livekit-plugins-hume 1.2.3__py3-none-any.whl → 1.3.5__py3-none-any.whl

livekit/plugins/hume/__init__.py

@@ -34,6 +34,7 @@ from .version import __version__
 __all__ = [
     "TTS",
     "AudioFormat",
+    "ModelVersion",
     "VoiceById",
     "VoiceByName",
     "VoiceProvider",

livekit/plugins/hume/tts.py

@@ -20,7 +20,7 @@ import json
 import os
 from dataclasses import dataclass, replace
 from enum import Enum
-from typing import Any, TypedDict
+from typing import Any, Literal, TypedDict
 
 import aiohttp
 
@@ -73,6 +73,9 @@ class AudioFormat(str, Enum):
     pcm = "pcm"
 
 
+ModelVersion = Literal["1", "2"]
+
+
 DEFAULT_HEADERS = {
     "X-Hume-Client-Name": "livekit",
     "X-Hume-Client-Version": __version__,
@@ -89,6 +92,7 @@ class _TTSOptions:
     api_key: str
     base_url: str
     voice: VoiceById | VoiceByName | None
+    model_version: ModelVersion | None
     description: str | None
     speed: float | None
     trailing_silence: float | None
@@ -106,6 +110,7 @@ class TTS(tts.TTS):
         *,
         api_key: str | None = None,
         voice: VoiceById | VoiceByName | None = DEFAULT_VOICE,
+        model_version: ModelVersion | None = "1",
         description: str | None = None,
         speed: float | None = None,
         trailing_silence: float | None = None,
@@ -121,10 +126,12 @@ class TTS(tts.TTS):
         Args:
             api_key: Hume AI API key. If not provided, will look for HUME_API_KEY environment
                 variable.
-            voice: A voice from the voice library specifed by name or id.
+            voice: A voice from the voice library specified by name or id.
+            model_version: Specifies which version of Octave to use. See Hume's documentation for
+                details on model version differences: https://dev.hume.ai/docs/text-to-speech-tts/overview.
             description: Natural language instructions describing how the synthesized speech
                 should sound (≤1000 characters).
-            speed: Speed multiplier for the synthesized speech (≥0.25, ≤3.0, default: 1.0).
+            speed: Speed multiplier for the synthesized speech (≥0.5, ≤2.0, default: 1.0).
             trailing_silence: Duration of trailing silence (in seconds) to add to each utterance
                 (≥0, ≤5.0, default: 0.35).
             context: Optional context for synthesis, either as text or list of utterances.
@@ -157,6 +164,7 @@ class TTS(tts.TTS):
         self._opts = _TTSOptions(
             api_key=key,
             voice=voice,
+            model_version=model_version,
             description=description,
             speed=speed,
             trailing_silence=trailing_silence,
@@ -167,6 +175,14 @@ class TTS(tts.TTS):
         )
         self._session = http_session
 
+    @property
+    def model(self) -> str:
+        return "Octave"
+
+    @property
+    def provider(self) -> str:
+        return "Hume"
+
     def _ensure_session(self) -> aiohttp.ClientSession:
         if not self._session:
             self._session = utils.http_context.http_session()
@@ -187,10 +203,10 @@ class TTS(tts.TTS):
         """Update TTS options used for all future synthesis (until updated again)
 
         Args:
-            voice: A voice from the voice library specifed by name or id.
+            voice: A voice from the voice library specified by name or id.
             description: Natural language instructions describing how the synthesized speech
                 should sound (≤1000 characters).
-            speed: Speed multiplier for the synthesized speech (≥0.25, ≤3.0, default: 1.0).
+            speed: Speed multiplier for the synthesized speech (≥0.5, ≤2.0, default: 1.0).
             trailing_silence: Duration of trailing silence (in seconds) to add to each utterance.
             context: Optional context for synthesis, either as text or list of utterances.
             instant_mode: Whether to use instant mode.
@@ -239,6 +255,7 @@ class ChunkedStream(tts.ChunkedStream):
 
         payload: dict[str, Any] = {
             "utterances": [utterance],
+            "version": self._opts.model_version,
             "strip_headers": True,
             "instant_mode": self._opts.instant_mode,
             "format": {"type": self._opts.audio_format.value},

livekit/plugins/hume/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.2.3"
+__version__ = "1.3.5"

