feat: [google-cloud-texttospeech] add multi-speaker markup, which allows generating dialogue between multiple speakers (googleapis#13223)

gcf-owl-bot[bot] · web-flow · commit b01d99dc321b · 2024-10-28T17:30:21.000-04:00
BEGIN_COMMIT_OVERRIDE feat: add multi-speaker markup, which allows generating dialogue between multiple speakers END_COMMIT_OVERRIDE - [ ] Regenerate this pull request now. PiperOrigin-RevId: 690597076 Source-Link: googleapis/googleapis@3bc81b7 Source-Link: https://github.com/googleapis/googleapis-gen/commit/a2253a01e6e93e79a1dec7e0b2aeea708b634d1e Copy-Tag: eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLXRleHR0b3NwZWVjaC8uT3dsQm90LnlhbWwiLCJoIjoiYTIyNTNhMDFlNmU5M2U3OWExZGVjN2UwYjJhZWVhNzA4YjYzNGQxZSJ9 --------- Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech/__init__.py b/packages/google-cloud-texttospeech/google/cloud/texttospeech/__init__.py
@@ -39,6 +39,7 @@
     CustomVoiceParams,
     ListVoicesRequest,
     ListVoicesResponse,
+    MultiSpeakerMarkup,
     SsmlVoiceGender,
     StreamingSynthesisInput,
     StreamingSynthesizeConfig,
@@ -69,6 +70,7 @@
     "CustomVoiceParams",
     "ListVoicesRequest",
     "ListVoicesResponse",
+    "MultiSpeakerMarkup",
     "StreamingSynthesisInput",
     "StreamingSynthesizeConfig",
     "StreamingSynthesizeRequest",
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech/gapic_version.py b/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__ = "2.20.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/__init__.py b/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/__init__.py
@@ -32,6 +32,7 @@
     CustomVoiceParams,
     ListVoicesRequest,
     ListVoicesResponse,
+    MultiSpeakerMarkup,
     SsmlVoiceGender,
     StreamingSynthesisInput,
     StreamingSynthesizeConfig,
@@ -61,6 +62,7 @@
     "CustomVoiceParams",
     "ListVoicesRequest",
     "ListVoicesResponse",
+    "MultiSpeakerMarkup",
     "SsmlVoiceGender",
     "StreamingSynthesisInput",
     "StreamingSynthesizeConfig",
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/gapic_version.py b/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__ = "2.20.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/__init__.py b/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/__init__.py
@@ -22,6 +22,7 @@
     CustomVoiceParams,
     ListVoicesRequest,
     ListVoicesResponse,
+    MultiSpeakerMarkup,
     SsmlVoiceGender,
     StreamingSynthesisInput,
     StreamingSynthesizeConfig,
@@ -48,6 +49,7 @@
     "CustomVoiceParams",
     "ListVoicesRequest",
     "ListVoicesResponse",
+    "MultiSpeakerMarkup",
     "StreamingSynthesisInput",
     "StreamingSynthesizeConfig",
     "StreamingSynthesizeRequest",
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/cloud_tts.py b/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1/types/cloud_tts.py
@@ -31,6 +31,7 @@
         "SynthesizeSpeechRequest",
         "CustomPronunciationParams",
         "CustomPronunciations",
+        "MultiSpeakerMarkup",
         "SynthesisInput",
         "VoiceSelectionParams",
         "AudioConfig",
@@ -328,6 +329,42 @@ class CustomPronunciations(proto.Message):
     )
 
 
+class MultiSpeakerMarkup(proto.Message):
+    r"""A collection of turns for multi-speaker synthesis.
+
+    Attributes:
+        turns (MutableSequence[google.cloud.texttospeech_v1.types.MultiSpeakerMarkup.Turn]):
+            Required. Speaker turns.
+    """
+
+    class Turn(proto.Message):
+        r"""A Multi-speaker turn.
+
+        Attributes:
+            speaker (str):
+                Required. The speaker of the turn, for
+                example, 'O' or 'Q'. Please refer to
+                documentation for available speakers.
+            text (str):
+                Required. The text to speak.
+        """
+
+        speaker: str = proto.Field(
+            proto.STRING,
+            number=1,
+        )
+        text: str = proto.Field(
+            proto.STRING,
+            number=2,
+        )
+
+    turns: MutableSequence[Turn] = proto.RepeatedField(
+        proto.MESSAGE,
+        number=1,
+        message=Turn,
+    )
+
+
 class SynthesisInput(proto.Message):
     r"""Contains text input to be synthesized. Either ``text`` or ``ssml``
     must be supplied. Supplying both or neither returns
@@ -354,6 +391,11 @@ class SynthesisInput(proto.Message):
             For more information, see
             `SSML <https://cloud.google.com/text-to-speech/docs/ssml>`__.
 
+            This field is a member of `oneof`_ ``input_source``.
+        multi_speaker_markup (google.cloud.texttospeech_v1.types.MultiSpeakerMarkup):
+            The multi-speaker input to be synthesized.
+            Only applicable for multi-speaker synthesis.
+
             This field is a member of `oneof`_ ``input_source``.
         custom_pronunciations (google.cloud.texttospeech_v1.types.CustomPronunciations):
             Optional. The pronunciation customizations to
@@ -383,6 +425,12 @@ class SynthesisInput(proto.Message):
         number=2,
         oneof="input_source",
     )
+    multi_speaker_markup: "MultiSpeakerMarkup" = proto.Field(
+        proto.MESSAGE,
+        number=4,
+        oneof="input_source",
+        message="MultiSpeakerMarkup",
+    )
     custom_pronunciations: "CustomPronunciations" = proto.Field(
         proto.MESSAGE,
         number=3,
diff --git a/packages/google-cloud-texttospeech/google/cloud/texttospeech_v1beta1/gapic_version.py b/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__ = "2.20.0"  # {x-release-please-version}
+__version__ = "0.0.0"  # {x-release-please-version}
diff --git a/packages/google-cloud-texttospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1.json b/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": "2.20.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {
diff --git a/packages/google-cloud-texttospeech/samples/generated_samples/snippet_metadata_google.cloud.texttospeech.v1beta1.json b/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": "2.20.0"
+    "version": "0.1.0"
   },
   "snippets": [
     {

Original file line number	Diff line number	Diff line change
`@@ -13,4 +13,4 @@`
`13`	`13`	`# See the License for the specific language governing permissions and`
`14`	`14`	`# limitations under the License.`
`15`	`15`	`#`
`16`		`-__version__ = "2.20.0" # {x-release-please-version}`
	`16`	`+__version__ = "0.0.0" # {x-release-please-version}`
Original file line number	Diff line number	Diff line change
`@@ -8,7 +8,7 @@`
`8`	`8`	`],`
`9`	`9`	`"language": "PYTHON",`
`10`	`10`	`"name": "google-cloud-texttospeech",`
`11`		`- "version": "2.20.0"`
	`11`	`+ "version": "0.1.0"`
`12`	`12`	`},`
`13`	`13`	`"snippets": [`
`14`	`14`	`{`