livekit-plugins-cartesia 0.4.10__py3-none-any.whl → 1.0.0__py3-none-any.whl

livekit/plugins/cartesia/tts.py

@@ -20,9 +20,10 @@ import json
 import os
 import weakref
 from dataclasses import dataclass
-from typing import Any, Optional
+from typing import Any
 
 import aiohttp
+
 from livekit.agents import (
     APIConnectionError,
     APIConnectOptions,
@@ -32,6 +33,12 @@ from livekit.agents import (
     tts,
     utils,
 )
+from livekit.agents.types import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    NOT_GIVEN,
+    NotGivenOr,
+)
+from livekit.agents.utils import is_given
 
 from .log import logger
 from .models import (
@@ -56,8 +63,8 @@ class _TTSOptions:
     encoding: TTSEncoding
     sample_rate: int
     voice: str | list[float]
-    speed: TTSVoiceSpeed | float | None
-    emotion: list[TTSVoiceEmotion | str] | None
+    speed: NotGivenOr[TTSVoiceSpeed | float]
+    emotion: NotGivenOr[list[TTSVoiceEmotion | str]]
     api_key: str
     language: str
     base_url: str
@@ -77,10 +84,10 @@ class TTS(tts.TTS):
         language: str = "en",
         encoding: TTSEncoding = "pcm_s16le",
         voice: str | list[float] = TTSDefaultVoiceId,
-        speed: TTSVoiceSpeed | float | None = None,
-        emotion: list[TTSVoiceEmotion | str] | None = None,
+        speed: NotGivenOr[TTSVoiceSpeed | float] = NOT_GIVEN,
+        emotion: NotGivenOr[list[TTSVoiceEmotion | str]] = NOT_GIVEN,
         sample_rate: int = 24000,
-        api_key: str | None = None,
+        api_key: NotGivenOr[str] = NOT_GIVEN,
         http_session: aiohttp.ClientSession | None = None,
         base_url: str = "https://api.cartesia.ai",
     ) -> None:
@@ -100,16 +107,15 @@ class TTS(tts.TTS):
             api_key (str, optional): The Cartesia API key. If not provided, it will be read from the CARTESIA_API_KEY environment variable.
             http_session (aiohttp.ClientSession | None, optional): An existing aiohttp ClientSession to use. If not provided, a new session will be created.
             base_url (str, optional): The base URL for the Cartesia API. Defaults to "https://api.cartesia.ai".
-        """
+        """  # noqa: E501
 
         super().__init__(
             capabilities=tts.TTSCapabilities(streaming=True),
             sample_rate=sample_rate,
             num_channels=NUM_CHANNELS,
         )
-
-        api_key = api_key or os.environ.get("CARTESIA_API_KEY")
-        if not api_key:
+        cartesia_api_key = api_key if is_given(api_key) else os.environ.get("CARTESIA_API_KEY")
+        if not cartesia_api_key:
             raise ValueError("CARTESIA_API_KEY must be set")
 
         self._opts = _TTSOptions(
@@ -120,7 +126,7 @@ class TTS(tts.TTS):
             voice=voice,
             speed=speed,
             emotion=emotion,
-            api_key=api_key,
+            api_key=cartesia_api_key,
             base_url=base_url,
         )
         self._session = http_session
@@ -137,9 +143,7 @@ class TTS(tts.TTS):
         url = self._opts.get_ws_url(
             f"/tts/websocket?api_key={self._opts.api_key}&cartesia_version={API_VERSION}"
         )
-        return await asyncio.wait_for(
-            session.ws_connect(url), self._conn_options.timeout
-        )
+        return await asyncio.wait_for(session.ws_connect(url), self._conn_options.timeout)
 
     async def _close_ws(self, ws: aiohttp.ClientWebSocketResponse):
         await ws.close()
@@ -156,11 +160,11 @@ class TTS(tts.TTS):
     def update_options(
         self,
         *,
-        model: TTSModels | None = None,
-        language: str | None = None,
-        voice: str | list[float] | None = None,
-        speed: TTSVoiceSpeed | float | None = None,
-        emotion: list[TTSVoiceEmotion | str] | None = None,
+        model: NotGivenOr[TTSModels | str] = NOT_GIVEN,
+        language: NotGivenOr[str] = NOT_GIVEN,
+        voice: NotGivenOr[str | list[float]] = NOT_GIVEN,
+        speed: NotGivenOr[TTSVoiceSpeed | float] = NOT_GIVEN,
+        emotion: NotGivenOr[list[TTSVoiceEmotion | str]] = NOT_GIVEN,
     ) -> None:
         """
         Update the Text-to-Speech (TTS) configuration options.
@@ -175,18 +179,22 @@ class TTS(tts.TTS):
             speed (TTSVoiceSpeed | float, optional): Voice Control - Speed (https://docs.cartesia.ai/user-guides/voice-control)
             emotion (list[TTSVoiceEmotion], optional): Voice Control - Emotion (https://docs.cartesia.ai/user-guides/voice-control)
         """
-        self._opts.model = model or self._opts.model
-        self._opts.language = language or self._opts.language
-        self._opts.voice = voice or self._opts.voice
-        self._opts.speed = speed or self._opts.speed
-        if emotion is not None:
+        if is_given(model):
+            self._opts.model = model
+        if is_given(language):
+            self._opts.language = language
+        if is_given(voice):
+            self._opts.voice = voice
+        if is_given(speed):
+            self._opts.speed = speed
+        if is_given(emotion):
             self._opts.emotion = emotion
 
     def synthesize(
         self,
         text: str,
         *,
-        conn_options: Optional[APIConnectOptions] = None,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
     ) -> ChunkedStream:
         return ChunkedStream(
             tts=self,
@@ -197,15 +205,13 @@ class TTS(tts.TTS):
         )
 
     def stream(
-        self, *, conn_options: Optional[APIConnectOptions] = None
-    ) -> "SynthesizeStream":
-        stream = SynthesizeStream(
+        self, *, conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS
+    ) -> SynthesizeStream:
+        return SynthesizeStream(
             tts=self,
             pool=self._pool,
             opts=self._opts,
         )
-        self._streams.add(stream)
-        return stream
 
     async def aclose(self) -> None:
         for stream in list(self._streams):
@@ -225,7 +231,7 @@ class ChunkedStream(tts.ChunkedStream):
         input_text: str,
         opts: _TTSOptions,
         session: aiohttp.ClientSession,
-        conn_options: Optional[APIConnectOptions] = None,
+        conn_options: APIConnectOptions,
     ) -> None:
         super().__init__(tts=tts, input_text=input_text, conn_options=conn_options)
         self._opts, self._session = opts, session
@@ -379,17 +385,18 @@ class SynthesizeStream(tts.SynthesizeStream):
 
 def _to_cartesia_options(opts: _TTSOptions) -> dict[str, Any]:
     voice: dict[str, Any] = {}
-    if isinstance(opts.voice, str):
-        voice["mode"] = "id"
-        voice["id"] = opts.voice
-    else:
-        voice["mode"] = "embedding"
-        voice["embedding"] = opts.voice
+    if is_given(opts.voice):
+        if isinstance(opts.voice, str):
+            voice["mode"] = "id"
+            voice["id"] = opts.voice
+        else:
+            voice["mode"] = "embedding"
+            voice["embedding"] = opts.voice
 
     voice_controls: dict = {}
-    if opts.speed is not None:
+    if is_given(opts.speed):
         voice_controls["speed"] = opts.speed
-    if opts.emotion is not None:
+    if is_given(opts.emotion):
         voice_controls["emotion"] = opts.emotion
 
     if voice_controls:

livekit/plugins/cartesia/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.4.10"
+__version__ = "1.0.0"

{livekit_plugins_cartesia-0.4.10.dist-info → livekit_plugins_cartesia-1.0.0.dist-info}/METADATA

@@ -1,35 +1,25 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: livekit-plugins-cartesia
-Version: 0.4.10
+Version: 1.0.0
 Summary: LiveKit Agents Plugin for Cartesia
-Home-page: https://github.com/livekit/agents
-License: Apache-2.0
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
 Project-URL: Source, https://github.com/livekit/agents
-Keywords: webrtc,realtime,audio,video,livekit
+Author-email: LiveKit <hello@livekit.io>
+License-Expression: Apache-2.0
+Keywords: audio,livekit,realtime,video,webrtc
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Topic :: Multimedia :: Sound/Audio
-Classifier: Topic :: Multimedia :: Video
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Multimedia :: Sound/Audio
+Classifier: Topic :: Multimedia :: Video
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0
+Requires-Dist: livekit-agents>=1.0.0
 Description-Content-Type: text/markdown
-Requires-Dist: livekit-agents<1.0.0,>=0.12.16
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: license
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
 
 # LiveKit Plugins Cartesia
 

livekit_plugins_cartesia-1.0.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+livekit/plugins/cartesia/__init__.py,sha256=UTa6Q7IxhRBCwPftowHEUDvmBg99J_UjGS_yxTzKD7g,1095
+livekit/plugins/cartesia/log.py,sha256=4Mnhjng_DU1dIWP9IWjIQGZ67EV3LnQhWMWCHVudJbo,71
+livekit/plugins/cartesia/models.py,sha256=KGY-r2luJuUNY6a3nnB0Rx-5Td12hikk-GtYLnqvysE,977
+livekit/plugins/cartesia/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/cartesia/tts.py,sha256=rHDiypiCdn0sKykNvYcl5Cf6SZE2XmPRlnLGQA4m7Ks,14443
+livekit/plugins/cartesia/version.py,sha256=nW89L_U9N4ukT3wAO3BeTqOaa87zLUOsEFz8TkiKIP8,600
+livekit_plugins_cartesia-1.0.0.dist-info/METADATA,sha256=-kXn2tHzxJ812b3gwTOoRfW4UCEKcFWa61gIqHyVsA8,1253
+livekit_plugins_cartesia-1.0.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+livekit_plugins_cartesia-1.0.0.dist-info/RECORD,,

{livekit_plugins_cartesia-0.4.10.dist-info → livekit_plugins_cartesia-1.0.0.dist-info}/WHEEL

@@ -1,5 +1,4 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: hatchling 1.27.0
 Root-Is-Purelib: true
 Tag: py3-none-any
-

livekit_plugins_cartesia-0.4.10.dist-info/RECORD

@@ -1,10 +0,0 @@
-livekit/plugins/cartesia/__init__.py,sha256=UTa6Q7IxhRBCwPftowHEUDvmBg99J_UjGS_yxTzKD7g,1095
-livekit/plugins/cartesia/log.py,sha256=4Mnhjng_DU1dIWP9IWjIQGZ67EV3LnQhWMWCHVudJbo,71
-livekit/plugins/cartesia/models.py,sha256=KGY-r2luJuUNY6a3nnB0Rx-5Td12hikk-GtYLnqvysE,977
-livekit/plugins/cartesia/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/cartesia/tts.py,sha256=cOoNFXNlw2NFN5o6PgLTccu_-y_W0MTAwNciNDtxdd8,14128
-livekit/plugins/cartesia/version.py,sha256=EAXwrHdOWRivmdK-RTQl1YBemh0E8ui_JHvG9dT490M,601
-livekit_plugins_cartesia-0.4.10.dist-info/METADATA,sha256=TXT6xGvQ3of6Gl9PyCCYLrurnkDdfyiOjzyrXC0gga4,1471
-livekit_plugins_cartesia-0.4.10.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-livekit_plugins_cartesia-0.4.10.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_cartesia-0.4.10.dist-info/RECORD,,

livekit_plugins_cartesia-0.4.10.dist-info/top_level.txt

@@ -1 +0,0 @@
-livekit