livekit-plugins-elevenlabs 0.2.0__py3-none-any.whl → 0.3.0__py3-none-any.whl

livekit/plugins/elevenlabs/__init__.py

@@ -12,8 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-
-from .tts import TTS, Voice, VoiceSettings, DEFAULT_VOICE
+from .tts import DEFAULT_VOICE, TTS, Voice, VoiceSettings
 from .version import __version__
 
 __all__ = ["TTS", "Voice", "VoiceSettings", "DEFAULT_VOICE", "__version__"]
@@ -23,7 +22,7 @@ from livekit.agents import Plugin
 
 class ElevenLabsPlugin(Plugin):
     def __init__(self):
-        super().__init__(__name__, __version__)
+        super().__init__(__name__, __version__, __package__)
 
     def download_files(self):
         pass

livekit/plugins/elevenlabs/tts.py

@@ -12,18 +12,20 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import contextlib
 import asyncio
-import logging
 import base64
+import contextlib
 import dataclasses
 import json
+import logging
 import os
 from dataclasses import dataclass
-from typing import List, Optional
+from typing import Any, AsyncIterable, Dict, List, Optional
+
 import aiohttp
 from livekit import rtc
 from livekit.agents import tts
+
 from .models import TTSModels
 
 
@@ -101,37 +103,40 @@ class TTS(tts.TTS):
             data = await resp.json()
             return dict_to_voices_list(data)
 
-    async def synthesize(
+    def synthesize(
         self,
-        *,
         text: str,
-    ) -> tts.SynthesizedAudio:
+    ) -> AsyncIterable[tts.SynthesizedAudio]:
         voice = self._config.voice
-        async with self._session.post(
-            f"{self._config.base_url}/text-to-speech/{voice.id}?output_format=pcm_44100",
-            headers={AUTHORIZATION_HEADER: self._config.api_key},
-            json=dict(
-                text=text,
-                model_id=self._config.model_id,
-                voice_settings=dataclasses.asdict(voice.settings)
-                if voice.settings
-                else None,
-            ),
-        ) as resp:
-            data = await resp.read()
-            return tts.SynthesizedAudio(
-                text=text,
-                data=rtc.AudioFrame(
-                    data=data,
-                    sample_rate=44100,
-                    num_channels=1,
-                    samples_per_channel=len(data) // 2,  # 16-bit
+
+        async def generator():
+            async with self._session.post(
+                f"{self._config.base_url}/text-to-speech/{voice.id}?output_format=pcm_44100",
+                headers={AUTHORIZATION_HEADER: self._config.api_key},
+                json=dict(
+                    text=text,
+                    model_id=self._config.model_id,
+                    voice_settings=dataclasses.asdict(voice.settings)
+                    if voice.settings
+                    else None,
                 ),
-            )
+            ) as resp:
+                data = await resp.read()
+                yield tts.SynthesizedAudio(
+                    text=text,
+                    data=rtc.AudioFrame(
+                        data=data,
+                        sample_rate=44100,
+                        num_channels=1,
+                        samples_per_channel=len(data) // 2,  # 16-bit
+                    ),
+                )
+
+        return generator()
 
     def stream(
         self,
-    ) -> tts.SynthesizeStream:
+    ) -> "SynthesizeStream":
         return SynthesizeStream(self._session, self._config)
 
 
@@ -163,7 +168,7 @@ class SynthesizeStream(tts.SynthesizeStream):
         model_id = self._config.model_id
         return f"{base_url}/text-to-speech/{voice_id}/stream-input?model_id={model_id}&output_format=pcm_{self._config.sample_rate}&optimize_streaming_latency={self._config.latency}"
 
-    def push_text(self, token: str) -> None:
+    def push_text(self, token: str | None) -> None:
         if self._closed:
             raise ValueError("cannot push to a closed stream")
 
@@ -283,9 +288,9 @@ class SynthesizeStream(tts.SynthesizeStream):
             if msg.type != aiohttp.WSMsgType.TEXT:
                 continue
 
