OPENAI - REALTIME SPEECH-TO-TEXT (FRONT-END DESKTOP & NATIVE MOBILE) ================================================================

ELEMENT DESCRIPTION
----------------------------------
 OPENAI - REALTIME SPEECH-TO-TEXT (FRONT-END DESKTOP & NATIVE MOBILE) enables real-time speech-to-text from a pre-selected language.

STEP-BY-STEP SETUP
--------------------------------
 0) Register on OpenAI and get your OPEN AI API KEY.

 1) Register on plugins.wiseable.io. Create a new Credential which associates your BUBBLE APP URL and your AZURE AI SPEECH RESOURCE KEY.
  The registration service will generate your PUBLIC ACCESS KEY. This key serves as a secure proxy for your real API key. It allows your application to communicate with the service without exposing your real API key. Since this PUBLIC ACCESS KEY is explicitly tied to your registered BUBBLE APP URL, it can only be used from that domain, ensuring that even if the key is publicly visible, it remains safe and cannot be misused by unauthorized sources.

 2) In the Plugin Settings, enter your PUBLIC ACCESS KEY generated at the previous step and the SPEECH REGION.

 3) Add the OPENAI - REALTIME SPEECH-TO-TEXT (FRONT-END DESKTOP & NATIVE MOBILE) to the page on which Speech to Text must be performed and configure its properties.

 FIELDS :
 - RESULT TYPE : Must always be set to SPEECH TRANSCRIPTION (OPENAI).
 - MODEL : Transcription model. Valid values: gpt-4o-transcribe | gpt-4o-mini-transcribe
 - LANGUAGE CODE : ISO-639-1 code such as en. See https://github.com/openai/whisper#available-models-and-languages
 - NOISE REDUCTION : Optional noise reduction that runs before VAD and turn detection. Valid values: near_field | far_field

 4) Integrate the logic into your application using the following OPENAI - REALTIME SPEECH-TO-TEXT (FRONT-END DESKTOP & NATIVE MOBILE), states and actions:

 EVENTS :
 - TRANSCRIPT CHANGED : Event triggered when the value of the transcribed text has changed.
 - ERROR : Event triggered when an error occurs.

 EXPOSED STATES:
 Use any element able to show/process the data of interest (such as a Group with a Text field) stored within the result of the following states of the OPENAI - REALTIME SPEECH-TO-TEXT (FRONT-END DESKTOP & NATIVE MOBILE) element :
 - TRANSCRIPT : Returns the list of zero-indexed transcript.
 - IS LISTENING : Boolean set to yes when transcription is in progress, otherwise set to no.
 - ERROR : Error message upon Error event trigger

 ELEMENT ACTIONS - TRIGGERED IN WORKFLOW:
   - START TRANSCRIPTION : Start Transcription.
   - STOP TRANSCRIPTION : Stop Transcription.

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

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

N/A

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.