Merge pull request #4003 from pipecat-ai/pk/fix-deprecated-vad-analyzer-usage

Fix deprecated vad_analyzer usage in examples

examples/foundational/07zk-interruptible-resemble.py

@@ -30,24 +30,20 @@ from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
-# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# We use lambdas to defer transport parameter creation until the transport
-# instantiated. The function will be called when the desired transport gets
+# type is selected at runtime.
-# selected.
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 

examples/foundational/13-whisper-transcription.py

@@ -13,6 +13,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -40,15 +41,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -59,8 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = WhisperSTTService()
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13a-whisper-local.py

@@ -15,6 +15,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper.stt import WhisperSTTService
 from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
@@ -40,15 +41,15 @@ async def main():
     transport = LocalAudioTransport(
         LocalAudioTransportParams(
             audio_in_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
         )
     )
 
     stt = WhisperSTTService()
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(pipeline)
 

examples/foundational/13e-whisper-mlx.py

@@ -15,6 +15,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeaking
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -61,15 +62,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
 }
 
@@ -84,8 +82,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS))
+    )
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13g-sambanova-transcription.py

@@ -16,6 +16,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame, UserStoppedSpeaking
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -62,15 +63,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
     ),
 }
 
@@ -86,8 +84,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS))
+    )
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13i-soniox-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,15 +40,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -60,8 +58,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13j-azure-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,15 +40,12 @@ class TranscriptionLogger(FrameProcessor):
 transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -61,8 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13k-elevenlabs-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,11 +40,9 @@ class TranscriptionLogger(FrameProcessor):
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
-    "daily": lambda: DailyParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+    "daily": lambda: DailyParams(audio_in_enabled=True),
-    "twilio": lambda: FastAPIWebsocketParams(
+    "twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
-        audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
+    "webrtc": lambda: TransportParams(audio_in_enabled=True),
-    ),
-    "webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
 }
 
 
@@ -53,8 +52,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = ElevenLabsRealtimeSTTService(api_key=os.getenv("ELEVENLABS_API_KEY"))
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/13m-openai-transcription.py

@@ -14,6 +14,7 @@ from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.audio.vad_processor import VADProcessor
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -39,11 +40,9 @@ class TranscriptionLogger(FrameProcessor):
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
-    "daily": lambda: DailyParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+    "daily": lambda: DailyParams(audio_in_enabled=True),
-    "twilio": lambda: FastAPIWebsocketParams(
+    "twilio": lambda: FastAPIWebsocketParams(audio_in_enabled=True),
-        audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
+    "webrtc": lambda: TransportParams(audio_in_enabled=True),
-    ),
-    "webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
 }
 
 
@@ -59,8 +58,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     tl = TranscriptionLogger()
+    vad_processor = VADProcessor(vad_analyzer=SileroVADAnalyzer())
 
-    pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), vad_processor, stt, tl])
 
     task = PipelineTask(
         pipeline,

examples/foundational/19-openai-realtime.py

@@ -24,6 +24,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
     UserTurnStoppedMessage,
 )
 from pipecat.runner.types import RunnerArguments
@@ -119,17 +120,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -187,7 +185,10 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         tools,
     )
 
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/19a-azure-realtime.py

@@ -19,7 +19,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
@@ -93,17 +96,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -172,7 +172,10 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         tools,
     )
 
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/19b-openai-realtime-text.py

@@ -19,7 +19,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -98,17 +101,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -175,7 +175,10 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         tools,
     )
 
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/19c-openai-realtime-live-video.py

@@ -17,7 +17,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import (
     create_transport,
@@ -46,13 +49,11 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         video_in_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -103,7 +104,10 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
         [{"role": "user", "content": "Say hello!"}],
     )
 
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/20b-persistent-context-openai-realtime.py

@@ -21,7 +21,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
@@ -153,17 +156,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -214,7 +214,10 @@ Remember, your responses should be short. Just one or two sentences, usually."""
     llm.register_function("load_conversation", load_conversation)
 
     context = LLMContext([{"role": "user", "content": "Say hello!"}], tools)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/20e-persistent-context-aws-nova-sonic.py

@@ -21,7 +21,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.aws.nova_sonic.llm import AWSNovaSonicLLMService
@@ -189,17 +192,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -236,7 +236,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm.register_function("load_conversation", load_conversation)
 
     context = LLMContext(tools=tools)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/25-google-audio-in.py

@@ -28,7 +28,10 @@ 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.frame_processor import FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -270,17 +273,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -324,7 +324,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(context)
+    context_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
     audio_collector = UserAudioCollector(context, context_aggregator.user())
     input_transcription_context_filter = InputTranscriptionContextFilter()
     transcription_frames_emitter = InputTranscriptionFrameEmitter()

examples/foundational/40-aws-nova-sonic.py

@@ -24,6 +24,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
     UserTurnStoppedMessage,
 )
 from pipecat.runner.types import RunnerArguments
@@ -87,17 +88,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -147,7 +145,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Set up context and context management.
     context = LLMContext(tools=tools)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     # Build the pipeline
     pipeline = Pipeline(

examples/foundational/55zl-update-settings-azure-realtime.py

@@ -19,6 +19,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -34,17 +35,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -65,7 +63,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/55zl-update-settings-openai-realtime.py

@@ -19,6 +19,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -34,17 +35,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -62,7 +60,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/55zm-update-settings-gemini-live-vertex.py

@@ -16,7 +16,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.gemini_live.vertex.llm import GeminiLiveVertexLLMService
@@ -30,17 +33,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -58,7 +58,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     context = LLMContext()
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/55zm-update-settings-gemini-live.py

@@ -16,7 +16,10 @@ 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.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
@@ -30,17 +33,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -56,7 +56,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     )
 
     context = LLMContext()
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/55zn-update-settings-ultravox-realtime.py

@@ -21,6 +21,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -35,17 +36,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -73,7 +71,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

examples/foundational/55zo-update-settings-grok-realtime.py

@@ -19,6 +19,7 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import (
     AssistantTurnStoppedMessage,
     LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
@@ -34,17 +35,14 @@ transport_params = {
     "daily": lambda: DailyParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "twilio": lambda: FastAPIWebsocketParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
-        vad_analyzer=SileroVADAnalyzer(),
     ),
 }
 
@@ -62,7 +60,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
 
     pipeline = Pipeline(
         [

src/pipecat/transports/base_input.py

@@ -150,8 +150,9 @@ class BaseInputTransport(FrameProcessor):
             with warnings.catch_warnings():
                 warnings.simplefilter("always")
                 warnings.warn(
-                    "Parameter 'vad_analyzer' is deprecated, use `LLMUserAggregator`'s new "
+                    "Parameter 'vad_analyzer' is deprecated. Use `LLMUserAggregator`'s "
-                    "`vad_analyzer` parameter instead.",
+                    "`vad_analyzer` parameter, or `VADProcessor` if no `LLMUserAggregator` "
+                    "is needed.",
                     DeprecationWarning,
                 )
 

src/pipecat/transports/base_transport.py

@@ -115,8 +115,9 @@ class TransportParams(BaseModel):
         vad_analyzer: Voice Activity Detection analyzer instance.
 
             .. deprecated:: 0.0.101
-                The `vad_analyzer` parameter is deprecated, use `LLMUSerAggregator`'s
+                The `vad_analyzer` parameter is deprecated. Use `LLMUserAggregator`'s
-                new `vad_analyzer` parameter instead.
+                `vad_analyzer` parameter, or `VADProcessor` if no `LLMUserAggregator`
+                is needed.
 
         turn_analyzer: Turn-taking analyzer instance for conversation management.