diff --git a/frigate/config/classification.py b/frigate/config/classification.py
index 63e89421c..cbfe58597 100644
--- a/frigate/config/classification.py
+++ b/frigate/config/classification.py
@@ -163,6 +163,32 @@ class CameraSemanticSearchConfig(FrigateBaseModel):
     model_config = ConfigDict(extra="forbid", protected_namespaces=())
 
 
+class TriggerConfig(FrigateBaseModel):
+    enabled: bool = Field(default=True, title="Enable this trigger")
+    type: TriggerType = Field(default=TriggerType.DESCRIPTION, title="Type of trigger")
+    data: str = Field(title="Trigger content (text phrase or image ID)")
+    threshold: float = Field(
+        title="Confidence score required to run the trigger",
+        default=0.8,
+        gt=0.0,
+        le=1.0,
+    )
+    actions: List[TriggerAction] = Field(
+        default=[], title="Actions to perform when trigger is matched"
+    )
+
+    model_config = ConfigDict(extra="forbid", protected_namespaces=())
+
+
+class CameraSemanticSearchConfig(FrigateBaseModel):
+    triggers: Dict[str, TriggerConfig] = Field(
+        default={},
+        title="Trigger actions on tracked objects that match existing thumbnails or descriptions",
+    )
+
+    model_config = ConfigDict(extra="forbid", protected_namespaces=())
+
+
 class FaceRecognitionConfig(FrigateBaseModel):
     enabled: bool = Field(default=False, title="Enable face recognition.")
     model_size: str = Field(
diff --git a/frigate/events/audio.py b/frigate/events/audio.py
index 31b9a7f3c..d6fed826b 100644
--- a/frigate/events/audio.py
+++ b/frigate/events/audio.py
@@ -180,6 +180,24 @@ class AudioEventMaintainer(threading.Thread):
         )
         self.detection_publisher = DetectionPublisher(DetectionTypeEnum.audio.value)
 
+        if self.camera_config.audio_transcription.enabled_in_config:
+            # init the transcription processor for this camera
+            self.transcription_processor = AudioTranscriptionRealTimeProcessor(
+                config=self.config,
+                camera_config=self.camera_config,
+                requestor=self.requestor,
+                model_runner=self.audio_transcription_model_runner,
+                metrics=self.camera_metrics[self.camera_config.name],
+                stop_event=self.stop_event,
+            )
+
+            self.transcription_thread = threading.Thread(
+                target=self.transcription_processor.run,
+                name=f"{self.camera_config.name}_transcription_processor",
+                daemon=True,
+            )
+            self.transcription_thread.start()
+
         if self.camera_config.audio_transcription.enabled_in_config:
             # init the transcription processor for this camera
             self.transcription_processor = AudioTranscriptionRealTimeProcessor(