{livekit_plugins_hume-1.2.3.dist-info → livekit_plugins_hume-1.3.5.dist-info}/METADATA

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-hume
-Version: 1.2.3
+Version: 1.3.5
 Summary: Hume TTS plugin for LiveKit agents
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
 Project-URL: Source, https://github.com/livekit/agents
 Author-email: LiveKit <info@livekit.io>
 License-Expression: Apache-2.0
-Keywords: Hume,HumeAI,Octave,audio,livekit,realtime,webrtc
+Keywords: Hume,HumeAI,Octave,ai,audio,livekit,realtime,video,voice
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
@@ -17,7 +17,7 @@ Classifier: Topic :: Multimedia :: Sound/Audio
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0
 Requires-Dist: aiohttp>=3.8.0
-Requires-Dist: livekit-agents>=1.2.3
+Requires-Dist: livekit-agents>=1.3.5
 Description-Content-Type: text/markdown
 
 # Hume AI TTS plugin for LiveKit Agents

livekit_plugins_hume-1.3.5.dist-info/RECORD

@@ -0,0 +1,8 @@
+livekit/plugins/hume/__init__.py,sha256=fhNNbmemEtPTM4Qwsi6-q3wDGyIcywHc4z9hMawQmjk,1394
+livekit/plugins/hume/log.py,sha256=TwpK1FOwgD6Jb0A2nl-9nIgi0q5qWo9HGDrDuV_2g0g,67
+livekit/plugins/hume/py.typed,sha256=Nqnn8clbgv-5l0PgxcTOldg8mkMKrFn4TvPL-rYUUGg,1
+livekit/plugins/hume/tts.py,sha256=12dM7n7eoLspJoBn3_eS6BwCqpSLHyBIk17iza8yAOA,11015
+livekit/plugins/hume/version.py,sha256=6H-6MQWvTBz1H6-_Ga4YEOkRJyH3Sy6H1ZSzAC2CJFU,600
+livekit_plugins_hume-1.3.5.dist-info/METADATA,sha256=WnbsxbcVzTgLvXWoC2ibl1VChI7SDFYYTpphz7rzjwg,1362
+livekit_plugins_hume-1.3.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+livekit_plugins_hume-1.3.5.dist-info/RECORD,,

livekit_plugins_hume-1.2.3.dist-info/RECORD

@@ -1,8 +0,0 @@
-livekit/plugins/hume/__init__.py,sha256=yYTwSJaYq5ufZ_EnoSuLa2FfSsnOZu-swAzYjNQAhhw,1374
-livekit/plugins/hume/log.py,sha256=TwpK1FOwgD6Jb0A2nl-9nIgi0q5qWo9HGDrDuV_2g0g,67
-livekit/plugins/hume/py.typed,sha256=Nqnn8clbgv-5l0PgxcTOldg8mkMKrFn4TvPL-rYUUGg,1
-livekit/plugins/hume/tts.py,sha256=LamNG1FxMKPm4NhV4wXJVu9u-fMaiZB_Qby_VpWjTfY,10451
-livekit/plugins/hume/version.py,sha256=HPlGgKoRBGGxd2wALrVSaLRImqWgzvVFpznNIABDgU8,600
-livekit_plugins_hume-1.2.3.dist-info/METADATA,sha256=3oWceDx5g17_yDvseuBVCm3cWQsjUFcUAoqfIsp3--8,1354
-livekit_plugins_hume-1.2.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-livekit_plugins_hume-1.2.3.dist-info/RECORD,,