livekit-plugins-google 0.3.0__py3-none-any.whl → 0.4.0__py3-none-any.whl

livekit/plugins/google/__init__.py

@@ -13,9 +13,10 @@
 # limitations under the License.
 
 from .stt import STT, SpeechStream
+from .tts import TTS
 from .version import __version__
 
-__all__ = ["STT", "SpeechStream", "__version__"]
+__all__ = ["STT", "TTS", "SpeechStream", "__version__"]
 
 from livekit.agents import Plugin
 

livekit/plugins/google/log.py

@@ -0,0 +1,3 @@
+import logging
+
+logger = logging.getLogger("livekit.plugins.google")

livekit/plugins/google/models.py

@@ -83,3 +83,7 @@ SpeechLanguages = Literal[
     "vi-VN",
     "da-DK",
 ]
+
+Gender = Literal["male", "female", "neutral"]
+
+AudioEncoding = Literal["wav", "mp3", "ogg", "mulaw", "alaw"]

livekit/plugins/google/stt.py

@@ -17,7 +17,6 @@ from __future__ import annotations
 import asyncio
 import contextlib
 import dataclasses
-import logging
 from dataclasses import dataclass
 from typing import Any, AsyncIterable, Dict, List
 
@@ -29,6 +28,7 @@ from google.auth import credentials  # type: ignore
 from google.cloud.speech_v2 import SpeechAsyncClient
 from google.cloud.speech_v2.types import cloud_speech
 
+from .log import logger
 from .models import SpeechLanguages, SpeechModels
 
 LgType = SpeechLanguages | str
@@ -105,7 +105,7 @@ class STT(stt.STT):
             config.languages = [config.languages]
         elif not config.detect_language:
             if len(config.languages) > 1:
-                logging.warning(
+                logger.warning(
                     "multiple languages provided, but language detection is disabled"
                 )
             config.languages = [config.languages[0]]
@@ -208,7 +208,7 @@ class SpeechStream(stt.SpeechStream):
 
         def log_exception(task: asyncio.Task) -> None:
             if not task.cancelled() and task.exception():
-                logging.error(f"google stt task failed: {task.exception()}")
+                logger.error(f"google stt task failed: {task.exception()}")
 
         self._main_task.add_done_callback(log_exception)
 
@@ -256,7 +256,7 @@ class SpeechStream(stt.SpeechStream):
                                     audio=frame.data.tobytes(),
                                 )
                         except Exception as e:
-                            logging.error(
+                            logger.error(
                                 f"an error occurred while streaming inputs: {e}"
                             )
 
@@ -269,7 +269,7 @@ class SpeechStream(stt.SpeechStream):
                     await self._run_stream(stream)
                 except Exception as e:
                     if retry_count >= max_retry:
-                        logging.error(
+                        logger.error(
                             f"failed to connect to google stt after {max_retry} tries",
                             exc_info=e,
                         )
@@ -277,7 +277,7 @@ class SpeechStream(stt.SpeechStream):
 
                     retry_delay = min(retry_count * 2, 10)  # max 10s
                     retry_count += 1
-                    logging.warning(
+                    logger.warning(
                         f"google stt connection failed, retrying in {retry_delay}s",
                         exc_info=e,
                     )

livekit/plugins/google/tts.py

@@ -0,0 +1,146 @@
+# Copyright 2023 LiveKit, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from dataclasses import dataclass
+from typing import AsyncIterable, Optional, Union
+
+from livekit import rtc
+from livekit.agents import codecs, tts
+
+from google.cloud import texttospeech
+from google.cloud.texttospeech_v1.types import (
+    SsmlVoiceGender,
+    SynthesizeSpeechResponse,
+)
+
+from .log import logger
+from .models import AudioEncoding, Gender, SpeechLanguages
+
+LgType = Union[SpeechLanguages, str]
+GenderType = Union[Gender, str]
+AudioEncodingType = Union[AudioEncoding, str]
+
+
+@dataclass
+class TTSOptions:
+    voice: texttospeech.VoiceSelectionParams
+    audio_config: texttospeech.AudioConfig
+
+
+class TTS(tts.TTS):
+    def __init__(
+        self,
+        config: Optional[TTSOptions] = None,
+        *,
+        language: LgType = "en-US",
+        gender: GenderType = "neutral",
+        voice_name: str = "",  # Not required
+        audio_encoding: AudioEncodingType = "wav",
+        sample_rate: int = 24000,
+        speaking_rate: float = 1.0,
+        credentials_info: Optional[dict] = None,
+        credentials_file: Optional[str] = None,
+    ) -> None:
+        super().__init__(
+            streaming_supported=False, sample_rate=sample_rate, num_channels=1
+        )
+
+        if credentials_info:
+            self._client = (
+                texttospeech.TextToSpeechAsyncClient.from_service_account_info(
+                    credentials_info
+                )
+            )
+        elif credentials_file:
+            self._client = (
+                texttospeech.TextToSpeechAsyncClient.from_service_account_file(
+                    credentials_file
+                )
+            )
+        else:
+            self._client = texttospeech.TextToSpeechAsyncClient()
+
+        if not config:
+            _gender = SsmlVoiceGender.NEUTRAL
+            if gender == "male":
+                _gender = SsmlVoiceGender.MALE
+            elif gender == "female":
+                _gender = SsmlVoiceGender.FEMALE
+            voice = texttospeech.VoiceSelectionParams(
+                name=voice_name,
+                language_code=language,
+                ssml_gender=_gender,
+            )
+            # Support wav and mp3 only
+            if audio_encoding == "wav":
+                _audio_encoding = texttospeech.AudioEncoding.LINEAR16
+            elif audio_encoding == "mp3":
+                _audio_encoding = texttospeech.AudioEncoding.MP3
+            # elif audio_encoding == "opus":
+            #     _audio_encoding = texttospeech.AudioEncoding.OGG_OPUS
+            # elif audio_encoding == "mulaw":
+            #     _audio_encoding = texttospeech.AudioEncoding.MULAW
+            # elif audio_encoding == "alaw":
+            #     _audio_encoding = texttospeech.AudioEncoding.ALAW
+            else:
+                raise NotImplementedError(
+                    f"Audio encoding {audio_encoding} is not supported"
+                )
+
+            config = TTSOptions(
+                voice=voice,
+                audio_config=texttospeech.AudioConfig(
+                    audio_encoding=_audio_encoding,
+                    sample_rate_hertz=sample_rate,
+                    speaking_rate=speaking_rate,
+                ),
+            )
+        self._config = config
+
+    def synthesize(
+        self,
+        text: str,
+    ) -> AsyncIterable[tts.SynthesizedAudio]:
+        async def generator():
+            try:
+                # Perform the text-to-speech request on the text input with the selected
+                # voice parameters and audio file type
+                response: SynthesizeSpeechResponse = (
+                    await self._client.synthesize_speech(
+                        input=texttospeech.SynthesisInput(text=text),
+                        voice=self._config.voice,
+                        audio_config=self._config.audio_config,
+                    )
+                )
+
+                data = response.audio_content
+                if self._config.audio_config.audio_encoding == "mp3":
+                    decoder = codecs.Mp3StreamDecoder()
+                    frames = decoder.decode_chunk(data)
+                    for frame in frames:
+                        yield tts.SynthesizedAudio(text=text, data=frame)
+                else:
+                    yield tts.SynthesizedAudio(
+                        text=text,
+                        data=rtc.AudioFrame(
+                            data=data,
+                            sample_rate=self._config.audio_config.sample_rate_hertz,
+                            num_channels=1,
+                            samples_per_channel=len(data) // 2,  # 16-bit
+                        ),
+                    )
+            except Exception as e:
+                logger.error(f"failed to synthesize: {e}")
+
+        return generator()

livekit/plugins/google/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.3.0"
+__version__ = "0.4.0"

{livekit_plugins_google-0.3.0.dist-info → livekit_plugins_google-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: livekit-plugins-google
-Version: 0.3.0
+Version: 0.4.0
 Summary: Agent Framework plugin for services from Google Cloud
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0
@@ -29,8 +29,8 @@ Requires-Dist: google-cloud-speech <3,>=2
 Requires-Dist: google-cloud-texttospeech <3,>=2
 Requires-Dist: google-cloud-translate <4,>=3
 Requires-Dist: googleapis-common-protos <2,>=1
-Requires-Dist: livekit >=0.9.2
-Requires-Dist: livekit-agents ~=0.5.dev0
+Requires-Dist: livekit ~=0.11
+Requires-Dist: livekit-agents ~=0.6.0
 
 # LiveKit Plugins Google
 

livekit_plugins_google-0.4.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+livekit/plugins/google/__init__.py,sha256=DlQC5cosMFyQlM8_vFvJGoZiziFkd0Sa4mutnsxXyZM,959
+livekit/plugins/google/log.py,sha256=GI3YWN5YzrafnUccljzPRS_ZALkMNk1i21IRnTl2vNA,69
+livekit/plugins/google/models.py,sha256=e-KvFKOn6eFfLucAltwdAwMEYByuHcJpIr7KfO0ClL0,1295
+livekit/plugins/google/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/google/stt.py,sha256=sPV4ByAxfeGBNvAGIuwZvheEA0k7NYjXR_UiYWjd39Y,15029
+livekit/plugins/google/tts.py,sha256=ZYtotaD8hZ-n53A7qOfp728oPAWIrJYLvCPjF_Ni-xo,5299
+livekit/plugins/google/version.py,sha256=yelanl1wEXtgUH0CzoNVXfi2yTc2hElSzuAhULFzANc,600
+livekit_plugins_google-0.4.0.dist-info/METADATA,sha256=xm5VC02Nbzj7x_cxZ-THc4iwb76_Jr7hu7C_G_Z-mtA,1941
+livekit_plugins_google-0.4.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+livekit_plugins_google-0.4.0.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
+livekit_plugins_google-0.4.0.dist-info/RECORD,,

livekit_plugins_google-0.3.0.dist-info/RECORD

@@ -1,9 +0,0 @@
-livekit/plugins/google/__init__.py,sha256=snPMHNLrurYbLWQOkV_o6qG1CEWsOCZ8ZfPMvmh5ejY,931
-livekit/plugins/google/models.py,sha256=DgiXOvGDO8D9rfCKHJL28lbyQR8mXXB2kpku-szXLRs,1185
-livekit/plugins/google/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/google/stt.py,sha256=lYA8hlkxG3YSw1Q34j8hgs4us5Ij-TLBQTRwtGPN9MY,15025
-livekit/plugins/google/version.py,sha256=G5iYozum4q7UpHwW43F7QfhzUfwcncPxBZ0gmUGsd5I,600
-livekit_plugins_google-0.3.0.dist-info/METADATA,sha256=sPd3OZxViD0Aq1uF1qJpbsYeqLAlq8tB720JXk-_RKw,1945
-livekit_plugins_google-0.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-livekit_plugins_google-0.3.0.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_google-0.3.0.dist-info/RECORD,,