagestr, NoneNone
json_filestr, NoneNone
param text:A UTF-8 text string
param language:if input language is known
param json_file:
 filepath to write results into
return:analysis in json format

List Supported Voices

List supported voices for Azure API Speech Services.

Arguments

Argument Type Default value Description
localestr, NoneNone
neural_onlyboolFalse
json_filestr, NoneNone
param locale:list only voices specific to locale, by default return all voices
param neural_only:
 True if only neural voices should be returned, False by default
param json_file:
 filepath to write results into
return:voices in json

Available voice selection might differ between regions.

Sentiment Analyze

Analyze sentiments in the given text

Arguments

Argument Type Default value Description
textstrnull
languagestr, NoneNone
json_filestr, NoneNone
param text:A UTF-8 text string
param language:if input language is known
param json_file:
 filepath to write results into
return:analysis in json format

Set Robocloud Vault

Set Robocorp Vault name

Arguments

Argument Type Default value Description
vault_namenull
param vault_name:
 Robocorp Vault name

Text To Speech

Synthesize speech synchronously

Arguments

Argument Type Default value Description
textstrnull
languagestren-US
namestren-US-AriaRUS
genderstrFEMALE
encodingstrMP3
neural_voice_styleAny, NoneNone
target_filestrsynthesized.mp3
param text:input text to synthesize
param language:voice language, defaults to "en-US"
param name:voice name, defaults to "en-US-AriaRUS"
param gender:voice gender, defaults to "FEMALE"
param encoding:result encoding type, defaults to "MP3"
param neural_voice_style:
 if given then neural voice is used, example style. "cheerful"
param target_file:
 save synthesized output to file, defaults to "synthesized.mp3"
return:synthesized output in bytes

Neural voices are only supported for Speech resources created in East US, South East Asia, and West Europe regions.

Vision Analyze

Identify features in the image

Arguments

Argument Type Default value Description
image_filestr, NoneNone
image_urlstr, NoneNone
visual_featuresstr, NoneNone
json_filestr, NoneNone
param image_file:
 filepath of image file
param image_url:
 URI to image, if given will be used instead of image_file
param visual_features:
 comma separated list of features, for example. "Categories,Description,Color"
param json_file:
 filepath to write results into
return:analysis in json format

See Computer Vision API for valid feature names and their explanations:

  • Adult
  • Brands
  • Categories
  • Color
  • Description
  • Faces
  • ImageType
  • Objects
  • Tags

Vision Describe

Describe image with tags and captions

Arguments

Argument Type Default value Description
image_filestr, NoneNone
image_urlstr, NoneNone
json_filestr, NoneNone
param image_file:
 filepath of image file
param image_url:
 URI to image, if given will be used instead of image_file
param json_file:
 filepath to write results into
return:analysis in json format

Vision Detect Objects

Detect objects in the image

Arguments

Argument Type Default value Description
image_filestr, NoneNone
image_urlstr, NoneNone
json_filestr, NoneNone
param image_file:
 filepath of image file
param image_url:
 URI to image, if given will be used instead of image_file
param json_file:
 filepath to write results into
return:analysis in json format

Vision Ocr

Optical Character Recognition (OCR) detects text in an image

Arguments

Argument Type Default value Description
image_filestr, NoneNone
image_urlstr, NoneNone
json_filestr, NoneNone
param image_file:
 filepath of image file
param image_url:
 URI to image, if given will be used instead of image_file
param json_file:
 filepath to write results into
return:analysis in json format