-            msg = json.loads(msg.data)
-            if msg.get("audio"):
-                data = base64.b64decode(msg["audio"])
+            jsonMessage: Dict[str, Any] = json.loads(str(msg.data))
+            if jsonMessage.get("audio"):
+                data = base64.b64decode(jsonMessage["audio"])
                 audio_frame = rtc.AudioFrame(
                     data=data,
                     sample_rate=self._config.sample_rate,
@@ -298,7 +303,7 @@ class SynthesizeStream(tts.SynthesizeStream):
                         audio=tts.SynthesizedAudio(text="", data=audio_frame),
                     )
                 )
-            elif msg.get("isFinal"):
+            elif jsonMessage.get("isFinal"):
                 break
             else:
                 logging.error(f"Unhandled message from ElevenLabs: {msg}")
@@ -309,7 +314,11 @@ class SynthesizeStream(tts.SynthesizeStream):
         self._queue.put_nowait(STREAM_EOS)
         await self._queue.join()
 
-    async def aclose(self) -> None:
+    async def aclose(self, wait=False) -> None:
+        if wait:
+            logging.warning(
+                "wait=True is not yet supported for ElevenLabs TTS. Closing immediately."
+            )
         self._main_task.cancel()
         with contextlib.suppress(asyncio.CancelledError):
             await self._main_task

livekit/plugins/elevenlabs/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"

{livekit_plugins_elevenlabs-0.2.0.dist-info → livekit_plugins_elevenlabs-0.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: livekit-plugins-elevenlabs
-Version: 0.2.0
+Version: 0.3.0
 Summary: Agent Framework plugin for voice synthesis with ElevenLabs' API.
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0
@@ -19,8 +19,8 @@ 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 >=0.9.0
-Requires-Dist: livekit-agents >=0.3.0
+Requires-Dist: livekit ~=0.9
+Requires-Dist: livekit-agents ~=0.5.dev0
 Requires-Dist: aiohttp >=3.8.5
 
 # LiveKit Plugins Elevenlabs

livekit_plugins_elevenlabs-0.3.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+livekit/plugins/elevenlabs/__init__.py,sha256=_IMIfE4YA7d3NxrN-iCrdfQ19mwh93SY676RJGEA57c,989
+livekit/plugins/elevenlabs/models.py,sha256=g46mCMMHP3x3qtHmybHHMcid1UwmjKCcF0T4IWjMjWE,163
+livekit/plugins/elevenlabs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/elevenlabs/tts.py,sha256=hN9aRGQ_9B9ehnB7cS19gtZ3uHIa-28RPoIIRZrdm-w,11503
+livekit/plugins/elevenlabs/version.py,sha256=G5iYozum4q7UpHwW43F7QfhzUfwcncPxBZ0gmUGsd5I,600
+livekit_plugins_elevenlabs-0.3.0.dist-info/METADATA,sha256=vY-Re5myy-A_j253KS9MNz7LGmE2TL5Trr6q54JnegQ,1361
+livekit_plugins_elevenlabs-0.3.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+livekit_plugins_elevenlabs-0.3.0.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
+livekit_plugins_elevenlabs-0.3.0.dist-info/RECORD,,

{livekit_plugins_elevenlabs-0.2.0.dist-info → livekit_plugins_elevenlabs-0.3.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: bdist_wheel (0.43.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

livekit_plugins_elevenlabs-0.2.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-livekit/plugins/elevenlabs/__init__.py,sha256=-FQ-hnTqqbaVFa0sEu8CwInVp9vzkt-nRWkd34ruFFk,977
-livekit/plugins/elevenlabs/models.py,sha256=g46mCMMHP3x3qtHmybHHMcid1UwmjKCcF0T4IWjMjWE,163
-livekit/plugins/elevenlabs/tts.py,sha256=L9k2jttTbkcv7qsKiamdR75MRGT3EfSQ7L6k-pkhDeY,11114
-livekit/plugins/elevenlabs/version.py,sha256=cLFCdnm5S21CiJ5UJBcqfRvvFkCQ8p6M5fFUJVJkEiM,600
-livekit_plugins_elevenlabs-0.2.0.dist-info/METADATA,sha256=sQ37PzuaXiCMjaeImY64h3QfvtbkUzui0zhNxl9Oebc,1360
-livekit_plugins_elevenlabs-0.2.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-livekit_plugins_elevenlabs-0.2.0.dist-info/top_level.txt,sha256=OoDok3xUmXbZRvOrfvvXB-Juu4DX79dlq188E19YHoo,8
-livekit_plugins_elevenlabs-0.2.0.dist-info/RECORD,,