add config options

frigate/config/camera/camera.py

@@ -19,6 +19,7 @@ from frigate.util.builtin import (
 
 from ..base import FrigateBaseModel
 from ..classification import (
+    AudioTranscriptionConfig,
     CameraFaceRecognitionConfig,
     CameraLicensePlateRecognitionConfig,
 )
@@ -56,6 +57,9 @@ class CameraConfig(FrigateBaseModel):
     audio: AudioConfig = Field(
         default_factory=AudioConfig, title="Audio events configuration."
     )
+    audio_transcription: AudioTranscriptionConfig = Field(
+        default_factory=AudioTranscriptionConfig, title="Audio transcription config."
+    )
     birdseye: BirdseyeCameraConfig = Field(
         default_factory=BirdseyeCameraConfig, title="Birdseye camera configuration."
     )

frigate/config/camera/updater.py

@@ -12,6 +12,7 @@ class CameraConfigUpdateEnum(str, Enum):
     """Supported camera config update types."""
 
     audio = "audio"
+    audio_transcription = "audio_transcription"
     birdseye = "birdseye"
     detect = "detect"
     enabled = "enabled"
@@ -74,6 +75,8 @@ class CameraConfigUpdateSubscriber:
 
         if update_type == CameraConfigUpdateEnum.audio:
             config.audio = updated_config
+        if update_type == CameraConfigUpdateEnum.audio_transcription:
+            config.audio_transcription = updated_config
         elif update_type == CameraConfigUpdateEnum.birdseye:
             config.birdseye = updated_config
         elif update_type == CameraConfigUpdateEnum.detect:

frigate/config/classification.py

@@ -19,11 +19,32 @@ class SemanticSearchModelEnum(str, Enum):
     jinav2 = "jinav2"
 
 
-class LPRDeviceEnum(str, Enum):
+class EnrichmentsDeviceEnum(str, Enum):
     GPU = "GPU"
     CPU = "CPU"
 
 
+class AudioTranscriptionConfig(FrigateBaseModel):
+    enabled: bool = Field(default=False, title="Enable audio transcription.")
+    language: str = Field(
+        default="en",
+        title="Language abbreviation to use for audio event transcription/translation.",
+    )
+    device: Optional[EnrichmentsDeviceEnum] = Field(
+        default=EnrichmentsDeviceEnum.CPU,
+        title="The device used for license plate recognition.",
+    )
+    model_size: str = Field(
+        default="small", title="The size of the embeddings model used."
+    )
+    enabled_in_config: Optional[bool] = Field(
+        default=None, title="Keep track of original state of camera."
+    )
+    live_enabled: Optional[bool] = Field(
+        default=False, title="Enable live transcriptions."
+    )
+
+
 class BirdClassificationConfig(FrigateBaseModel):
     enabled: bool = Field(default=False, title="Enable bird classification.")
     threshold: float = Field(
@@ -144,8 +165,8 @@ class CameraFaceRecognitionConfig(FrigateBaseModel):
 
 class LicensePlateRecognitionConfig(FrigateBaseModel):
     enabled: bool = Field(default=False, title="Enable license plate recognition.")
-    device: Optional[LPRDeviceEnum] = Field(
+    device: Optional[EnrichmentsDeviceEnum] = Field(
-        default=LPRDeviceEnum.CPU,
+        default=EnrichmentsDeviceEnum.CPU,
         title="The device used for license plate recognition.",
     )
     model_size: str = Field(

frigate/config/config.py

@@ -54,6 +54,7 @@ from .camera.snapshots import SnapshotsConfig
 from .camera.timestamp import TimestampStyleConfig
 from .camera_group import CameraGroupConfig
 from .classification import (
+    AudioTranscriptionConfig,
     ClassificationConfig,
     FaceRecognitionConfig,
     LicensePlateRecognitionConfig,
@@ -419,6 +420,9 @@ class FrigateConfig(FrigateBaseModel):
     )
 
     # Classification Config
+    audio_transcription: AudioTranscriptionConfig = Field(
+        default_factory=AudioTranscriptionConfig, title="Audio transcription config."
+    )
     classification: ClassificationConfig = Field(
         default_factory=ClassificationConfig, title="Object classification config."
     )
@@ -472,6 +476,7 @@ class FrigateConfig(FrigateBaseModel):
         global_config = self.model_dump(
             include={
                 "audio": ...,
+                "audio_transcription": ...,
                 "birdseye": ...,
                 "face_recognition": ...,
                 "lpr": ...,
@@ -528,6 +533,7 @@ class FrigateConfig(FrigateBaseModel):
             allowed_fields_map = {
                 "face_recognition": ["enabled", "min_area"],
                 "lpr": ["enabled", "expire_time", "min_area", "enhancement"],
+                "audio_transcription": ["enabled", "live_enabled"],
             }
 
             for section in allowed_fields_map:
@@ -609,6 +615,9 @@ class FrigateConfig(FrigateBaseModel):
             # set config pre-value
             camera_config.enabled_in_config = camera_config.enabled
             camera_config.audio.enabled_in_config = camera_config.audio.enabled
+            camera_config.audio_transcription.enabled_in_config = (
+                camera_config.audio_transcription.enabled
+            )
             camera_config.record.enabled_in_config = camera_config.record.enabled
             camera_config.notifications.enabled_in_config = (
                 camera_config.notifications.enabled