feat(v1beta1): add CustomVoiceParams (#215)

* feat: update v1beta1 proto

PiperOrigin-RevId: 409139454

Source-Link: googleapis/googleapis@7c10623

Source-Link: googleapis/googleapis-gen@48051eb
Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiNDgwNTFlYmFiZjk5MWFiY2RkY2IyNjg1Y2VmYzMzMWFlYTdmNTIwOCJ9

* 🦉 Updates from OwlBot

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
Co-authored-by: Anthonios Partheniou <partheniou@google.com>

google/cloud/texttospeech_v1beta1/__init__.py

@@ -18,6 +18,7 @@
 from .services.text_to_speech import TextToSpeechAsyncClient
 
 from .types.cloud_tts import AudioConfig
+from .types.cloud_tts import CustomVoiceParams
 from .types.cloud_tts import ListVoicesRequest
 from .types.cloud_tts import ListVoicesResponse
 from .types.cloud_tts import SynthesisInput
@@ -33,6 +34,7 @@
     "TextToSpeechAsyncClient",
     "AudioConfig",
     "AudioEncoding",
+    "CustomVoiceParams",
     "ListVoicesRequest",
     "ListVoicesResponse",
     "SsmlVoiceGender",

google/cloud/texttospeech_v1beta1/services/text_to_speech/async_client.py

@@ -45,6 +45,8 @@ class TextToSpeechAsyncClient:
     DEFAULT_ENDPOINT = TextToSpeechClient.DEFAULT_ENDPOINT
     DEFAULT_MTLS_ENDPOINT = TextToSpeechClient.DEFAULT_MTLS_ENDPOINT
 
+    model_path = staticmethod(TextToSpeechClient.model_path)
+    parse_model_path = staticmethod(TextToSpeechClient.parse_model_path)
     common_billing_account_path = staticmethod(
         TextToSpeechClient.common_billing_account_path
     )
@@ -180,12 +182,13 @@ async def list_voices(
                 language tag. If not specified, the API will return all
                 supported voices. If specified, the ListVoices call will
                 only return voices that can be used to synthesize this
-                language_code. E.g. when specifying "en-NZ", you will
-                get supported "en-NZ" voices; when specifying "no", you
-                will get supported "no-\*" (Norwegian) and "nb-\*"
-                (Norwegian Bokmal) voices; specifying "zh" will also get
-                supported "cmn-\*" voices; specifying "zh-hk" will also
-                get supported "yue-hk" voices.
+                language_code. E.g. when specifying ``"en-NZ"``, you
+                will get supported ``"en-NZ"`` voices; when specifying
+                ``"no"``, you will get supported ``"no-\*"`` (Norwegian)
+                and ``"nb-\*"`` (Norwegian Bokmal) voices; specifying
+                ``"zh"`` will also get supported ``"cmn-\*"`` voices;
+                specifying ``"zh-hk"`` will also get supported
+                ``"yue-hk"`` voices.
 
                 This corresponds to the ``language_code`` field
                 on the ``request`` instance; if ``request`` is provided, this

google/cloud/texttospeech_v1beta1/services/text_to_speech/client.py

@@ -156,6 +156,22 @@ def transport(self) -> TextToSpeechTransport:
         """
         return self._transport
 
+    @staticmethod
+    def model_path(project: str, location: str, model: str,) -> str:
+        """Returns a fully-qualified model string."""
+        return "projects/{project}/locations/{location}/models/{model}".format(
+            project=project, location=location, model=model,
+        )
+
+    @staticmethod
+    def parse_model_path(path: str) -> Dict[str, str]:
+        """Parses a model path into its component segments."""
+        m = re.match(
+            r"^projects/(?P<project>.+?)/locations/(?P<location>.+?)/models/(?P<model>.+?)$",
+            path,
+        )
+        return m.groupdict() if m else {}
+
     @staticmethod
     def common_billing_account_path(billing_account: str,) -> str:
         """Returns a fully-qualified billing_account string."""
@@ -360,12 +376,13 @@ def list_voices(
                 language tag. If not specified, the API will return all
                 supported voices. If specified, the ListVoices call will
                 only return voices that can be used to synthesize this
-                language_code. E.g. when specifying "en-NZ", you will
-                get supported "en-NZ" voices; when specifying "no", you
-                will get supported "no-\*" (Norwegian) and "nb-\*"
-                (Norwegian Bokmal) voices; specifying "zh" will also get
-                supported "cmn-\*" voices; specifying "zh-hk" will also
-                get supported "yue-hk" voices.
+                language_code. E.g. when specifying ``"en-NZ"``, you
+                will get supported ``"en-NZ"`` voices; when specifying
+                ``"no"``, you will get supported ``"no-\*"`` (Norwegian)
+                and ``"nb-\*"`` (Norwegian Bokmal) voices; specifying
+                ``"zh"`` will also get supported ``"cmn-\*"`` voices;
+                specifying ``"zh-hk"`` will also get supported
+                ``"yue-hk"`` voices.
 
                 This corresponds to the ``language_code`` field
                 on the ``request`` instance; if ``request`` is provided, this

google/cloud/texttospeech_v1beta1/types/__init__.py

@@ -15,6 +15,7 @@
 #
 from .cloud_tts import (
     AudioConfig,
+    CustomVoiceParams,
     ListVoicesRequest,
     ListVoicesResponse,
     SynthesisInput,
@@ -29,6 +30,7 @@
 
 __all__ = (
     "AudioConfig",
+    "CustomVoiceParams",
     "ListVoicesRequest",
     "ListVoicesResponse",
     "SynthesisInput",

google/cloud/texttospeech_v1beta1/types/cloud_tts.py

@@ -28,6 +28,7 @@
         "SynthesisInput",
         "VoiceSelectionParams",
         "AudioConfig",
+        "CustomVoiceParams",
         "SynthesizeSpeechResponse",
         "Timepoint",
     },
@@ -68,12 +69,12 @@ class ListVoicesRequest(proto.Message):
             language tag. If not specified, the API will return all
             supported voices. If specified, the ListVoices call will
             only return voices that can be used to synthesize this
-            language_code. E.g. when specifying "en-NZ", you will get
-            supported "en-NZ" voices; when specifying "no", you will get
-            supported "no-\*" (Norwegian) and "nb-\*" (Norwegian Bokmal)
-            voices; specifying "zh" will also get supported "cmn-\*"
-            voices; specifying "zh-hk" will also get supported "yue-hk"
-            voices.
+            language_code. E.g. when specifying ``"en-NZ"``, you will
+            get supported ``"en-NZ"`` voices; when specifying ``"no"``,
+            you will get supported ``"no-\*"`` (Norwegian) and
+            ``"nb-\*"`` (Norwegian Bokmal) voices; specifying ``"zh"``
+            will also get supported ``"cmn-\*"`` voices; specifying
+            ``"zh-hk"`` will also get supported ``"yue-hk"`` voices.
     """
 
     language_code = proto.Field(proto.STRING, number=1,)
@@ -210,11 +211,16 @@ class VoiceSelectionParams(proto.Message):
             not requirement; if a voice of the appropriate gender is not
             available, the synthesizer should substitute a voice with a
             different gender rather than failing the request.
+        custom_voice (google.cloud.texttospeech_v1beta1.types.CustomVoiceParams):
+            The configuration for a custom voice. If
+            [CustomVoiceParams.model] is set, the service will choose
+            the custom voice matching the specified configuration.
     """
 
     language_code = proto.Field(proto.STRING, number=1,)
     name = proto.Field(proto.STRING, number=2,)
     ssml_gender = proto.Field(proto.ENUM, number=3, enum="SsmlVoiceGender",)
+    custom_voice = proto.Field(proto.MESSAGE, number=4, message="CustomVoiceParams",)
 
 
 class AudioConfig(proto.Message):
@@ -272,6 +278,31 @@ class AudioConfig(proto.Message):
     effects_profile_id = proto.RepeatedField(proto.STRING, number=6,)
 
 
+class CustomVoiceParams(proto.Message):
+    r"""Description of the custom voice to be synthesized.
+
+    Attributes:
+        model (str):
+            Required. The name of the AutoML model that
+            synthesizes the custom voice.
+        reported_usage (google.cloud.texttospeech_v1beta1.types.CustomVoiceParams.ReportedUsage):
+            Optional. The usage of the synthesized audio
+            to be reported.
+    """
+
+    class ReportedUsage(proto.Enum):
+        r"""The usage of the synthesized audio. You must report your
+        honest and correct usage of the service as it's regulated by
+        contract and will cause significant difference in billing.
+        """
+        REPORTED_USAGE_UNSPECIFIED = 0
+        REALTIME = 1
+        OFFLINE = 2
+
+    model = proto.Field(proto.STRING, number=1,)
+    reported_usage = proto.Field(proto.ENUM, number=3, enum=ReportedUsage,)
+
+
 class SynthesizeSpeechResponse(proto.Message):
     r"""The message returned to the client by the ``SynthesizeSpeech``
     method.

tests/unit/gapic/texttospeech_v1beta1/test_text_to_speech.py

@@ -1193,8 +1193,32 @@ def test_text_to_speech_transport_channel_mtls_with_adc(transport_class):
             assert transport.grpc_channel == mock_grpc_channel
 
 
+def test_model_path():
+    project = "squid"
+    location = "clam"
+    model = "whelk"
+    expected = "projects/{project}/locations/{location}/models/{model}".format(
+        project=project, location=location, model=model,
+    )
+    actual = TextToSpeechClient.model_path(project, location, model)
+    assert expected == actual
+
+
+def test_parse_model_path():
+    expected = {
+        "project": "octopus",
+        "location": "oyster",
+        "model": "nudibranch",
+    }
+    path = TextToSpeechClient.model_path(**expected)
+
+    # Check that the path construction is reversible.
+    actual = TextToSpeechClient.parse_model_path(path)
+    assert expected == actual
+
+
 def test_common_billing_account_path():
-    billing_account = "squid"
+    billing_account = "cuttlefish"
     expected = "billingAccounts/{billing_account}".format(
         billing_account=billing_account,
     )
@@ -1204,7 +1228,7 @@ def test_common_billing_account_path():
 
 def test_parse_common_billing_account_path():
     expected = {
-        "billing_account": "clam",
+        "billing_account": "mussel",
     }
     path = TextToSpeechClient.common_billing_account_path(**expected)
 
@@ -1214,15 +1238,15 @@ def test_parse_common_billing_account_path():
 
 
 def test_common_folder_path():
-    folder = "whelk"
+    folder = "winkle"
     expected = "folders/{folder}".format(folder=folder,)
     actual = TextToSpeechClient.common_folder_path(folder)
     assert expected == actual
 
 
 def test_parse_common_folder_path():
     expected = {
-        "folder": "octopus",
+        "folder": "nautilus",
     }
     path = TextToSpeechClient.common_folder_path(**expected)
 
@@ -1232,15 +1256,15 @@ def test_parse_common_folder_path():
 
 
 def test_common_organization_path():
-    organization = "oyster"
+    organization = "scallop"
     expected = "organizations/{organization}".format(organization=organization,)
     actual = TextToSpeechClient.common_organization_path(organization)
     assert expected == actual
 
 
 def test_parse_common_organization_path():
     expected = {
-        "organization": "nudibranch",
+        "organization": "abalone",
     }
     path = TextToSpeechClient.common_organization_path(**expected)
 
@@ -1250,15 +1274,15 @@ def test_parse_common_organization_path():
 
 
 def test_common_project_path():
-    project = "cuttlefish"
+    project = "squid"
     expected = "projects/{project}".format(project=project,)
     actual = TextToSpeechClient.common_project_path(project)
     assert expected == actual
 
 
 def test_parse_common_project_path():
     expected = {
-        "project": "mussel",
+        "project": "clam",
     }
     path = TextToSpeechClient.common_project_path(**expected)
 
@@ -1268,8 +1292,8 @@ def test_parse_common_project_path():
 
 
 def test_common_location_path():
-    project = "winkle"
-    location = "nautilus"
+    project = "whelk"
+    location = "octopus"
     expected = "projects/{project}/locations/{location}".format(
         project=project, location=location,
     )
@@ -1279,8 +1303,8 @@ def test_common_location_path():
 
 def test_parse_common_location_path():
     expected = {
-        "project": "scallop",
-        "location": "abalone",
+        "project": "oyster",
+        "location": "nudibranch",
     }
     path = TextToSpeechClient.common_location_path(**expected)