Code review feedback

CHANGELOG.md

@@ -9,7 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
-- Added AWS Polly TTS support.
+- Added AWS Polly TTS support and `07m-interruptible-aws.py` as an example.
 
 - Added InputParams to Azure TTS service.
 

examples/foundational/07m-interruptible-aws.py

@@ -22,6 +22,7 @@ from pipecat.processors.aggregators.llm_response import (
     LLMUserResponseAggregator,
 )
 from pipecat.services.aws import AWSTTSService
+from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 from pipecat.vad.silero import SileroVADAnalyzer
@@ -43,12 +44,14 @@ async def main():
             DailyParams(
                 audio_out_enabled=True,
                 audio_out_sample_rate=16000,
-                transcription_enabled=True,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
             ),
         )
 
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
         tts = AWSTTSService(
             api_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
             aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
@@ -72,6 +75,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,  # STT
                 tma_in,  # User responses
                 llm,  # LLM
                 tts,  # TTS

src/pipecat/services/aws.py

@@ -9,6 +9,7 @@ from loguru import logger
 from pydantic import BaseModel
 
 from pipecat.frames.frames import (
+    ErrorFrame,
     Frame,
     TTSAudioRawFrame,
     TTSStartedFrame,
@@ -152,7 +153,7 @@ class AWSTTSService(TTSService):
             if "AudioStream" in response:
                 with response["AudioStream"] as stream:
                     audio_data = stream.read()
-                    chunk_size = 4096  # You can adjust this value
+                    chunk_size = 8192
                     for i in range(0, len(audio_data), chunk_size):
                         chunk = audio_data[i : i + chunk_size]
                         if len(chunk) > 0:
@@ -164,3 +165,8 @@ class AWSTTSService(TTSService):
 
         except (BotoCoreError, ClientError) as error:
             logger.exception(f"{self} error generating TTS: {error}")
+            error_message = f"AWS Polly TTS error: {str(error)}"
+            yield ErrorFrame(error=error_message)
+
+        finally:
+            await self.push_frame(TTSStoppedFrame())