Take into account VAD start_secs when passing audio data to Smart Turn, and add an extra 500ms of pre-speech audio for good measure

examples/quickstart/bot.py

@@ -36,6 +36,7 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
 
 logger.info("✅ Silero VAD model loaded")
 
+from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
 
@@ -44,7 +45,10 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
 from pipecat.processors.frameworks.rtvi import RTVIConfig, RTVIObserver, RTVIProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -53,6 +57,10 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
+from pipecat.turns.user_stop.turn_analyzer_user_turn_stop_strategy import (
+    TurnAnalyzerUserTurnStopStrategy,
+)
+from pipecat.turns.user_turn_strategies import UserTurnStrategies
 
 logger.info("✅ All components loaded successfully!")
 
@@ -79,7 +87,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=UserTurnStrategies(
+                stop=[
+                    TurnAnalyzerUserTurnStopStrategy(
+                        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
+                    )
+                ],
+            )
+        ),
+    )
 
     rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
 
@@ -130,13 +149,11 @@ async def bot(runner_args: RunnerArguments):
             audio_in_enabled=True,
             audio_out_enabled=True,
             vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(),
         ),
         "webrtc": lambda: TransportParams(
             audio_in_enabled=True,
             audio_out_enabled=True,
             vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-            turn_analyzer=LocalSmartTurnAnalyzerV3(),
         ),
     }