livekit-plugins-aws 1.2.5__tar.gz → 1.2.7__tar.gz

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-aws
-Version: 1.2.5
+Version: 1.2.7
 Summary: LiveKit Agents Plugin for services from AWS
 Project-URL: Documentation, https://docs.livekit.io
 Project-URL: Website, https://livekit.io/
@@ -19,8 +19,8 @@ Classifier: Topic :: Multimedia :: Video
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0
 Requires-Dist: aioboto3>=14.1.0
-Requires-Dist: amazon-transcribe>=0.6.2
-Requires-Dist: livekit-agents>=1.2.5
+Requires-Dist: amazon-transcribe>=0.6.4
+Requires-Dist: livekit-agents>=1.2.7
 Provides-Extra: realtime
 Requires-Dist: aws-sdk-bedrock-runtime==0.0.2; (python_version >= '3.12') and extra == 'realtime'
 Requires-Dist: boto3>1.35.10; extra == 'realtime'

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/livekit/plugins/aws/models.py

@@ -46,3 +46,4 @@ TTSLanguages = Literal[
 ]
 
 TTSEncoding = Literal["mp3"]
+TTSTextType = Literal["text", "ssml"]

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/livekit/plugins/aws/stt.py

@@ -192,7 +192,7 @@ class SpeechStream(stt.SpeechStream):
                     self._event_ch.send_nowait(
                         stt.SpeechEvent(
                             type=stt.SpeechEventType.INTERIM_TRANSCRIPT,
-                            alternatives=[_streaming_recognize_response_to_speech_data(resp)],
+                            alternatives=[self._streaming_recognize_response_to_speech_data(resp)],
                         )
                     )
 
@@ -200,20 +200,22 @@ class SpeechStream(stt.SpeechStream):
                     self._event_ch.send_nowait(
                         stt.SpeechEvent(
                             type=stt.SpeechEventType.FINAL_TRANSCRIPT,
-                            alternatives=[_streaming_recognize_response_to_speech_data(resp)],
+                            alternatives=[self._streaming_recognize_response_to_speech_data(resp)],
                         )
                     )
 
             if not resp.is_partial:
                 self._event_ch.send_nowait(stt.SpeechEvent(type=stt.SpeechEventType.END_OF_SPEECH))
 
-
-def _streaming_recognize_response_to_speech_data(resp: Result) -> stt.SpeechData:
-    data = stt.SpeechData(
-        language="en-US",
-        start_time=resp.start_time if resp.start_time else 0.0,
-        end_time=resp.end_time if resp.end_time else 0.0,
-        text=resp.alternatives[0].transcript if resp.alternatives else "",
-    )
-
-    return data
+    def _streaming_recognize_response_to_speech_data(self, resp: Result) -> stt.SpeechData:
+        confidence = 0.0
+        if resp.alternatives and (items := resp.alternatives[0].items):
+            confidence = items[0].confidence or 0.0
+
+        return stt.SpeechData(
+            language=resp.language_code or self._opts.language,
+            start_time=resp.start_time if resp.start_time is not None else 0.0,
+            end_time=resp.end_time if resp.end_time is not None else 0.0,
+            text=resp.alternatives[0].transcript if resp.alternatives else "",
+            confidence=confidence,
+        )

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/livekit/plugins/aws/tts.py

@@ -32,11 +32,12 @@ from livekit.agents.types import (
 )
 from livekit.agents.utils import is_given
 
-from .models import TTSLanguages, TTSSpeechEngine
+from .models import TTSLanguages, TTSSpeechEngine, TTSTextType
 from .utils import _strip_nones
 
 DEFAULT_SPEECH_ENGINE: TTSSpeechEngine = "generative"
 DEFAULT_VOICE = "Ruth"
+DEFAULT_TEXT_TYPE: TTSTextType = "text"
 
 
 @dataclass
@@ -47,6 +48,7 @@ class _TTSOptions:
     region: str | None
     sample_rate: int
     language: TTSLanguages | str | None
+    text_type: TTSTextType
 
 
 class TTS(tts.TTS):
@@ -56,6 +58,7 @@ class TTS(tts.TTS):
         voice: str = "Ruth",
         language: NotGivenOr[TTSLanguages | str] = NOT_GIVEN,
         speech_engine: TTSSpeechEngine = "generative",
+        text_type: TTSTextType = "text",
         sample_rate: int = 16000,
         region: str | None = None,
         api_key: str | None = None,
@@ -71,10 +74,11 @@ class TTS(tts.TTS):
         See https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html for more details on the the AWS Polly TTS.
 
         Args:
-            Voice (TTSModels, optional): Voice ID to use for the synthesis. Defaults to "Ruth".
-            language (TTS_LANGUAGE, optional): language code for the Synthesize Speech request. This is only necessary if using a bilingual voice, such as Aditi, which can be used for either Indian English (en-IN) or Hindi (hi-IN).
+            voice (TTSModels, optional): Voice ID to use for the synthesis. Defaults to "Ruth".
+            language (TTSLanguages, optional): language code for the Synthesize Speech request. This is only necessary if using a bilingual voice, such as Aditi, which can be used for either Indian English (en-IN) or Hindi (hi-IN).
+            speech_engine(TTSSpeechEngine, optional): The engine to use for the synthesis. Defaults to "generative".
+            text_type(TTSTextType, optional): Type of text to synthesize. Use "ssml" for SSML-enhanced text. Defaults to "text".
             sample_rate(int, optional): The audio frequency specified in Hz. Defaults to 16000.
-            speech_engine(TTS_SPEECH_ENGINE, optional): The engine to use for the synthesis. Defaults to "generative".
             region(str, optional): The region to use for the synthesis. Defaults to "us-east-1".
             api_key(str, optional): AWS access key id.
             api_secret(str, optional): AWS secret access key.
@@ -96,6 +100,7 @@ class TTS(tts.TTS):
         self._opts = _TTSOptions(
             voice=voice,
             speech_engine=speech_engine,
+            text_type=text_type,
             region=region or None,
             language=language or None,
             sample_rate=sample_rate,
@@ -130,7 +135,7 @@ class ChunkedStream(tts.ChunkedStream):
                             "OutputFormat": "mp3",
                             "Engine": self._opts.speech_engine,
                             "VoiceId": self._opts.voice,
-                            "TextType": "text",
+                            "TextType": self._opts.text_type,
                             "SampleRate": str(self._opts.sample_rate),
                             "LanguageCode": self._opts.language,
                         }

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/livekit/plugins/aws/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.2.5"
+__version__ = "1.2.7"

{livekit_plugins_aws-1.2.5 → livekit_plugins_aws-1.2.7}/pyproject.toml

@@ -23,9 +23,9 @@ classifiers = [
     "Programming Language :: Python :: 3 :: Only",
 ]
 dependencies = [
-    "livekit-agents>=1.2.5",
+    "livekit-agents>=1.2.7",
     "aioboto3>=14.1.0",
-    "amazon-transcribe>=0.6.2",
+    "amazon-transcribe>=0.6.4",
 ]
 
 [project.optional-dependencies]