API Reference

All types use the ERP_ / UERP_ / FERP_ prefix and are Blueprint-accessible.

UERP_STTComponent

The Blueprint-friendly entry point. Add it to an actor (client-side).

Member	Kind	Description
Config	property FERP_STTConfig	Per-component STT configuration
bAutoStartListening	property bool	Start on BeginPlay
bAutoRegisterAudioConsumer	property bool	Auto-register with capture
StartListening()	function → bool	Begin capture + transcription
StopListening()	function	Stop and unregister
IsListening()	pure → bool	Currently listening?
SetConfig(NewConfig)	function	Update config at runtime
IsSTTReady()	pure → bool	Backend loaded and ready?
OnSTTResult	event FERP_STTResult	Fires for interim and final results
OnText	event FString	Final transcript text — for chaining

FERP_STTResult

Field	Type	Description
TranscribedText	FString	The recognized text
Confidence	float	0.0–1.0
bIsFinal	bool	Final vs. interim result
ProcessingTimeMs	float	Inference time

FERP_STTConfig

Field	Type	Description
LanguageCode	FString	e.g. en-US, fr-FR
bEnableInterimResults	bool	Emit partial results
MinConfidenceThreshold	float	Drop results below this

UERP_STTSubsystem

GameInstanceSubsystem owning the shared backend.

Member	Description
InitializeBackend(Config) → bool	Load the model
ShutdownBackend()	Unload
IsBackendInitialized() → bool	Ready state
GetModelInfo() → FString	Loaded model description

UERP_AudioCaptureSubsystem

Microphone capture, fanned out to consumers. Supports push-to-talk and mute via SetPushToTalkMode, SetPushToTalkActive, SetMuted.

IERP_STTBackend

Implement this to add a custom STT engine (e.g. Vosk, Moonshine), then select Custom as the backend in settings. Whisper is the bundled implementation (UERP_WhisperBackend).