googleapis · parthea · Apr 12, 2025 · Apr 3, 2025 · Apr 3, 2025
@@ -45,6 +45,7 @@
 
 from google.longrunning import operations_pb2  # type: ignore
 from google.protobuf import field_mask_pb2  # type: ignore
+from google.protobuf import timestamp_pb2  # type: ignore
 
 from google.cloud.speech_v1p1beta1.services.adaptation import pagers
 from google.cloud.speech_v1p1beta1.types import cloud_speech_adaptation, resource
@@ -75,6 +76,12 @@ class AdaptationAsyncClient:
     _DEFAULT_ENDPOINT_TEMPLATE = AdaptationClient._DEFAULT_ENDPOINT_TEMPLATE
     _DEFAULT_UNIVERSE = AdaptationClient._DEFAULT_UNIVERSE
 
+    crypto_key_path = staticmethod(AdaptationClient.crypto_key_path)
+    parse_crypto_key_path = staticmethod(AdaptationClient.parse_crypto_key_path)
+    crypto_key_version_path = staticmethod(AdaptationClient.crypto_key_version_path)
+    parse_crypto_key_version_path = staticmethod(
+        AdaptationClient.parse_crypto_key_version_path
+    )
     custom_class_path = staticmethod(AdaptationClient.custom_class_path)
     parse_custom_class_path = staticmethod(AdaptationClient.parse_custom_class_path)
     phrase_set_path = staticmethod(AdaptationClient.phrase_set_path)

@@ -62,6 +62,7 @@
 
 from google.longrunning import operations_pb2  # type: ignore
 from google.protobuf import field_mask_pb2  # type: ignore
+from google.protobuf import timestamp_pb2  # type: ignore
 
 from google.cloud.speech_v1p1beta1.services.adaptation import pagers
 from google.cloud.speech_v1p1beta1.types import cloud_speech_adaptation, resource
@@ -196,6 +197,56 @@ def transport(self) -> AdaptationTransport:
         """
         return self._transport
 
+    @staticmethod
+    def crypto_key_path(
+        project: str,
+        location: str,
+        key_ring: str,
+        crypto_key: str,
+    ) -> str:
+        """Returns a fully-qualified crypto_key string."""
+        return "projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}".format(
+            project=project,
+            location=location,
+            key_ring=key_ring,
+            crypto_key=crypto_key,
+        )
+
+    @staticmethod
+    def parse_crypto_key_path(path: str) -> Dict[str, str]:
+        """Parses a crypto_key path into its component segments."""
+        m = re.match(
+            r"^projects/(?P<project>.+?)/locations/(?P<location>.+?)/keyRings/(?P<key_ring>.+?)/cryptoKeys/(?P<crypto_key>.+?)$",
+            path,
+        )
+        return m.groupdict() if m else {}
+
+    @staticmethod
+    def crypto_key_version_path(
+        project: str,
+        location: str,
+        key_ring: str,
+        crypto_key: str,
+        crypto_key_version: str,
+    ) -> str:
+        """Returns a fully-qualified crypto_key_version string."""
+        return "projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}/cryptoKeyVersions/{crypto_key_version}".format(
+            project=project,
+            location=location,
+            key_ring=key_ring,
+            crypto_key=crypto_key,
+            crypto_key_version=crypto_key_version,
+        )
+
+    @staticmethod
+    def parse_crypto_key_version_path(path: str) -> Dict[str, str]:
+        """Parses a crypto_key_version path into its component segments."""
+        m = re.match(
+            r"^projects/(?P<project>.+?)/locations/(?P<location>.+?)/keyRings/(?P<key_ring>.+?)/cryptoKeys/(?P<crypto_key>.+?)/cryptoKeyVersions/(?P<crypto_key_version>.+?)$",
+            path,
+        )
+        return m.groupdict() if m else {}
+
     @staticmethod
     def custom_class_path(
         project: str,

@@ -80,6 +80,12 @@ class SpeechAsyncClient:
     _DEFAULT_ENDPOINT_TEMPLATE = SpeechClient._DEFAULT_ENDPOINT_TEMPLATE
     _DEFAULT_UNIVERSE = SpeechClient._DEFAULT_UNIVERSE
 
+    crypto_key_path = staticmethod(SpeechClient.crypto_key_path)
+    parse_crypto_key_path = staticmethod(SpeechClient.parse_crypto_key_path)
+    crypto_key_version_path = staticmethod(SpeechClient.crypto_key_version_path)
+    parse_crypto_key_version_path = staticmethod(
+        SpeechClient.parse_crypto_key_version_path
+    )
     custom_class_path = staticmethod(SpeechClient.custom_class_path)
     parse_custom_class_path = staticmethod(SpeechClient.parse_custom_class_path)
     phrase_set_path = staticmethod(SpeechClient.phrase_set_path)

@@ -200,6 +200,56 @@ def transport(self) -> SpeechTransport:
         """
         return self._transport
 
