livekit-plugins-elevenlabs 1.0.0rc8__py3-none-any.whl → 1.0.1__py3-none-any.whl

livekit/plugins/elevenlabs/__init__.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 from .models import TTSEncoding, TTSModels
-from .tts import DEFAULT_VOICE, TTS, Voice, VoiceSettings
+from .tts import DEFAULT_VOICE_ID, TTS, Voice, VoiceSettings
 from .version import __version__
 
 __all__ = [
@@ -22,7 +22,7 @@ __all__ = [
     "VoiceSettings",
     "TTSEncoding",
     "TTSModels",
-    "DEFAULT_VOICE",
+    "DEFAULT_VOICE_ID",
     "__version__",
 ]
 

livekit/plugins/elevenlabs/tts.py

@@ -68,22 +68,9 @@ class Voice:
     id: str
     name: str
     category: str
-    settings: NotGivenOr[VoiceSettings] = NOT_GIVEN
-
-
-DEFAULT_VOICE = Voice(
-    id="EXAVITQu4vr4xnSDxMaL",
-    name="Bella",
-    category="premade",
-    settings=VoiceSettings(
-        stability=0.71,
-        speed=1.0,
-        similarity_boost=0.5,
-        style=0.0,
-        use_speaker_boost=True,
-    ),
-)
 
+
+DEFAULT_VOICE_ID = "EXAVITQu4vr4xnSDxMaL"
 API_BASE_URL_V1 = "https://api.elevenlabs.io/v1"
 AUTHORIZATION_HEADER = "xi-api-key"
 WS_INACTIVITY_TIMEOUT = 300
@@ -92,7 +79,8 @@ WS_INACTIVITY_TIMEOUT = 300
 @dataclass
 class _TTSOptions:
     api_key: str
-    voice: Voice
+    voice_id: str
+    voice_settings: NotGivenOr[VoiceSettings]
     model: TTSModels | str
     language: NotGivenOr[str]
     base_url: str
@@ -109,7 +97,8 @@ class TTS(tts.TTS):
     def __init__(
         self,
         *,
-        voice: Voice = DEFAULT_VOICE,
+        voice_id: str = DEFAULT_VOICE_ID,
+        voice_settings: NotGivenOr[VoiceSettings] = NOT_GIVEN,
         model: TTSModels | str = "eleven_flash_v2_5",
         encoding: NotGivenOr[TTSEncoding] = NOT_GIVEN,
         api_key: NotGivenOr[str] = NOT_GIVEN,
@@ -126,15 +115,16 @@ class TTS(tts.TTS):
         Create a new instance of ElevenLabs TTS.
 
         Args:
-            voice (Voice): Voice configuration. Defaults to `DEFAULT_VOICE`.
+            voice_id (str): Voice ID. Defaults to `DEFAULT_VOICE_ID`.
+            voice_settings (NotGivenOr[VoiceSettings]): Voice settings.
             model (TTSModels | str): TTS model to use. Defaults to "eleven_turbo_v2_5".
-            api_key (str | None): ElevenLabs API key. Can be set via argument or `ELEVEN_API_KEY` environment variable.
-            base_url (str | None): Custom base URL for the API. Optional.
-            streaming_latency (int): Optimize for streaming latency, defaults to 0 - disabled. 4 for max latency optimizations. deprecated
+            api_key (NotGivenOr[str]): ElevenLabs API key. Can be set via argument or `ELEVEN_API_KEY` environment variable.
+            base_url (NotGivenOr[str]): Custom base URL for the API. Optional.
+            streaming_latency (NotGivenOr[int]): Optimize for streaming latency, defaults to 0 - disabled. 4 for max latency optimizations. deprecated
             inactivity_timeout (int): Inactivity timeout in seconds for the websocket connection. Defaults to 300.
-            word_tokenizer (tokenize.WordTokenizer): Tokenizer for processing text. Defaults to basic WordTokenizer.
+            word_tokenizer (NotGivenOr[tokenize.WordTokenizer]): Tokenizer for processing text. Defaults to basic WordTokenizer.
             enable_ssml_parsing (bool): Enable SSML parsing for input text. Defaults to False.
-            chunk_length_schedule (list[int]): Schedule for chunk lengths, ranging from 50 to 500. Defaults to [80, 120, 200, 260].
+            chunk_length_schedule (NotGivenOr[list[int]]): Schedule for chunk lengths, ranging from 50 to 500. Defaults to [80, 120, 200, 260].
             http_session (aiohttp.ClientSession | None): Custom HTTP session for API requests. Optional.
             language (NotGivenOr[str]): Language code for the TTS model, as of 10/24/24 only valid for "eleven_turbo_v2_5".
         """  # noqa: E501
@@ -165,7 +155,8 @@ class TTS(tts.TTS):
             )
 
