- Create account on Google Cloud.
- Enable API’s that You need to use (Image AI, Text To Speech, Speech to Text, Document AI, Cloud Storage).
- Create Processor from cloud Console(Needed for Document AI)
- Create Service Account. - Add Credentials to IAM.
- Enable billing (needed, but You get from google trial period and free calls).
- Download private key as JSON
Hint for Text To Speech: You can specify voices and Languages from
https://cloud.google.com/text-to-speech/docs/voices You need to copy/paste Language Code and Name without “”. ex: LanguageCode: en-US and Name: en-US-Neural2-H
Speech to Text works only with “gs” links. First create bucket or upload audio file to storage, get “gs” link(ex. gs://bucket/filename).
If enabled, Speech-to-Text will attempt to detect profane words and return only the first letter followed by asterisks in the transcript (for example, f***). If this field is set to false or not set, Speech-to-Text will not attempt to filter profanities.
Hint for Document AI:
You need to create Processor with “Document OCR” option.
Location is a spec for where Your Site will OCR document
Document AI supports file format:
.pdf, .gif, .tiff, .tif, .jpg, .jpeg, .png, .bmp, .webp
https://cloud.google.com/document-ai/docs/file-typesHint for Text To Speech: You can specify voices and Languages from
https://cloud.google.com/text-to-speech/docs/voices You need to copy/paste Language Code and Name without “”. ex: LanguageCode: en-US and Name: en-US-Neural2-H
Hint for Image AI:
Google has photo size restrictions
https://cloud.google.com/vision/docs/supported-filesOpen the private key JSON file with a text editor, copy/paste the following parameters from your file to the Plugin settings:
- client_email
- project_id
- private_key, including the -----BEGIN PRIVATE KEY-----\n prefix and \n-----END PRIVATE KEY-----\n.
How it’s Work
Ez Google AI contains Actions, Specify trigger (button, event etc.) and start Plugin Action.
Demo:
https://eazycodedemo.bubbleapps.io/version-test/google_ai
Built on Bubble
