Closed n41tik closed 1 week ago
This pull request implements audio transcription using Whisper API and SOAP note generation using Jan AI. It also simplifies the user interface by removing audio output device selection and adds configuration options for the APIs used.
sequenceDiagram
actor User
participant Browser
participant WhisperAPI as Whisper API
participant JanAI as Jan AI
User->>Browser: Click Record
Browser->>User: Record audio
User->>Browser: Click Stop
Browser->>WhisperAPI: Send audio for transcription
WhisperAPI-->>Browser: Return transcribed text
Browser->>JanAI: Send transcribed text for SOAP note generation
JanAI-->>Browser: Return SOAP notes
Browser->>User: Display SOAP notes
journey
title User journey for generating SOAP notes
section Recording Audio
User: 1: Click Record
User: 2: Speak into microphone
User: 3: Click Stop
section Transcription and SOAP Note Generation
System: 1: Transcribe audio using Whisper API
System: 2: Generate SOAP notes using Jan AI
section Displaying Results
User: 1: View generated SOAP notes
Change | Details | Files |
---|---|---|
Implement audio transcription using Whisper API |
|
index.js |
Implement SOAP note generation using Jan AI |
|
index.js index.html |
Simplify user interface by removing audio output device selection |
|
index.js index.html |
Add configuration management for API settings |
|
index.js index.html |
Update UI to support new functionalities |
|
index.html |
@sourcery-ai review
Description:
Summary by Sourcery
Integrate Whisper and JAN AI to enable audio transcription and SOAP note generation from recorded audio. Enhance the user interface with a configuration section for setting service parameters and a toggle button for managing its visibility.
New Features:
Enhancements: