feat: [google-cloud-texttospeech] add Gemini TTS Multispeaker API fields (#14508)

- [ ] Regenerate this pull request now.

PiperOrigin-RevId: 809186275

Source-Link:
googleapis/googleapis@b2cd70b

Source-Link:
googleapis/googleapis-gen@cbd7c4e
Copy-Tag:
eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLXRleHR0b3NwZWVjaC8uT3dsQm90LnlhbWwiLCJoIjoiY2JkN2M0ZWM1MWQwYWRhYzcyNzg3YWI3NGNlNDA3OGU3ZjI3YTg3YSJ9

---------

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

Author: gcf-owl-bot[bot]

packages/google-cloud-texttospeech/google/cloud/texttospeech/__init__.py

@@ -40,6 +40,8 @@
     ListVoicesRequest,
     ListVoicesResponse,
     MultiSpeakerMarkup,
+    MultispeakerPrebuiltVoice,
+    MultiSpeakerVoiceConfig,
     SsmlVoiceGender,
     StreamingAudioConfig,
     StreamingSynthesisInput,
@@ -72,6 +74,8 @@
     "ListVoicesRequest",
     "ListVoicesResponse",
     "MultiSpeakerMarkup",
+    "MultispeakerPrebuiltVoice",
+    "MultiSpeakerVoiceConfig",
     "StreamingAudioConfig",
     "StreamingSynthesisInput",
     "StreamingSynthesizeConfig",

packages/google-cloud-texttospeech/google/cloud/texttospeech/gapic_version.py

@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-__version__ = "2.29.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}

packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/__init__.py

@@ -33,6 +33,8 @@
     ListVoicesRequest,
     ListVoicesResponse,
     MultiSpeakerMarkup,
+    MultispeakerPrebuiltVoice,
+    MultiSpeakerVoiceConfig,
     SsmlVoiceGender,
     StreamingAudioConfig,
     StreamingSynthesisInput,
@@ -64,6 +66,8 @@
     "ListVoicesRequest",
     "ListVoicesResponse",
     "MultiSpeakerMarkup",
+    "MultiSpeakerVoiceConfig",
+    "MultispeakerPrebuiltVoice",
     "SsmlVoiceGender",
     "StreamingAudioConfig",
     "StreamingSynthesisInput",

packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/gapic_version.py

@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-__version__ = "2.29.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}

packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/__init__.py

@@ -23,6 +23,8 @@
     ListVoicesRequest,
     ListVoicesResponse,
     MultiSpeakerMarkup,
+    MultispeakerPrebuiltVoice,
+    MultiSpeakerVoiceConfig,
     SsmlVoiceGender,
     StreamingAudioConfig,
     StreamingSynthesisInput,
@@ -51,6 +53,8 @@
     "ListVoicesRequest",
     "ListVoicesResponse",
     "MultiSpeakerMarkup",
+    "MultispeakerPrebuiltVoice",
+    "MultiSpeakerVoiceConfig",
     "StreamingAudioConfig",
     "StreamingSynthesisInput",
     "StreamingSynthesizeConfig",

packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/cloud_tts.py

@@ -32,6 +32,8 @@
         "CustomPronunciationParams",
         "CustomPronunciations",
         "MultiSpeakerMarkup",
+        "MultispeakerPrebuiltVoice",
+        "MultiSpeakerVoiceConfig",
         "SynthesisInput",
         "VoiceSelectionParams",
         "AudioConfig",
@@ -404,6 +406,53 @@ class Turn(proto.Message):
     )
 
 
+class MultispeakerPrebuiltVoice(proto.Message):
+    r"""Configuration for a single speaker in a Gemini TTS
+    multi-speaker setup. Enables dialogue between two speakers.
+
+    Attributes:
+        speaker_alias (str):
+            Required. The speaker alias of the voice.
+            This is the user-chosen speaker name that is
+            used in the multispeaker text input, such as
+            "Speaker1".
+        speaker_id (str):
+            Required. The speaker ID of the voice. See
+            https://cloud.google.com/text-to-speech/docs/gemini-tts#voice_options
+            for available values.
+    """
+
+    speaker_alias: str = proto.Field(
+        proto.STRING,
+        number=1,
+    )
+    speaker_id: str = proto.Field(
+        proto.STRING,
+        number=2,
+    )
+
+
+class MultiSpeakerVoiceConfig(proto.Message):
+    r"""Configuration for a multi-speaker text-to-speech setup.
+    Enables the use of up to two distinct voices in a single
+    synthesis request.
+
+    Attributes:
+        speaker_voice_configs (MutableSequence[google.cloud.texttospeech_v1.types.MultispeakerPrebuiltVoice]):
+            Required. A list of configurations for the
+            voices of the speakers. Exactly two speaker
+            voice configurations must be provided.
+    """
+
+    speaker_voice_configs: MutableSequence[
+        "MultispeakerPrebuiltVoice"
+    ] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=2,
+        message="MultispeakerPrebuiltVoice",
+    )
+
+
 class SynthesisInput(proto.Message):
     r"""Contains text input to be synthesized. Either ``text`` or ``ssml``
     must be supplied. Supplying both or neither returns
@@ -542,6 +591,11 @@ class VoiceSelectionParams(proto.Message):
             Optional. The name of the model. If set, the
             service will choose the model matching the
             specified configuration.
+        multi_speaker_voice_config (google.cloud.texttospeech_v1.types.MultiSpeakerVoiceConfig):
+            Optional. The configuration for a Gemini
+            multi-speaker text-to-speech setup. Enables the
+            use of two distinct voices in a single synthesis
+            request.
     """
 
     language_code: str = proto.Field(
@@ -571,6 +625,11 @@ class VoiceSelectionParams(proto.Message):
         proto.STRING,
         number=6,
     )
+    multi_speaker_voice_config: "MultiSpeakerVoiceConfig" = proto.Field(
+        proto.MESSAGE,
+        number=7,
+        message="MultiSpeakerVoiceConfig",
+    )
 
 
 class AudioConfig(proto.Message):
@@ -827,6 +886,11 @@ class StreamingSynthesisInput(proto.Message):
             Markup for HD voices specifically. This field
             may not be used with any other voices.
 
+            This field is a member of `oneof`_ ``input_source``.
+        multi_speaker_markup (google.cloud.texttospeech_v1.types.MultiSpeakerMarkup):
+            Multi-speaker markup for Gemini TTS. This
+            field may not be used with any other voices.
+
             This field is a member of `oneof`_ ``input_source``.
         prompt (str):
             This is system instruction supported only for
@@ -845,6 +909,12 @@ class StreamingSynthesisInput(proto.Message):
         number=5,
         oneof="input_source",
     )
+    multi_speaker_markup: "MultiSpeakerMarkup" = proto.Field(
+        proto.MESSAGE,
+        number=7,
+        oneof="input_source",
+        message="MultiSpeakerMarkup",
+    )
     prompt: str = proto.Field(
         proto.STRING,
         number=6,

packages/google-cloud-texttospeech/google/cloud/texttospeech_v1beta1/gapic_version.py

@@ -13,4 +13,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-__version__ = "2.29.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}

packages/google-cloud-texttospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1.json

@@ -8,7 +8,7 @@
     ],
     "language": "PYTHON",
     "name": "google-cloud-texttospeech",
-    "version": "2.29.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {

packages/google-cloud-texttospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1beta1.json

@@ -8,7 +8,7 @@
     ],
     "language": "PYTHON",
     "name": "google-cloud-texttospeech",
-    "version": "2.29.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {