livekit-plugins-cartesia 0.4.8__py3-none-any.whl → 0.4.10__py3-none-any.whl

livekit/plugins/cartesia/models.py

@@ -8,7 +8,7 @@ TTSEncoding = Literal[
     # "pcm_alaw",
 ]
 
-TTSModels = Literal["sonic-english", "sonic-multilingual"]
+TTSModels = Literal["sonic", "sonic-2", "sonic-lite", "sonic-preview", "sonic-turbo"]
 TTSLanguages = Literal["en", "es", "fr", "de", "pt", "zh", "ja"]
 TTSDefaultVoiceId = "794f9389-aac1-45b6-b726-9d9369183238"
 TTSVoiceSpeed = Literal["fastest", "fast", "normal", "slow", "slowest"]

livekit/plugins/cartesia/tts.py

@@ -23,7 +23,6 @@ from dataclasses import dataclass
 from typing import Any, Optional
 
 import aiohttp
-from livekit import rtc
 from livekit.agents import (
     APIConnectionError,
     APIConnectOptions,
@@ -74,7 +73,7 @@ class TTS(tts.TTS):
     def __init__(
         self,
         *,
-        model: TTSModels | str = "sonic",
+        model: TTSModels | str = "sonic-2",
         language: str = "en",
         encoding: TTSEncoding = "pcm_s16le",
         voice: str | list[float] = TTSDefaultVoiceId,
@@ -91,7 +90,7 @@ class TTS(tts.TTS):
         See https://docs.cartesia.ai/reference/web-socket/stream-speech/stream-speech for more details on the the Cartesia API.
 
         Args:
-            model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-english".
+            model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-2".
             language (str, optional): The language code for synthesis. Defaults to "en".
             encoding (TTSEncoding, optional): The audio encoding format. Defaults to "pcm_s16le".
             voice (str | list[float], optional): The voice ID or embedding array.
@@ -128,6 +127,8 @@ class TTS(tts.TTS):
         self._pool = utils.ConnectionPool[aiohttp.ClientWebSocketResponse](
             connect_cb=self._connect_ws,
             close_cb=self._close_ws,
+            max_session_duration=300,
+            mark_refreshed_on_get=True,
         )
         self._streams = weakref.WeakSet[SynthesizeStream]()
 
@@ -149,6 +150,9 @@ class TTS(tts.TTS):
 
         return self._session
 
+    def prewarm(self) -> None:
+        self._pool.prewarm()
+
     def update_options(
         self,
         *,
@@ -165,7 +169,7 @@ class TTS(tts.TTS):
         and emotion. If any parameter is not provided, the existing value will be retained.
 
         Args:
-            model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-english".
+            model (TTSModels, optional): The Cartesia TTS model to use. Defaults to "sonic-2".
             language (str, optional): The language code for synthesis. Defaults to "en".
             voice (str | list[float], optional): The voice ID or embedding array.
             speed (TTSVoiceSpeed | float, optional): Voice Control - Speed (https://docs.cartesia.ai/user-guides/voice-control)
@@ -251,19 +255,17 @@ class ChunkedStream(tts.ChunkedStream):
                 ),
             ) as resp:
                 resp.raise_for_status()
+                emitter = tts.SynthesizedAudioEmitter(
+                    event_ch=self._event_ch,
+                    request_id=request_id,
+                )
                 async for data, _ in resp.content.iter_chunks():
                     for frame in bstream.write(data):
-                        self._event_ch.send_nowait(
-                            tts.SynthesizedAudio(
-                                request_id=request_id,
-                                frame=frame,
-                            )
-                        )
+                        emitter.push(frame)
 
                 for frame in bstream.flush():
-                    self._event_ch.send_nowait(
-                        tts.SynthesizedAudio(request_id=request_id, frame=frame)
-                    )
+                    emitter.push(frame)
+                emitter.flush()
         except asyncio.TimeoutError as e:
             raise APITimeoutError() from e
         except aiohttp.ClientResponseError as e:
@@ -323,22 +325,10 @@ class SynthesizeStream(tts.SynthesizeStream):
                 sample_rate=self._opts.sample_rate,
                 num_channels=NUM_CHANNELS,
             )
-
-            last_frame: rtc.AudioFrame | None = None
-
-            def _send_last_frame(*, segment_id: str, is_final: bool) -> None:
-                nonlocal last_frame
-                if last_frame is not None:
-                    self._event_ch.send_nowait(
-                        tts.SynthesizedAudio(
-                            request_id=request_id,
-                            segment_id=segment_id,
-                            frame=last_frame,
-                            is_final=is_final,
-                        )
-                    )
-
-                    last_frame = None
+            emitter = tts.SynthesizedAudioEmitter(
+                event_ch=self._event_ch,
+                request_id=request_id,
+            )
 
             while True:
                 msg = await ws.receive()
@@ -358,18 +348,16 @@ class SynthesizeStream(tts.SynthesizeStream):
 
                 data = json.loads(msg.data)
                 segment_id = data.get("context_id")
+                emitter._segment_id = segment_id
 
                 if data.get("data"):
                     b64data = base64.b64decode(data["data"])
                     for frame in audio_bstream.write(b64data):
-                        _send_last_frame(segment_id=segment_id, is_final=False)
-                        last_frame = frame
+                        emitter.push(frame)
                 elif data.get("done"):
                     for frame in audio_bstream.flush():
-                        _send_last_frame(segment_id=segment_id, is_final=False)
-                        last_frame = frame
-
-                    _send_last_frame(segment_id=segment_id, is_final=True)
+                        emitter.push(frame)
+                    emitter.flush()
                     if segment_id == request_id:
                         # we're not going to receive more frames, end stream
                         break

livekit/plugins/cartesia/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.4.8"
+__version__ = "0.4.10"

{livekit_plugins_cartesia-0.4.8.dist-info → livekit_plugins_cartesia-0.4.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: livekit-plugins-cartesia
-Version: 0.4.8
+Version: 0.4.10
 Summary: LiveKit Agents Plugin for Cartesia
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0
@@ -19,7 +19,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3 :: Only
 Requires-Python: >=3.9.0
 Description-Content-Type: text/markdown
-Requires-Dist: livekit-agents>=0.12.11
+Requires-Dist: livekit-agents<1.0.0,>=0.12.16
 Dynamic: classifier
 Dynamic: description
 Dynamic: description-content-type

livekit_plugins_cartesia-0.4.10.dist-info/RECORD

@@ -0,0 +1,10 @@
+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-0.4.8.dist-info → livekit_plugins_cartesia-0.4.10.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.8.2)
+Generator: setuptools (76.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

livekit_plugins_cartesia-0.4.8.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=56CJgo7my-w-vpedir_ImV_aqKASeLihE5DbcCCgGJI,950
-livekit/plugins/cartesia/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/cartesia/tts.py,sha256=UUnGrqizmnyHhA-rmbtVD6-pYCMEWozbZxlVRe0HFw4,14747
-livekit/plugins/cartesia/version.py,sha256=1PUjLiYcL1-nwBUG1EXqZsTfF_WQI8KxpzCeCIZHeLc,600
-livekit_plugins_cartesia-0.4.8.dist-info/METADATA,sha256=sJRr9rLGGOUcOonnwQX6xxbKu1Ag-DFWrxjBf4uhDtw,1463
-livekit_plugins_cartesia-0.4.8.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-livekit_plugins_cartesia-0.4.8.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_cartesia-0.4.8.dist-info/RECORD,,