livekit-plugins-google 0.11.1__py3-none-any.whl → 0.11.3__py3-none-any.whl

livekit/plugins/google/stt.py

@@ -94,7 +94,7 @@ class STT(stt.STT):
         punctuate: bool = True,
         spoken_punctuation: bool = False,
         model: SpeechModels | str = "latest_long",
-        location: str = "us-central1",
+        location: str = "global",
         sample_rate: int = 16000,
         credentials_info: dict | None = None,
         credentials_file: str | None = None,
@@ -114,7 +114,7 @@ class STT(stt.STT):
             punctuate(bool): whether to punctuate the audio (default: True)
             spoken_punctuation(bool): whether to use spoken punctuation (default: False)
             model(SpeechModels): the model to use for recognition default: "latest_long"
-            location(str): the location to use for recognition default: "us-central1"
+            location(str): the location to use for recognition default: "global"
             sample_rate(int): the sample rate of the audio default: 16000
             credentials_info(dict): the credentials info to use for recognition (default: None)
             credentials_file(str): the credentials file to use for recognition (default: None)
@@ -488,7 +488,6 @@ class SpeechStream(stt.SpeechStream):
                             ),
                         ),
                         streaming_features=cloud_speech.StreamingRecognitionFeatures(
-                            enable_voice_activity_events=True,
                             interim_results=self._config.interim_results,
                         ),
                     )

livekit/plugins/google/tts.py

@@ -26,6 +26,7 @@ from livekit.agents import (
     utils,
 )
 
+from google.api_core.client_options import ClientOptions
 from google.api_core.exceptions import DeadlineExceeded, GoogleAPICallError
 from google.cloud import texttospeech
 from google.cloud.texttospeech_v1.types import SsmlVoiceGender, SynthesizeSpeechResponse
@@ -50,6 +51,7 @@ class TTS(tts.TTS):
         pitch: int = 0,
         effects_profile_id: str = "",
         speaking_rate: float = 1.0,
+        location: str = "global",
         credentials_info: dict | None = None,
         credentials_file: str | None = None,
     ) -> None:
@@ -65,6 +67,7 @@ class TTS(tts.TTS):
             gender (Gender | str, optional): Voice gender ("male", "female", "neutral"). Default is "neutral".
             voice_name (str, optional): Specific voice name. Default is an empty string.
             sample_rate (int, optional): Audio sample rate in Hz. Default is 24000.
+            location (str, optional): Location for the TTS client. Default is "global".
             pitch (float, optional): Speaking pitch, ranging from -20.0 to 20.0 semitones relative to the original pitch. Default is 0.
             effects_profile_id (str): Optional identifier for selecting audio effects profiles to apply to the synthesized speech.
             speaking_rate (float, optional): Speed of speech. Default is 1.0.
@@ -83,7 +86,7 @@ class TTS(tts.TTS):
         self._client: texttospeech.TextToSpeechAsyncClient | None = None
         self._credentials_info = credentials_info
         self._credentials_file = credentials_file
-
+        self._location = location
         voice = texttospeech.VoiceSelectionParams(
             name=voice_name,
             language_code=language,
@@ -126,22 +129,30 @@ class TTS(tts.TTS):
         self._opts.audio_config.speaking_rate = speaking_rate
 
     def _ensure_client(self) -> texttospeech.TextToSpeechAsyncClient:
+        api_endpoint = "texttospeech.googleapis.com"
+        if self._location != "global":
+            api_endpoint = f"{self._location}-texttospeech.googleapis.com"
+
         if self._client is None:
             if self._credentials_info:
                 self._client = (
                     texttospeech.TextToSpeechAsyncClient.from_service_account_info(
-                        self._credentials_info
+                        self._credentials_info,
+                        client_options=ClientOptions(api_endpoint=api_endpoint),
                     )
                 )
 
             elif self._credentials_file:
                 self._client = (
                     texttospeech.TextToSpeechAsyncClient.from_service_account_file(
-                        self._credentials_file
+                        self._credentials_file,
+                        client_options=ClientOptions(api_endpoint=api_endpoint),
                     )
                 )
             else:
-                self._client = texttospeech.TextToSpeechAsyncClient()
+                self._client = texttospeech.TextToSpeechAsyncClient(
+                    client_options=ClientOptions(api_endpoint=api_endpoint)
+                )
 
         assert self._client is not None
         return self._client

livekit/plugins/google/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.11.1"
+__version__ = "0.11.3"

