AI VOICE CONTROL FOR BUBBLE APP =================================

ELEMENT DESCRIPTION
----------------------------------
 AI VOICE CONTROL FOR BUBBLE APP allows users to control your app by triggering upon voice commands custom or backend workflows. Parameters may also be passed to customise workflows' behaviour.

STEP-BY-STEP SETUP
--------------------------------
 1) Implement the customs or backend workflows along with their parameters you wish to trigger via voice control. In the next steps, you will associate a VERB (workflow identifier) and optionally their associated NOUN values (workflow parameters).

 2) Add the AI VOICE CONTROL FOR BUBBLE APP ELEMENT on the page on which voice control must be performed and configure its properties.

 FIELDS :
 - LANGUAGE CODE : ISO 639-1 Language Code, e.g. en-US for American English. Leave empty for autodetection based on browser settings.
 - CONTINUOUS : Keep the microphone on until the stop action is triggered. Otherwise stops when no sound is detected.

 3) Create a workflow, triggered by a button for example, to invoke "START VOICE CONTROL". This action is used to start listening for voice commands.

 4) Integrate the logic into your application using the following AI VOICE CONTROL FOR BUBBLE APP, states and actions:

 EVENTS :
 - EVENT TO TRIGGER : Event triggered when user's speech matching a VERB has been detected.
 - ERROR : Event triggered when an error occurs.

 EXPOSED STATES:
 - VERB : Returns the most likely VERB detected from user's speech.
 - NOUN CATEGORY : List of detected NOUN CATEGORY.
 - NOUNS VALUES : List of detected NOUN VALUES.
 - IS LISTENING : Boolean set to yes when transcription is in progress, otherwise set to no.
 - ERROR : Error message upon Error event trigger
 - SET LANGUAGE : ISO 639-1 Language Code of the spoken language.

 ELEMENT ACTIONS - TRIGGERED IN WORKFLOW:
   - START VOICE CONTROL : Start Voice Control.
         - VERBS LIST : List of verbs each associated with a set of vocal commands. These commands are separated by the “|” character. The system will identify the most likely verb from the user’s speech and return it as the VERB state. This state can then be used to trigger the appropriate workflow.For example, the verb could be “addProduct”, and the associated vocal commands could be “Add product to basket” or “Put product to basket”.
Optionally, you can also set up a NOUNS LIST. This list will help the system detect specific words in the vocal command and return a NOUN value as a state. For instance, if the noun is a product name, the system will know which product to add to the basket.In summary, the system uses the VERB state to determine the action (like adding a product) and the NOUN state to specify the object of that action (like which product to add).
         - NOUNS LIST : List of noun categories, each associated with certain values. These values are separated by the “|” character and are meant to be identified within the user’s speech. These noun categories are typically linked with a verb to customize the workflow that the verb triggers. For instance, a category could be “product”, and its associated values could be “iPhone 14” or “Samsung S9”. These values are what the system looks for in the user’s speech. So, if the user mentions “iPhone 14”, the system can determine that the category is “product” and the value is “iPhone 14”. In essence, the system uses the noun categories and their values to further specify the action triggered by the verb state. In this case, not only does the system know to add a product (from the verb), but it also knows that the product to add is an “iPhone 14” (from the noun).
         - EXACT NOUN MATCHING  :  Enable to perform exact noun matching such as "iPhone 12". If disabled, loose matching will be used, such as "iPhone" or "12".
         - SENSITIVITY : Valid range from 0 to 1. The higher the threshold, the more accurate the user speech will have to be in order to trigger an EVENT TO TRIGGER event. .
   - STOP VOICE CONTROL : Stop Voice Control.

 5) Set as workflow start the event "EVENT TO TRIGGER", that will be triggered when user's speech matching a VERB has been detected within the configured SENSITIVITY. This workflow will be used to trigger  which custom or backend workflows to start.

 6) In the previously created workflow, create actions to start your custom or backend workflows upon EVENT TO TRIGGER EVENT, depending on your use case, and set as "ONLY WHEN" conditional "THIS VOICE CONTROL FOR BUBBLE APP's EVENT NAME IS <NAME OF YOUR CUSTOMER WORKFLOW>. The NOUN CATEGORIES and NOUN VALUES may also be passed to said workflows.

IMPLEMENTATION EXAMPLE
======================
Feel free to browse the app editor in the Service URL for an implementation example.

ADDITIONAL INFORMATION
======================

FIREFOX is not supported.

TROUBLESHOOTING
================
Any plugin related error will be posted to the the Logs tab, "Server logs" section of your App Editor.
 Make sure that "Plugin server side output" and "Plugin server side output" is selected in "Show Advanced".

> Server Logs Details: https://manual.bubble.io/core-resources/bubbles-interface/logs-tab#server-logs

PERFORMANCE CONSIDERATIONS
===========================
 N/A

QUESTIONS ?
===========
Contact us at [email protected] for any additional feature you would require or support question.