         self._opts = _TTSOptions(
-            voice=voice,
+            voice_id=voice_id,
+            voice_settings=voice_settings,
             model=model,
             api_key=elevenlabs_api_key,
             base_url=base_url if is_given(base_url) else API_BASE_URL_V1,
@@ -197,20 +188,24 @@ class TTS(tts.TTS):
     def update_options(
         self,
         *,
-        voice: NotGivenOr[Voice] = NOT_GIVEN,
+        voice_id: NotGivenOr[str] = NOT_GIVEN,
+        voice_settings: NotGivenOr[VoiceSettings] = NOT_GIVEN,
         model: NotGivenOr[TTSModels | str] = NOT_GIVEN,
         language: NotGivenOr[str] = NOT_GIVEN,
     ) -> None:
         """
         Args:
-            voice (NotGivenOr[Voice]): Voice configuration.
+            voice_id (NotGivenOr[str]): Voice ID.
+            voice_settings (NotGivenOr[VoiceSettings]): Voice settings.
             model (NotGivenOr[TTSModels | str]): TTS model to use.
             language (NotGivenOr[str]): Language code for the TTS model.
         """
         if is_given(model):
             self._opts.model = model
-        if is_given(voice):
-            self._opts.voice = voice
+        if is_given(voice_id):
+            self._opts.voice_id = voice_id
+        if is_given(voice_settings):
+            self._opts.voice_settings = voice_settings
         if is_given(language):
             self._opts.language = language
 
@@ -265,8 +260,8 @@ class ChunkedStream(tts.ChunkedStream):
     async def _run(self) -> None:
         request_id = utils.shortuuid()
         voice_settings = (
-            _strip_nones(dataclasses.asdict(self._opts.voice.settings))
-            if is_given(self._opts.voice.settings)
+            _strip_nones(dataclasses.asdict(self._opts.voice_settings))
+            if is_given(self._opts.voice_settings)
             else None
         )
         data = {
@@ -405,8 +400,8 @@ class SynthesizeStream(tts.SynthesizeStream):
         # 11labs protocol expects the first message to be an "init msg"
         init_pkt = {
             "text": " ",
-            "voice_settings": _strip_nones(dataclasses.asdict(self._opts.voice.settings))
-            if is_given(self._opts.voice.settings)
+            "voice_settings": _strip_nones(dataclasses.asdict(self._opts.voice_settings))
+            if is_given(self._opts.voice_settings)
             else None,
             "generation_config": {"chunk_length_schedule": self._opts.chunk_length_schedule},
         }
@@ -536,7 +531,6 @@ def _dict_to_voices_list(data: dict[str, Any]):
                 id=voice["voice_id"],
                 name=voice["name"],
                 category=voice["category"],
-                settings=None,
             )
         )
     return voices
@@ -548,7 +542,7 @@ def _strip_nones(data: dict[str, Any]):
 
 def _synthesize_url(opts: _TTSOptions) -> str:
     base_url = opts.base_url
-    voice_id = opts.voice.id
+    voice_id = opts.voice_id
     model_id = opts.model
     output_format = opts.encoding
     url = (
@@ -562,7 +556,7 @@ def _synthesize_url(opts: _TTSOptions) -> str:
 
 def _stream_url(opts: _TTSOptions) -> str:
     base_url = opts.base_url
-    voice_id = opts.voice.id
+    voice_id = opts.voice_id
     model_id = opts.model
     output_format = opts.encoding
     enable_ssml = str(opts.enable_ssml_parsing).lower()

livekit/plugins/elevenlabs/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = '1.0.0.rc8'
+__version__ = "1.0.1"

{livekit_plugins_elevenlabs-1.0.0rc8.dist-info → livekit_plugins_elevenlabs-1.0.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-elevenlabs
-Version: 1.0.0rc8
+Version: 1.0.1
 Summary: Agent Framework plugin for voice synthesis with ElevenLabs' API.
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
@@ -18,7 +18,7 @@ Classifier: Topic :: Multimedia :: Sound/Audio
 Classifier: Topic :: Multimedia :: Video
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0
-Requires-Dist: livekit-agents[codecs]>=1.0.0.rc8
+Requires-Dist: livekit-agents[codecs]>=1.0.1
 Description-Content-Type: text/markdown
 
 # LiveKit Plugins Elevenlabs

livekit_plugins_elevenlabs-1.0.1.dist-info/RECORD

@@ -0,0 +1,9 @@
+livekit/plugins/elevenlabs/__init__.py,sha256=Va24UYTuuosmRuTcuzd_DIHYQOgV-wSYKJIXmOSB2Go,1255
+livekit/plugins/elevenlabs/log.py,sha256=hIuXqDsEB5GBa7rQY3z4Uqi1oCqc_lRmCHZEmXz0LHw,73
+livekit/plugins/elevenlabs/models.py,sha256=p_wHEz15bdsNEqwzN831ysm70PNWQ-xeN__BKvGPZxA,401
+livekit/plugins/elevenlabs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+livekit/plugins/elevenlabs/tts.py,sha256=gs9p4TwBAYX3vlsNn2XQ-oyPNUGcuvgix8K7vChRMmc,19985
+livekit/plugins/elevenlabs/version.py,sha256=TtCLsefaBT9ruij-b2hjHqy9SEqKIZtjDkEw0g9Py1U,600
+livekit_plugins_elevenlabs-1.0.1.dist-info/METADATA,sha256=pspnb5LTpttYVM8mimJNFVVvmzQ6wqCMvimS7_LSep8,1312
+livekit_plugins_elevenlabs-1.0.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+livekit_plugins_elevenlabs-1.0.1.dist-info/RECORD,,

livekit_plugins_elevenlabs-1.0.0rc8.dist-info/RECORD

@@ -1,9 +0,0 @@
-livekit/plugins/elevenlabs/__init__.py,sha256=YZVadomFq3JWiZN6GWXJbuE4vaNNWq1CmdH25du8qwg,1249
-livekit/plugins/elevenlabs/log.py,sha256=hIuXqDsEB5GBa7rQY3z4Uqi1oCqc_lRmCHZEmXz0LHw,73
-livekit/plugins/elevenlabs/models.py,sha256=p_wHEz15bdsNEqwzN831ysm70PNWQ-xeN__BKvGPZxA,401
-livekit/plugins/elevenlabs/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/elevenlabs/tts.py,sha256=rrCtSEJT9MUk1wb-xJLcbmDmJNyXVOn8WN6eS8ATYRA,19783
-livekit/plugins/elevenlabs/version.py,sha256=5qCM_eosxi507YOAQ3_Cf_-PVZbiE3NumVYwZ2yRcHQ,604
-livekit_plugins_elevenlabs-1.0.0rc8.dist-info/METADATA,sha256=2R7jsUiJklzTM57PlqxEXrqPmmo6sK-6cMiMO4WbpxY,1319
-livekit_plugins_elevenlabs-1.0.0rc8.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-livekit_plugins_elevenlabs-1.0.0rc8.dist-info/RECORD,,