livekit-plugins-aws 1.2.5__py3-none-any.whl → 1.2.6__py3-none-any.whl

livekit/plugins/aws/models.py

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

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/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,
@@ -96,6 +99,7 @@ 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 +134,7 @@ 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/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__ = "1.2.6"

{livekit_plugins_aws-1.2.5.dist-info → livekit_plugins_aws-1.2.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: livekit-plugins-aws
-Version: 1.2.5
+Version: 1.2.6
 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>=1.2.6
 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.dist-info → livekit_plugins_aws-1.2.6.dist-info}/RECORD

@@ -1,17 +1,17 @@
 livekit/plugins/aws/__init__.py,sha256=dCZISj1yZG0WZTojk3sU-Ub4PK1ThCVhamrl9k_NbBw,2047
 livekit/plugins/aws/llm.py,sha256=SUPWhJTbQ6HZJEK7WYUADDo2BJZJl2EaRvfG05IobzU,12150
 livekit/plugins/aws/log.py,sha256=S5ICcsnwshZhMG0HPmc_lI3mtHmcY4oQMJBsnnho-bM,289
-livekit/plugins/aws/models.py,sha256=ztI9n3r8OHGlQewWXiyQP3SaavFKHkw-VVuK9Xz4K1I,696
+livekit/plugins/aws/models.py,sha256=J4yzik9sR68RPZpR1ubRQ9hdn14D9IwA3KaRvAf5tAE,734
 livekit/plugins/aws/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-livekit/plugins/aws/stt.py,sha256=zlUrIVVYsSMhtVzXVxHTypW_E2YpMD9EAqvW3lZYj1c,8888
-livekit/plugins/aws/tts.py,sha256=T5dVpTuIuzQimYNnkfXi5dRLmRldWySL4IcbkXjmJLM,6083
+livekit/plugins/aws/stt.py,sha256=sNy7zcAatd7OqhnjfA0C6A3oK1CTaDeuBvEMashjySU,9157
+livekit/plugins/aws/tts.py,sha256=kPWRwqsfwXSMVuFmHc8U4ibJ6mHkQZKLh_S5dhQVFTE,6251
 livekit/plugins/aws/utils.py,sha256=nA5Ua1f4T-25Loar6EvlrKTXI9N-zpTIH7cdQkwGyGI,1518
-livekit/plugins/aws/version.py,sha256=3JgPC-1CyezRI7gGvBZSyMSrxGE-TY9iCMkxdV4uM9Y,600
+livekit/plugins/aws/version.py,sha256=OCvv6KMSdgnrGPol-1roA6aGLQW4B_dSwFfBeuUbZTs,600
 livekit/plugins/aws/experimental/realtime/__init__.py,sha256=mm_TGZc9QAWSO-VOO3PdE8Y5R6xlWckXRZuiFUIHa-Q,287
 livekit/plugins/aws/experimental/realtime/events.py,sha256=ltdGEipE3ZOkjn7K6rKN6WSCUPJkVg-S88mUmQ_V00s,15981
 livekit/plugins/aws/experimental/realtime/pretty_printer.py,sha256=KN7KPrfQu8cU7ff34vFAtfrd1umUSTVNKXQU7D8AMiM,1442
 livekit/plugins/aws/experimental/realtime/realtime_model.py,sha256=JkFv4LnlME17v-yXVvZiFdFyKHZBkKlOffmbUAd7qYw,60403
 livekit/plugins/aws/experimental/realtime/turn_tracker.py,sha256=bcufaap-coeIYuK3ct1Is9W_UoefGYRmnJu7Mn5DCYU,6002
-livekit_plugins_aws-1.2.5.dist-info/METADATA,sha256=fgeWw9L_LntoBpa5Uz5mCML0MLy-DvZZKWQNAyS-81A,1989
-livekit_plugins_aws-1.2.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-livekit_plugins_aws-1.2.5.dist-info/RECORD,,
+livekit_plugins_aws-1.2.6.dist-info/METADATA,sha256=Ev-SpTLbzBP1wuJLm0q-5MOljF2HfmF_S0Ygx5GiquQ,1989
+livekit_plugins_aws-1.2.6.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+livekit_plugins_aws-1.2.6.dist-info/RECORD,,