+    @staticmethod
+    def crypto_key_path(
+        project: str,
+        location: str,
+        key_ring: str,
+        crypto_key: str,
+    ) -> str:
+        """Returns a fully-qualified crypto_key string."""
+        return "projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}".format(
+            project=project,
+            location=location,
+            key_ring=key_ring,
+            crypto_key=crypto_key,
+        )
+
+    @staticmethod
+    def parse_crypto_key_path(path: str) -> Dict[str, str]:
+        """Parses a crypto_key path into its component segments."""
+        m = re.match(
+            r"^projects/(?P<project>.+?)/locations/(?P<location>.+?)/keyRings/(?P<key_ring>.+?)/cryptoKeys/(?P<crypto_key>.+?)$",
+            path,
+        )
+        return m.groupdict() if m else {}
+
+    @staticmethod
+    def crypto_key_version_path(
+        project: str,
+        location: str,
+        key_ring: str,
+        crypto_key: str,
+        crypto_key_version: str,
+    ) -> str:
+        """Returns a fully-qualified crypto_key_version string."""
+        return "projects/{project}/locations/{location}/keyRings/{key_ring}/cryptoKeys/{crypto_key}/cryptoKeyVersions/{crypto_key_version}".format(
+            project=project,
+            location=location,
+            key_ring=key_ring,
+            crypto_key=crypto_key,
+            crypto_key_version=crypto_key_version,
+        )
+
+    @staticmethod
+    def parse_crypto_key_version_path(path: str) -> Dict[str, str]:
+        """Parses a crypto_key_version path into its component segments."""
+        m = re.match(
+            r"^projects/(?P<project>.+?)/locations/(?P<location>.+?)/keyRings/(?P<key_ring>.+?)/cryptoKeys/(?P<crypto_key>.+?)/cryptoKeyVersions/(?P<crypto_key_version>.+?)$",
+            path,
+        )
+        return m.groupdict() if m else {}
+
     @staticmethod
     def custom_class_path(
         project: str,

@@ -211,7 +211,9 @@ class StreamingRecognitionConfig(proto.Message):
 
             The ``single_utterance`` field can only be used with
             specified models, otherwise an error is thrown. The
-            ``model`` field in [``RecognitionConfig``][] must be set to:
+            ``model`` field in
+            [RecognitionConfig][google.cloud.speech.v1p1beta1.RecognitionConfig]
+            must be set to:
 
             -  ``command_and_search``
             -  ``phone_call`` AND additional field
@@ -360,7 +362,7 @@ class RecognitionConfig(proto.Message):
             documentation. When speech adaptation is set it supersedes
             the ``speech_contexts`` field.
         transcript_normalization (google.cloud.speech_v1p1beta1.types.TranscriptNormalization):
-            Use transcription normalization to
+            Optional. Use transcription normalization to
             automatically replace parts of the transcript
             with phrases of your choosing. For
             StreamingRecognize, this normalization only
@@ -409,7 +411,7 @@ class RecognitionConfig(proto.Message):
         enable_speaker_diarization (bool):
             If 'true', enables speaker detection for each recognized
             word in the top alternative of the recognition result using
-            a speaker_tag provided in the WordInfo. Note: Use
+            a speaker_label provided in the WordInfo. Note: Use
             diarization_config instead.
         diarization_speaker_count (int):
             If set, specifies the estimated number of speakers in the
@@ -576,9 +578,12 @@ class AudioEncoding(proto.Enum):
                 file being used.
             WEBM_OPUS (9):
                 Opus encoded audio frames in WebM container
-                (`OggOpus <https://wiki.xiph.org/OggOpus>`__).
+                (`WebM <https://www.webmproject.org/docs/container/>`__).
                 ``sample_rate_hertz`` must be one of 8000, 12000, 16000,
                 24000, or 48000.
+            ALAW (10):
+                8-bit samples that compand 13-bit audio
+                samples using G.711 PCMU/a-law.
         """
         ENCODING_UNSPECIFIED = 0
         LINEAR16 = 1
@@ -590,6 +595,7 @@ class AudioEncoding(proto.Enum):
         SPEEX_WITH_HEADER_BYTE = 7
         MP3 = 8
         WEBM_OPUS = 9
+        ALAW = 10
 
     encoding: AudioEncoding = proto.Field(
         proto.ENUM,
@@ -696,7 +702,7 @@ class SpeakerDiarizationConfig(proto.Message):
         enable_speaker_diarization (bool):
             If 'true', enables speaker detection for each recognized
             word in the top alternative of the recognition result using
-            a speaker_tag provided in the WordInfo.
+            a speaker_label provided in the WordInfo.
         min_speaker_count (int):
             Minimum number of speakers in the
             conversation. This range gives you more
@@ -1042,6 +1048,10 @@ class RecognizeResponse(proto.Message):
         request_id (int):
             The ID associated with the request. This is a
             unique ID specific only to the given request.
+        using_legacy_models (bool):
+            Whether request used legacy asr models (was
+            not automatically migrated to use conformer
+            models).
     """
 
     results: MutableSequence["SpeechRecognitionResult"] = proto.RepeatedField(
@@ -1063,6 +1073,10 @@ class RecognizeResponse(proto.Message):
         proto.INT64,
         number=8,
     )
+    using_legacy_models: bool = proto.Field(
+        proto.BOOL,
+        number=9,
+    )
 
 
 class LongRunningRecognizeResponse(proto.Message):
@@ -1523,8 +1537,17 @@ class WordInfo(proto.Message):
             speaker within the audio. This field specifies which one of
             those speakers was detected to have spoken this word. Value
             ranges from '1' to diarization_speaker_count. speaker_tag is
-            set if enable_speaker_diarization = 'true' and only in the
-            top alternative.
+            set if enable_speaker_diarization = 'true' and only for the
+            top alternative. Note: Use speaker_label instead.
+        speaker_label (str):
+            Output only. A label value assigned for every unique speaker
+            within the audio. This field specifies which speaker was
+            detected to have spoken this word. For some models, like
+            medical_conversation this can be actual speaker role, for
+            example "patient" or "provider", but generally this would be
+            a number identifying a speaker. This field is only set if
+            enable_speaker_diarization = 'true' and only for the top
+            alternative.
     """
 
     start_time: duration_pb2.Duration = proto.Field(
@@ -1549,6 +1572,10 @@ class WordInfo(proto.Message):
         proto.INT32,
         number=5,
     )
+    speaker_label: str = proto.Field(
+        proto.STRING,
+        number=6,
+    )
 
 
 class SpeechAdaptationInfo(proto.Message):