livekit-plugins-aws 0.1.0__tar.gz → 0.1.1__tar.gz

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: livekit-plugins-aws
-Version: 0.1.0
+Version: 0.1.1
 Summary: LiveKit Agents Plugin for services from AWS
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0
@@ -19,7 +19,7 @@ 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-agents>=0.12.0
+Requires-Dist: livekit-agents[codecs]<1.0.0,>=0.12.16
 Requires-Dist: aiobotocore==2.19.0
 Requires-Dist: boto3==1.36.3
 Requires-Dist: amazon-transcribe>=0.6.2

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/livekit/plugins/aws/models.py

@@ -45,4 +45,4 @@ TTS_LANGUAGE = Literal[
     "de-CH",
 ]
 
-TTS_OUTPUT_FORMAT = Literal["pcm", "mp3"]
+TTS_OUTPUT_FORMAT = Literal["mp3"]

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/livekit/plugins/aws/tts.py

@@ -18,7 +18,6 @@ from typing import Any, Callable, Optional
 
 import aiohttp
 from aiobotocore.session import AioSession, get_session
-from livekit import rtc
 from livekit.agents import (
     APIConnectionError,
     APIConnectOptions,
@@ -29,10 +28,9 @@ from livekit.agents import (
 )
 
 from ._utils import _get_aws_credentials
-from .models import TTS_LANGUAGE, TTS_OUTPUT_FORMAT, TTS_SPEECH_ENGINE
+from .models import TTS_LANGUAGE, TTS_SPEECH_ENGINE
 
 TTS_NUM_CHANNELS: int = 1
-DEFAULT_OUTPUT_FORMAT: TTS_OUTPUT_FORMAT = "pcm"
 DEFAULT_SPEECH_ENGINE: TTS_SPEECH_ENGINE = "generative"
 DEFAULT_SPEECH_REGION = "us-east-1"
 DEFAULT_VOICE = "Ruth"
@@ -43,7 +41,6 @@ DEFAULT_SAMPLE_RATE = 16000
 class _TTSOptions:
     # https://docs.aws.amazon.com/polly/latest/dg/API_SynthesizeSpeech.html
     voice: str | None
-    output_format: TTS_OUTPUT_FORMAT
     speech_engine: TTS_SPEECH_ENGINE
     speech_region: str
     sample_rate: int
@@ -56,7 +53,6 @@ class TTS(tts.TTS):
         *,
         voice: str | None = DEFAULT_VOICE,
         language: TTS_LANGUAGE | str | None = None,
-        output_format: TTS_OUTPUT_FORMAT = DEFAULT_OUTPUT_FORMAT,
         speech_engine: TTS_SPEECH_ENGINE = DEFAULT_SPEECH_ENGINE,
         sample_rate: int = DEFAULT_SAMPLE_RATE,
         speech_region: str = DEFAULT_SPEECH_REGION,
@@ -75,7 +71,6 @@ class TTS(tts.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).
-            output_format(TTS_OUTPUT_FORMAT, optional): The format in which the returned output will be encoded. Defaults to "pcm".
             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".
             speech_region(str, optional): The region to use for the synthesis. Defaults to "us-east-1".
@@ -96,7 +91,6 @@ class TTS(tts.TTS):
 
         self._opts = _TTSOptions(
             voice=voice,
-            output_format=output_format,
             speech_engine=speech_engine,
             speech_region=speech_region,
             language=language,
@@ -149,7 +143,7 @@ class ChunkedStream(tts.ChunkedStream):
             async with self._get_client() as client:
                 params = {
                     "Text": self._input_text,
-                    "OutputFormat": self._opts.output_format,
+                    "OutputFormat": "mp3",
                     "Engine": self._opts.speech_engine,
                     "VoiceId": self._opts.voice,
                     "TextType": "text",
@@ -158,32 +152,36 @@ class ChunkedStream(tts.ChunkedStream):
                 }
                 response = await client.synthesize_speech(**_strip_nones(params))
                 if "AudioStream" in response:
-                    decoder = utils.codecs.Mp3StreamDecoder()
-                    async with response["AudioStream"] as resp:
-                        async for data, _ in resp.content.iter_chunks():
-                            if self._opts.output_format == "mp3":
-                                frames = decoder.decode_chunk(data)
-                                for frame in frames:
-                                    self._event_ch.send_nowait(
-                                        tts.SynthesizedAudio(
-                                            request_id=request_id,
-                                            segment_id=self._segment_id,
-                                            frame=frame,
-                                        )
-                                    )
-                            else:
-                                self._event_ch.send_nowait(
-                                    tts.SynthesizedAudio(
-                                        request_id=request_id,
-                                        segment_id=self._segment_id,
-                                        frame=rtc.AudioFrame(
-                                            data=data,
-                                            sample_rate=self._opts.sample_rate,
-                                            num_channels=1,
-                                            samples_per_channel=len(data) // 2,
-                                        ),
-                                    )
-                                )
+                    decoder = utils.codecs.AudioStreamDecoder(
+                        sample_rate=self._opts.sample_rate,
+                        num_channels=1,
+                    )
+
+                    # Create a task to push data to the decoder
+                    async def push_data():
+                        try:
+                            async with response["AudioStream"] as resp:
+                                async for data, _ in resp.content.iter_chunks():
+                                    decoder.push(data)
+                        finally:
+                            decoder.end_input()
+
+                    # Start pushing data to the decoder
+                    push_task = asyncio.create_task(push_data())
+
+                    try:
+                        # Create emitter and process decoded frames
+                        emitter = tts.SynthesizedAudioEmitter(
+                            event_ch=self._event_ch,
+                            request_id=request_id,
+                            segment_id=self._segment_id,
+                        )
+                        async for frame in decoder:
+                            emitter.push(frame)
+                        emitter.flush()
+                        await push_task
+                    finally:
+                        await utils.aio.gracefully_cancel(push_task)
 
         except asyncio.TimeoutError as e:
             raise APITimeoutError() from e

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/livekit/plugins/aws/version.py

@@ -12,4 +12,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "0.1.0"
+__version__ = "0.1.1"

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/livekit_plugins_aws.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: livekit-plugins-aws
-Version: 0.1.0
+Version: 0.1.1
 Summary: LiveKit Agents Plugin for services from AWS
 Home-page: https://github.com/livekit/agents
 License: Apache-2.0
@@ -19,7 +19,7 @@ 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-agents>=0.12.0
+Requires-Dist: livekit-agents[codecs]<1.0.0,>=0.12.16
 Requires-Dist: aiobotocore==2.19.0
 Requires-Dist: boto3==1.36.3
 Requires-Dist: amazon-transcribe>=0.6.2

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/livekit_plugins_aws.egg-info/requires.txt

@@ -1,4 +1,4 @@
-livekit-agents>=0.12.0
+livekit-agents[codecs]<1.0.0,>=0.12.16
 aiobotocore==2.19.0
 boto3==1.36.3
 amazon-transcribe>=0.6.2

{livekit_plugins_aws-0.1.0 → livekit_plugins_aws-0.1.1}/setup.py

@@ -48,7 +48,7 @@ setuptools.setup(
     packages=setuptools.find_namespace_packages(include=["livekit.*"]),
     python_requires=">=3.9.0",
     install_requires=[
-        "livekit-agents>=0.12.0",
+        "livekit-agents[codecs]>=0.12.16,<1.0.0",
         "aiobotocore==2.19.0",
         "boto3==1.36.3",
         "amazon-transcribe>=0.6.2",