{livekit_plugins_google-0.11.1.dist-info → livekit_plugins_google-0.11.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: livekit-plugins-google
-Version: 0.11.1
+Version: 0.11.3
 Summary: Agent Framework plugin for services from Google Cloud
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0

{livekit_plugins_google-0.11.1.dist-info → livekit_plugins_google-0.11.3.dist-info}/RECORD

@@ -4,15 +4,15 @@ livekit/plugins/google/llm.py,sha256=LZaHsrkjfboRZLWm7L2G0mw62q2sXBNj4YeeV2Sk2uU
 livekit/plugins/google/log.py,sha256=GI3YWN5YzrafnUccljzPRS_ZALkMNk1i21IRnTl2vNA,69
 livekit/plugins/google/models.py,sha256=SGjAumdDK97NNLwMFcqZdKR68f1NoGB2Rk1UP2-imG0,1457
 livekit/plugins/google/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/google/stt.py,sha256=96GJmGDAIBdCpDECArwIXpj2s1xlcA_zuvTnwsvq4xA,22854
-livekit/plugins/google/tts.py,sha256=pG9_pibO3NDGEMa4huU5S9lbeyI3daQyrS17SuTKfZI,8008
-livekit/plugins/google/version.py,sha256=LeUJJQ9jwADplJbF46ClzVjYAClwJEhZMCToNJN9lWc,601
+livekit/plugins/google/stt.py,sha256=l6UB9oaM7eFInnI_0t7Ub-edXLVRgvaiyHj-e_gEuwE,22781
+livekit/plugins/google/tts.py,sha256=t4a6so5mR6HxrZa3In_PxD37voIxs1fRL4F9Zu5qltE,8645
+livekit/plugins/google/version.py,sha256=_Let6gsoyIgPmq62suQfckCl_Qx9L10STGT9OrmzGp0,601
 livekit/plugins/google/beta/__init__.py,sha256=AxRYc7NGG62Tv1MmcZVCDHNvlhbC86hM-_yP01Qb28k,47
 livekit/plugins/google/beta/realtime/__init__.py,sha256=sGTn6JFNyA30QUXBZ_BV3l2eHpGAzR35ByXxg77vWNU,205
 livekit/plugins/google/beta/realtime/api_proto.py,sha256=9EhmwgeIgKDqdSijv5Q9pgx7UhAakK02ZDwbnUsra_o,657
 livekit/plugins/google/beta/realtime/realtime_api.py,sha256=8JdWUMUheGhy1ia6JbN3_U2_cL7CNs8-1fTOAgW4I38,22999
 livekit/plugins/google/beta/realtime/transcriber.py,sha256=rjXO0cSPr3HATxrSfv1MX7IbrjmiTvnLPF280BfRBL8,9809
-livekit_plugins_google-0.11.1.dist-info/METADATA,sha256=m7B07abY9wTbEJVa3dmdsgfatxYwJFwDNQYhyJgIPJU,3732
-livekit_plugins_google-0.11.1.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
-livekit_plugins_google-0.11.1.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_google-0.11.1.dist-info/RECORD,,
+livekit_plugins_google-0.11.3.dist-info/METADATA,sha256=LAZ-OoQF5_QUi5qe-STwxDiJ_mVDz2VxW1FyyUHwI6k,3732
+livekit_plugins_google-0.11.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+livekit_plugins_google-0.11.3.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
+livekit_plugins_google-0.11.3.dist-info/RECORD,,

{livekit_plugins_google-0.11.1.dist-info → livekit_plugins_google-0.11.3.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.1.0)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any