feat: [google-cloud-texttospeech] add brand voice lite, which lets you clone a voice with just 10 seconds of audio (#13192)

- [ ] Regenerate this pull request now.

PiperOrigin-RevId: 688491221

Source-Link:
googleapis/googleapis@60688dc

Source-Link:
googleapis/googleapis-gen@4072c99
Copy-Tag:
eyJwIjoicGFja2FnZXMvZ29vZ2xlLWNsb3VkLXRleHR0b3NwZWVjaC8uT3dsQm90LnlhbWwiLCJoIjoiNDA3MmM5OTliMzZiYWEyMWNjYjI5YzVmNWQ1NjA4OTYyODQwYjMxYSJ9

---------

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

@@ -48,6 +48,7 @@
     SynthesizeSpeechRequest,
     SynthesizeSpeechResponse,
     Voice,
+    VoiceCloneParams,
     VoiceSelectionParams,
 )
 from google.cloud.texttospeech_v1.types.cloud_tts_lrs import (
@@ -76,6 +77,7 @@
     "SynthesizeSpeechRequest",
     "SynthesizeSpeechResponse",
     "Voice",
+    "VoiceCloneParams",
     "VoiceSelectionParams",
     "AudioEncoding",
     "SsmlVoiceGender",

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

@@ -41,6 +41,7 @@
     SynthesizeSpeechRequest,
     SynthesizeSpeechResponse,
     Voice,
+    VoiceCloneParams,
     VoiceSelectionParams,
 )
 from .types.cloud_tts_lrs import (
@@ -74,5 +75,6 @@
     "TextToSpeechClient",
     "TextToSpeechLongAudioSynthesizeClient",
     "Voice",
+    "VoiceCloneParams",
     "VoiceSelectionParams",
 )

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

@@ -31,6 +31,7 @@
     SynthesizeSpeechRequest,
     SynthesizeSpeechResponse,
     Voice,
+    VoiceCloneParams,
     VoiceSelectionParams,
 )
 from .cloud_tts_lrs import (
@@ -55,6 +56,7 @@
     "SynthesizeSpeechRequest",
     "SynthesizeSpeechResponse",
     "Voice",
+    "VoiceCloneParams",
     "VoiceSelectionParams",
     "AudioEncoding",
     "SsmlVoiceGender",

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

@@ -35,6 +35,7 @@
         "VoiceSelectionParams",
         "AudioConfig",
         "CustomVoiceParams",
+        "VoiceCloneParams",
         "SynthesizeSpeechResponse",
         "StreamingSynthesizeConfig",
         "StreamingSynthesisInput",
@@ -423,6 +424,10 @@ class VoiceSelectionParams(proto.Message):
             The configuration for a custom voice. If
             [CustomVoiceParams.model] is set, the service will choose
             the custom voice matching the specified configuration.
+        voice_clone (google.cloud.texttospeech_v1.types.VoiceCloneParams):
+            Optional. The configuration for a voice clone. If
+            [VoiceCloneParams.voice_clone_key] is set, the service will
+            choose the voice clone matching the specified configuration.
     """
 
     language_code: str = proto.Field(
@@ -443,6 +448,11 @@ class VoiceSelectionParams(proto.Message):
         number=4,
         message="CustomVoiceParams",
     )
+    voice_clone: "VoiceCloneParams" = proto.Field(
+        proto.MESSAGE,
+        number=5,
+        message="VoiceCloneParams",
+    )
 
 
 class AudioConfig(proto.Message):
@@ -565,6 +575,20 @@ class ReportedUsage(proto.Enum):
     )
 
 
+class VoiceCloneParams(proto.Message):
+    r"""The configuration of Voice Clone feature.
+
+    Attributes:
+        voice_cloning_key (str):
+            Required. Created by GenerateVoiceCloningKey.
+    """
+
+    voice_cloning_key: str = proto.Field(
+        proto.STRING,
+        number=1,
+    )
+
+
 class SynthesizeSpeechResponse(proto.Message):
     r"""The message returned to the client by the ``SynthesizeSpeech``
     method.