attempt at 2 pipelines

CHANGELOG.md

@@ -5,35 +5,10 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## Unreleased
 
 ### Added
 
-- Pipecat version will now be logged on every application startup. This will
-  help us identify what version we are running in case of any issues.
-
-- Added a new `StopFrame` which can be used to stop a pipeline task while
-  keeping the frame processors running. The frame processors could then be used
-  in a different pipeline. The difference between a `StopFrame` and a
-  `StopTaskFrame` is that, as with `EndFrame` and `EndTaskFrame`, the
-  `StopFrame` is pushed from the task and the `StopTaskFrame` is pushed upstream
-  inside the pipeline by any processor.
-
-- Added a new `PipelineTask` parameter `observers` that replaces the previous
-  `PipelineParams.observers`.
-
-- Added a new `PipelineTask` parameter `check_dangling_tasks` to enable or
-  disable checking for frame processors' dangling tasks when the Pipeline
-  finishes running.
-
-- Added new `on_completion_timeout` event for LLM services (all OpenAI-based
-  services, Anthropic and Google). Note that this event will only get triggered
-  if LLM timeouts are setup and if the timeout was reached. It can be useful to
-  retrigger another completion and see if the timeout was just a blip.
-
-- Added new log observers `LLMLogObserver` and `TranscriptionLogObserver` that
-  can be useful for debugging your pipelines.
-
 - Added `room_url` property to `DailyTransport`.
 
 - Added `addons` argument to `DeepgramSTTService`.
@@ -42,23 +17,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
-- ⚠️ `PipelineTask` now requires keyword arguments (except for the first one for
-  the pipeline).
-
-- The base `TTSService` class now strips leading newlines before sending text
-  to the TTS provider. This change is to solve issues where some TTS providers,
-  like Azure, would not output text due to newlines.
-
-- `GrokLLMSService` now uses `grok-2` as the default model.
-
-- `AnthropicLLMService` now uses `claude-3-7-sonnet-20250219` as the default
-  model.
-
-- `RimeHttpTTSService` needs an `aiohttp.ClientSession` to be passed to the
-  constructor as all the other HTTP-based services.
-
-- `RimeHttpTTSService` doesn't use a default voice anymore.
-
 - `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
   to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
   (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
@@ -67,47 +25,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 ```
 
-### Deprecated
-
-- `PipelineParams.observers` is now deprecated, you the new `PipelineTask`
-  parameter `observers`.
-
-### Removed
-
-- Remove `TransportParams.audio_out_is_live` since it was not being used at all.
-
 ### Fixed
 
-- Fixed an `AudioContextWordTTSService` issue that would cause an `EndFrame` to
-  disconnect from the TTS service before audio from all the contexts was
-  received. This affected services like Cartesia and Rime.
-
-- Fixed an issue that was not allowing to pass an `OpenAILLMContext` to create
-  `GoogleLLMService`'s context aggregators.
-
-- Fixed a `ElevenLabsTTSService`, `FishAudioTTSService`, `LMNTTTSService` and
-  `PlayHTTTSService` issue that was resulting in audio requested before an
-  interruption being played after an interruption.
-
-- Fixed `match_endofsentence` support for ellipses.
-
-- Fixed an issue that would cause undesired interruptions via
-  `EmulateUserStartedSpeakingFrame` when only interim transcriptions (i.e. no
-  final transcriptions) where received.
-
-- Fixed an issue where `EndTaskFrame` was not triggering
-  `on_client_disconnected` or closing the WebSocket in FastAPI.
-
-- Fixed an issue in `DeepgramSTTService` where the `sample_rate` passed to the
-  `LiveOptions` was not being used, causing the service to use the default
-  sample rate of pipeline.
-
-- Fixed a context aggregator issue that would not append the LLM text response
-  to the context if a function call happened in the same LLM turn.
-
-- Fixed an issue that was causing HTTP TTS services to push `TTSStoppedFrame`
-  more than once.
-
 - Fixed a `FishAudioTTSService` issue where `TTSStoppedFrame` was not being
   pushed.
 

dev-requirements.txt

@@ -3,10 +3,10 @@ coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.394
+pyright~=1.1.393
 pytest~=8.3.4
-pytest-asyncio~=0.25.3
-ruff~=0.9.7
+pytest-asyncio~=0.25.2
+ruff~=0.9.5
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

dot-env.template

@@ -18,9 +18,6 @@ AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
-# Cartesia
-CARTESIA_API_KEY=...
-
 # Daily
 DAILY_API_KEY=...
 DAILY_SAMPLE_ROOM_URL=https://...

examples/bot-ready-signalling/server/signalling_bot.py

@@ -17,7 +17,7 @@ from runner import configure
 from pipecat.frames.frames import AudioRawFrame, EndFrame, OutputAudioRawFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 

examples/canonical-metrics/bot.py

@@ -119,7 +119,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/chatbot-audio-recording/bot.py

@@ -124,7 +124,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @audiobuffer.event_handler("on_audio_data")
         async def on_audio_data(buffer, audio, sample_rate, num_channels):

examples/deployment/flyio-example/bot.py

@@ -70,7 +70,7 @@ async def main(room_url: str, token: str):
         ]
     )
 
-    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):

examples/deployment/modal-example/bot.py

@@ -62,7 +62,7 @@ async def main(room_url: str, token: str):
 
     task = PipelineTask(
         pipeline,
-        params=PipelineParams(
+        PipelineParams(
             allow_interruptions=True,
             enable_metrics=True,
             enable_usage_metrics=True,

examples/foundational/03a-local-still-frame.py

@@ -18,7 +18,8 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.fal import FalImageGenService
-from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
 
 load_dotenv(override=True)
 
@@ -33,9 +34,7 @@ async def main():
 
         transport = TkLocalTransport(
             tk_root,
-            TkTransportParams(
-                camera_out_enabled=True, camera_out_width=1024, camera_out_height=1024
-            ),
+            TransportParams(camera_out_enabled=True, camera_out_width=1024, camera_out_height=1024),
         )
 
         imagegen = FalImageGenService(

examples/foundational/03b-still-frame-imagen.py

@@ -44,8 +44,7 @@ async def main():
         runner = PipelineRunner()
 
         task = PipelineTask(
-            Pipeline([imagegen, transport.output()]),
-            params=PipelineParams(enable_metrics=True),
+            Pipeline([imagegen, transport.output()]), PipelineParams(enable_metrics=True)
         )
 
         @transport.event_handler("on_first_participant_joined")

examples/foundational/05a-local-sync-speech-and-image.py

@@ -30,7 +30,8 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
 from pipecat.services.fal import FalImageGenService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport, TkOutputTransport
 
 load_dotenv(override=True)
 
@@ -151,7 +152,7 @@ async def main():
 
         transport = TkLocalTransport(
             tk_root,
-            TkTransportParams(
+            TransportParams(
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_width=1024,

examples/foundational/06-listen-and-respond.py

@@ -105,10 +105,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
+            PipelineParams(enable_metrics=True, enable_usage_metrics=True),
         )
 
         @transport.event_handler("on_first_participant_joined")

examples/foundational/06a-image-sync.py

@@ -127,7 +127,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07-interruptible-vad.py

@@ -76,7 +76,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07-interruptible.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07a-interruptible-anthropic.py

@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07b-interruptible-langchain.py

@@ -103,7 +103,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07c-interruptible-deepgram-vad.py

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07c-interruptible-deepgram.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07d-interruptible-elevenlabs.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07e-interruptible-playht-http.py

@@ -75,7 +75,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07e-interruptible-playht.py

@@ -77,7 +77,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07f-interruptible-azure.py

@@ -83,7 +83,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07g-interruptible-openai.py

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07h-interruptible-openpipe.py

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07i-interruptible-xtts.py

@@ -75,7 +75,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07j-interruptible-gladia.py

@@ -80,7 +80,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07k-interruptible-lmnt.py

@@ -71,7 +71,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07l-interruptible-together.py

@@ -88,7 +88,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -81,7 +81,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07n-interruptible-google.py

@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07o-interruptible-assemblyai.py

@@ -80,7 +80,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07p-interruptible-krisp.py

@@ -76,7 +76,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07q-interruptible-rime.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07r-interruptible-riva-nim.py

@@ -74,7 +74,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/07s-interruptible-google-audio-in.py

@@ -251,7 +251,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/07t-interruptible-fish.py

@@ -74,7 +74,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/09-mirror.py

@@ -78,11 +78,7 @@ async def main():
         runner = PipelineRunner()
 
         task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                audio_in_sample_rate=24000,
-                audio_out_sample_rate=24000,
-            ),
+            pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
         )
 
         await runner.run(task)

examples/foundational/09a-local-mirror.py

@@ -24,7 +24,8 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -66,7 +67,7 @@ async def main():
 
         tk_transport = TkLocalTransport(
             tk_root,
-            TkTransportParams(
+            TransportParams(
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_is_live=True,
@@ -82,11 +83,7 @@ async def main():
         pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
 
         task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                audio_in_sample_rate=24000,
-                audio_out_sample_rate=24000,
-            ),
+            pipeline, PipelineParams(audio_in_sample_rate=24000, audio_out_sample_rate=24000)
         )
 
         async def run_tk():

examples/foundational/10-wake-phrase.py

@@ -76,7 +76,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/14-function-calling.py

@@ -112,7 +112,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14a-function-calling-anthropic.py

@@ -99,13 +99,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/14b-function-calling-anthropic-video.py

@@ -153,13 +153,7 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
             ]
         )
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/14e-function-calling-gemini.py

@@ -152,7 +152,7 @@ indicate you should use the get_image tool are:
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14f-function-calling-groq.py

@@ -116,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14g-function-calling-grok.py

@@ -113,7 +113,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14h-function-calling-azure.py

@@ -117,7 +117,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14i-function-calling-fireworks.py

@@ -116,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14j-function-calling-nim.py

@@ -116,7 +116,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14k-function-calling-cerebras.py

@@ -123,7 +123,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14l-function-calling-deepseek.py

@@ -123,7 +123,7 @@ Start by asking me for my location. Then, use 'get_weather_current' to give me a
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14m-function-calling-openrouter.py

@@ -117,7 +117,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/14n-function-calling-perplexity.py

@@ -83,7 +83,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/15-switch-voices.py

@@ -133,7 +133,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/15a-switch-languages.py

@@ -126,7 +126,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/16-gpu-container-local-bot.py

@@ -85,13 +85,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
 
         # When a participant joins, start transcription for that participant so the
         # bot can "hear" and respond to them.

examples/foundational/17-detect-user-idle.py

@@ -108,7 +108,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 report_only_initial_ttfb=True,

examples/foundational/18-gstreamer-filesrc.py

@@ -38,6 +38,7 @@ async def main():
             "GStreamer",
             DailyParams(
                 audio_out_enabled=True,
+                audio_out_is_live=True,
                 camera_out_enabled=True,
                 camera_out_width=1280,
                 camera_out_height=720,

examples/foundational/19-openai-realtime-beta.py

@@ -16,13 +16,10 @@ from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.transcript_processor import TranscriptProcessor
-from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai_realtime_beta import (
     InputAudioTranscription,
     OpenAIRealtimeBetaLLMService,
@@ -143,29 +140,21 @@ Remember, your responses should be short. Just one or two sentences, usually."""
             tools,
         )
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
-        # Create transcript processor and handler
-        transcript = TranscriptProcessor()
-
         context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                stt,
-                transcript.user(),  # User transcripts
                 context_aggregator.user(),
                 llm,  # LLM
                 context_aggregator.assistant(),
-                transcript.assistant(),  # Assistant transcripts
                 transport.output(),  # Transport bot output
             ]
         )
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
@@ -173,16 +162,9 @@ Remember, your responses should be short. Just one or two sentences, usually."""
             ),
         )
 
-        # Register event handler for transcript updates
-        @transcript.event_handler("on_transcript_update")
-        async def on_transcript_update(processor, frame):
-            logger.debug(f"Received transcript update with {len(frame.messages)} new messages")
-            for msg in frame.messages:
-                logger.debug(msg)
-
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            # await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20a-persistent-context-openai.py

@@ -212,7 +212,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -237,7 +237,7 @@ Remember, your responses should be short. Just one or two sentences, usually."""
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/20c-persistent-context-anthropic.py

@@ -209,7 +209,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/20d-persistent-context-gemini.py

@@ -263,7 +263,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/21-tavus-layer.py

@@ -87,7 +87,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 # We just use 16000 because that's what Tavus is expecting and
                 # we avoid resampling.
                 audio_in_sample_rate=16000,

examples/foundational/22-natural-conversation.py

@@ -145,7 +145,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22b-natural-conversation-proposal.py

@@ -138,7 +138,6 @@ class OutputGate(FrameProcessor):
         self._gate_open = start_open
         self._frames_buffer = []
         self._notifier = notifier
-        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -179,13 +178,10 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        if not self._gate_task:
-            self._gate_task = self.create_task(self._gate_task_handler())
+        self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        if self._gate_task:
-            await self.cancel_task(self._gate_task)
-            self._gate_task = None
+        await self.cancel_task(self._gate_task)
 
     async def _gate_task_handler(self):
         while True:
@@ -355,7 +351,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22c-natural-conversation-mixed-llms.py

@@ -342,7 +342,6 @@ class OutputGate(FrameProcessor):
         self._gate_open = start_open
         self._frames_buffer = []
         self._notifier = notifier
-        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -383,13 +382,10 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        if not self._gate_task:
-            self._gate_task = self.create_task(self._gate_task_handler())
+        self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        if self._gate_task:
-            await self.cancel_task(self._gate_task)
-            self._gate_task = None
+        await self.cancel_task(self._gate_task)
 
     async def _gate_task_handler(self):
         while True:
@@ -564,7 +560,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/22d-natural-conversation-gemini-audio.py

@@ -25,8 +25,10 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
+    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
+    StopInterruptionFrame,
     SystemFrame,
     TextFrame,
     TranscriptionFrame,
@@ -553,7 +555,6 @@ class OutputGate(FrameProcessor):
         self._notifier = notifier
         self._context = context
         self._transcription_buffer = user_transcription_buffer
-        self._gate_task = None
 
     def close_gate(self):
         self._gate_open = False
@@ -601,13 +602,10 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        if not self._gate_task:
-            self._gate_task = self.create_task(self._gate_task_handler())
+        self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        if self._gate_task:
-            await self.cancel_task(self._gate_task)
-            self._gate_task = None
+        await self.cancel_task(self._gate_task)
 
     async def _gate_task_handler(self):
         while True:
@@ -742,7 +740,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/23-bot-background-sound.py

@@ -87,7 +87,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/24-stt-mute-filter.py

@@ -122,7 +122,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

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

@@ -354,7 +354,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26-gemini-multimodal-live.py

@@ -63,7 +63,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26a-gemini-multimodal-live-transcription.py

@@ -89,7 +89,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26b-gemini-multimodal-live-function-calling.py

@@ -120,7 +120,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26c-gemini-multimodal-live-video.py

@@ -79,7 +79,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26d-gemini-multimodal-live-text.py

@@ -106,7 +106,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/26e-gemini-multimodal-google-search.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024-2025, Daily
+# Copyright (c) 2024, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -34,7 +34,7 @@ search_tool = {"google_search": {}}
 tools = [search_tool]
 
 system_instruction = """
-You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting.
+You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting. 
 
 Always use the google search API to retrieve the latest news. You must also use it to check which day is today.
 
@@ -93,7 +93,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/27-simli-layer.py

@@ -83,7 +83,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
             ),

examples/foundational/28a-transcription-processor-openai.py

@@ -150,7 +150,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/28b-transcript-processor-anthropic.py

@@ -150,7 +150,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/28c-transcription-processor-gemini.py

@@ -178,7 +178,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/30-observer.py

@@ -18,10 +18,12 @@ from pipecat.frames.frames import (
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     Frame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMTextFrame,
     StartInterruptionFrame,
 )
 from pipecat.observers.base_observer import BaseObserver
-from pipecat.observers.loggers.llm_log_observer import LLMLogObserver
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -71,6 +73,38 @@ class DebugObserver(BaseObserver):
             logger.info(f"🤖 BOT STOP SPEAKING: {src} {arrow} {dst} at {time_sec:.2f}s")
 
 
+class LLMLogObserver(BaseObserver):
+    """Observer to log LLM activity to the console.
+
+    Logs all frame instances of:
+    - LLMFullResponseStartFrame (only from LLM service)
+    - LLMTextFrame
+    - LLMFullResponseEndFrame (only from LLM service)
+
+    This allows you to track when the LLM starts responding, what it generates, and when it finishes.
+    Log format: [LLM EVENT]: [details] at [timestamp]s
+    """
+
+    async def on_push_frame(
+        self,
+        src: FrameProcessor,
+        dst: FrameProcessor,
+        frame: Frame,
+        direction: FrameDirection,
+        timestamp: int,
+    ):
+        time_sec = timestamp / 1_000_000_000
+
+        # Only log start/end frames from OpenAILLMService
+        if isinstance(frame, (LLMFullResponseStartFrame, LLMFullResponseEndFrame)):
+            if isinstance(src, OpenAILLMService):
+                event = "START" if isinstance(frame, LLMFullResponseStartFrame) else "END"
+                logger.info(f"🧠 LLM {event} RESPONSE at {time_sec:.2f}s")
+        # Log all LLMTextFrames
+        elif isinstance(frame, LLMTextFrame):
+            logger.info(f"🧠 LLM GENERATING: {frame.text!r} at {time_sec:.2f}s")
+
+
 async def main():
     async with aiohttp.ClientSession() as session:
         (room_url, token) = await configure(session)
@@ -117,13 +151,13 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
                 report_only_initial_ttfb=True,
+                observers=[DebugObserver(), LLMLogObserver()],
             ),
-            observers=[DebugObserver(), LLMLogObserver()],
         )
 
         @transport.event_handler("on_first_participant_joined")

examples/foundational/31-heartbeats.py

@@ -32,7 +32,7 @@ async def main():
 
     pipeline = Pipeline([NullProcessor()])
 
-    task = PipelineTask(pipeline, params=PipelineParams(enable_heartbeats=True))
+    task = PipelineTask(pipeline, PipelineParams(enable_heartbeats=True))
 
     runner = PipelineRunner()
 

examples/foundational/32-gemini-grounding-metadata.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024-2025, Daily
+# Copyright (c) 2024, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -38,7 +38,7 @@ search_tool = {"google_search_retrieval": {}}
 tools = [search_tool]
 
 system_instruction = """
-You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting.
+You are an expert at providing the most recent news from any place. Your responses will be converted to audio, so avoid using special characters or overly complex formatting. 
 
 Always use the google search API to retrieve the latest news. You must also use it to check which day is today.
 
@@ -117,7 +117,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/foundational/33-gemini-rag.py

@@ -230,7 +230,7 @@ Your response will be turned into speech so use only simple words and punctuatio
         )
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/instant-voice/server/src/single_bot.py

@@ -92,8 +92,10 @@ async def main():
 
     task = PipelineTask(
         pipeline,
-        params=PipelineParams(allow_interruptions=True),
-        observers=[rtvi.observer()],
+        params=PipelineParams(
+            allow_interruptions=True,
+            observers=[rtvi.observer()],
+        ),
     )
 
     @rtvi.event_handler("on_client_ready")

examples/news-chatbot/server/news_bot.py

@@ -140,8 +140,10 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(allow_interruptions=True),
-            observers=[GoogleRTVIObserver(rtvi)],
+            PipelineParams(
+                allow_interruptions=True,
+                observers=[GoogleRTVIObserver(rtvi)],
+            ),
         )
 
         @rtvi.event_handler("on_client_ready")

examples/patient-intake/bot.py

@@ -346,7 +346,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=False))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=False))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/phone-chatbot/README.md

@@ -113,6 +113,7 @@ We have introduced support for Google's Gemini 2.0 Flash Lite model in this exam
 **Quick Start**
 To use the Gemini-based bot instead of OpenAI:
 
+
 ```shell
 curl -X POST "http://localhost:7860/daily_gemini_start_bot" \                                                                                                        py pipecat
      -H "Content-Type: application/json" \
@@ -121,25 +122,24 @@ curl -X POST "http://localhost:7860/daily_gemini_start_bot" \
 
 All request body parameters supported by /daily_start_bot (such as detectVoicemail, dialoutNumber, etc.) are also compatible with /daily_gemini_start_bot.
 
-This example uses context switching to help steer the bot in the right direction. As Flash Lite is a smaller model, breaking the prompt down into smaller piece helps to improve the bot's accuracy.
-
-For example, instead of giving one large prompt like:
-
-```python
-system_instruction="""You are a chatbot that needs to detect if you're talking to a voicemail system or human, then either leave a message or have a conversation. If it's voicemail, say "Hello, this is a message..." and hang up. If it's a human, introduce yourself and be helpful until they say goodbye."""
-```
-
-We break it into stages:
-
-First prompt focuses only on detection: "Determine if this is voicemail or human"
-After detection, we switch to a new context: either "Leave this specific voicemail message" or "Have a conversation with the human".
+This example uses context switching to help steer the bot in the right direction. As Flash Lite is a smaller model, getting it to consistently call functions was difficult for these longer prompts. Breaking the prompt
+down into smaller pieces helped improve the accuracy of the bot.
 
 **Implementation Details**
 The implementation is available in bot_daily_gemini.py and features:
 
-- Staged prompting approach: Breaking down complex tasks into smaller, more focused prompts to improve the lightweight model's performance
-- Dynamic context switching: The bot can change its behavior in real-time based on what it detects (voicemail vs. human caller)
-- Function-based architecture: Uses function calling to trigger context switches and call termination
+Staged prompting approach: Breaking down complex tasks into smaller, more focused prompts to improve the lightweight model's performance
+Dynamic context switching: The bot can change its behavior in real-time based on what it detects (voicemail vs. human caller)
+Function-based architecture: Uses function calling to trigger context switches and call termination
+
+**Optimizations for Lightweight Models**
+Working with Gemini 2.0 Flash Lite required some specific optimizations:
+
+Simplified prompts: Each prompt focuses on a single task with clear instructions
+Function-driven state changes: The model calls specific functions to switch between different conversation modes
+Reduced context requirements: Each stage maintains only the context needed for its specific purpose
+
+This approach significantly improves the consistency of function calling in this lightweight model, which was challenging with longer, more complex prompts.
 
 ### More information
 

examples/phone-chatbot/bot_daily.py

@@ -49,7 +49,7 @@ async def main(
     # If you are handling this via Twilio, Telnyx, set this to None
     # and handle call-forwarding when on_dialin_ready fires.
 
-    # We don't want to specify dial-in settings if we're not dialing in
+    # We don't want to specify dialin settings if we're not dialing in
     dialin_settings = None
     if callId and callDomain:
         dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
@@ -150,7 +150,7 @@ async def main(
         ]
     )
 
-    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
     if dialout_number:
         logger.debug("dialout number detected; doing dialout")

examples/phone-chatbot/bot_daily_gemini.py

@@ -20,6 +20,7 @@ from pipecat.frames.frames import (
     EndTaskFrame,
     Frame,
     InputAudioRawFrame,
+    StopTaskFrame,
     SystemFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
@@ -44,6 +45,8 @@ logger.add(sys.stderr, level="DEBUG")
 daily_api_key = os.getenv("DAILY_API_KEY", "")
 daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
 
+system_message = None
+
 
 class UserAudioCollector(FrameProcessor):
     """This FrameProcessor collects audio frames in a buffer, then adds them to the
@@ -120,21 +123,24 @@ class FunctionHandlers:
         self, function_name, tool_call_id, args, llm, context, result_callback
     ):
         """Function the bot can call to leave a voicemail message."""
-        message = """You are Chatbot leaving a voicemail message. Say EXACTLY this message and nothing else:
+        print(f"!!! Got a voicemail response, llm is: {llm}")
+        system_message = """You are Chatbot leaving a voicemail message. Say EXACTLY this message and nothing else:
 
                     "Hello, this is a message for Pipecat example user. This is Chatbot. Please call back on 123-456-7891. Thank you."
 
                     After saying this message, call the terminate_call function."""
-
-        await self.context_switcher.switch_context(system_instruction=message)
-
-        await result_callback("Leaving a voicemail message")
+        print("!!! about to push stop task frame from voicemail")
+        await llm.queue_frame(StopTaskFrame(), FrameDirection.UPSTREAM)
+        print("!!! pushed stop task frame from voicemail")
+        await result_callback("Goodbye")
 
     async def human_conversation(
         self, function_name, tool_call_id, args, llm, context, result_callback
     ):
         """Function the bot can when it detects it's talking to a human."""
-        message = """You are Chatbot talking to a human. Be friendly and helpful.
+        print(f"!!! Got a human response, llm is: {llm}")
+
+        system_message = """You are Chatbot talking to a human. Be friendly and helpful.
 
                     Start with: "Hello! I'm a friendly chatbot. How can I help you today?"
 
@@ -147,17 +153,16 @@ class FunctionHandlers:
                     - "Thank you, that's all I needed"
 
                     THEN say: "Thank you for chatting. Goodbye!" and call the terminate_call function."""
-
-        await self.context_switcher.switch_context(system_instruction=message)
-
-        await result_callback("Talking to the customer")
+        print("!!! about to push stop task frame from human")
+        await llm.queue_frame(StopTaskFrame(), FrameDirection.UPSTREAM)
+        print("!!! pushed stop task frame from human")
+        await result_callback("Goodbye")
 
 
 async def terminate_call(
     function_name, tool_call_id, args, llm: LLMService, context, result_callback
 ):
     """Function the bot can call to terminate the call upon completion of the call."""
-
     await llm.queue_frame(EndTaskFrame(), FrameDirection.UPSTREAM)
 
 
@@ -173,7 +178,7 @@ async def main(
     # If you are handling this via Twilio, Telnyx, set this to None
     # and handle call-forwarding when on_dialin_ready fires.
 
-    # We don't want to specify dial-in settings if we're not dialing in
+    # We don't want to specify dialin settings if we're not dialing in
     dialin_settings = None
     if callId and callDomain:
         dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
@@ -239,39 +244,88 @@ If it sounds like a human (saying hello, asking questions, etc.), call the funct
 
 DO NOT say anything until you've determined if this is a voicemail or human."""
 
-    llm = GoogleLLMService(
+    greeting_llm = GoogleLLMService(
         model="models/gemini-2.0-flash-lite-preview-02-05",
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=system_instruction,
         tools=tools,
     )
 
-    context = GoogleLLMContext()
-    context_aggregator = llm.create_context_aggregator(context)
-    audio_collector = UserAudioCollector(context, context_aggregator.user())
+    greeting_context = GoogleLLMContext()
+    greeting_context_aggregator = greeting_llm.create_context_aggregator(greeting_context)
+    greeting_audio_collector = UserAudioCollector(
+        greeting_context, greeting_context_aggregator.user()
+    )
 
-    context_switcher = ContextSwitcher(llm, context_aggregator.user())
+    context_switcher = ContextSwitcher(greeting_llm, greeting_context_aggregator.user())
     handlers = FunctionHandlers(context_switcher)
 
-    llm.register_function("switch_to_voicemail_response", handlers.voicemail_response)
-    llm.register_function("switch_to_human_conversation", handlers.human_conversation)
-    llm.register_function("terminate_call", terminate_call)
+    greeting_llm.register_function("switch_to_voicemail_response", handlers.voicemail_response)
+    greeting_llm.register_function("switch_to_human_conversation", handlers.human_conversation)
+    greeting_llm.register_function("terminate_call", terminate_call)
 
-    pipeline = Pipeline(
+    greeting_pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
-            audio_collector,  # Collect audio frames
-            context_aggregator.user(),  # User responses
-            llm,  # LLM
+            greeting_audio_collector,  # Collect audio frames
+            greeting_context_aggregator.user(),  # User responses
+            greeting_llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            greeting_context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+    greeting_pipeline_task = PipelineTask(
+        greeting_pipeline,
+        PipelineParams(allow_interruptions=True),
+    )
+    runner = PipelineRunner()
+
+    print("!!! starting greeting")
+    await runner.run(greeting_pipeline_task)
+    print("!!! Done with greeting")
+
+    # Create conversation pipeline with new system message
+    conversation_llm = GoogleLLMService(
+        model="models/gemini-2.0-flash-lite-preview-02-05",
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        system_instruction=system_message if system_message else "You are a helpful chatbot.",
+        tools=[
+            {
+                "function_declarations": [
+                    {
+                        "name": "terminate_call",
+                        "description": "Call this function to terminate the call.",
+                    }
+                ]
+            }
+        ],
+    )
+    conversation_llm.register_function("terminate_call", terminate_call)
+
+    conversation_context = GoogleLLMContext()
+    conversation_context_aggregator = conversation_llm.create_context_aggregator(
+        conversation_context
+    )
+    conversation_audio_collector = UserAudioCollector(
+        conversation_context, conversation_context_aggregator.user()
+    )
+
+    conversation_pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            conversation_audio_collector,  # Collect audio frames
+            conversation_context_aggregator.user(),  # User responses
+            conversation_llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            conversation_context_aggregator.assistant(),  # Assistant spoken responses
         ]
     )
 
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(allow_interruptions=True),
+    conversation_task = PipelineTask(
+        conversation_pipeline,
+        PipelineParams(allow_interruptions=True),
     )
 
     if dialout_number:
@@ -319,11 +373,11 @@ DO NOT say anything until you've determined if this is a voicemail or human."""
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):
-        await task.cancel()
+        await conversation_task.cancel()
 
-    runner = PipelineRunner()
-
-    await runner.run(task)
+    print("!!! Starting conversation")
+    await runner.run(conversation_task)
+    print("!!! Done with conversation")
 
 
 if __name__ == "__main__":

examples/phone-chatbot/bot_twilio.py

@@ -77,7 +77,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
         ]
     )
 
-    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):

examples/sentry-metrics/bot.py

@@ -90,7 +90,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(allow_interruptions=True, enable_metrics=True),
+            PipelineParams(allow_interruptions=True, enable_metrics=True),
         )
 
         @transport.event_handler("on_first_participant_joined")

examples/simple-chatbot/server/bot-gemini.py

@@ -172,12 +172,12 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                observers=[RTVIObserver(rtvi)],
             ),
-            observers=[RTVIObserver(rtvi)],
         )
         await task.queue_frame(quiet_frame)
 

examples/simple-chatbot/server/bot-openai.py

@@ -198,12 +198,12 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                observers=[RTVIObserver(rtvi)],
             ),
-            observers=[RTVIObserver(rtvi)],
         )
         await task.queue_frame(quiet_frame)
 

examples/storytelling-chatbot/src/bot.py

@@ -104,7 +104,7 @@ async def main(room_url, token=None):
 
         main_task = PipelineTask(
             main_pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/studypal/studypal.py

@@ -155,10 +155,8 @@ Your task is to help the user understand and learn from this article in 2 senten
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
-                audio_out_sample_rate=44100,
-                allow_interruptions=True,
-                enable_metrics=True,
+            PipelineParams(
+                audio_out_sample_rate=44100, allow_interruptions=True, enable_metrics=True
             ),
         )
 

examples/translation-chatbot/bot.py

@@ -183,12 +183,12 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            params=PipelineParams(
+            PipelineParams(
                 allow_interruptions=False,  # We don't want to interrupt the translator bot
                 enable_metrics=True,
                 enable_usage_metrics=True,
+                observers=[RTVIObserver(rtvi)],
             ),
-            observers=[RTVIObserver(rtvi)],
         )
 
         @transport.event_handler("on_first_participant_joined")

examples/twilio-chatbot/bot.py

@@ -108,9 +108,7 @@ async def run_bot(websocket_client: WebSocket, stream_sid: str, testing: bool):
     task = PipelineTask(
         pipeline,
         params=PipelineParams(
-            audio_in_sample_rate=8000,
-            audio_out_sample_rate=8000,
-            allow_interruptions=True,
+            audio_in_sample_rate=8000, audio_out_sample_rate=8000, allow_interruptions=True
         ),
     )
 

examples/twilio-chatbot/client.py

@@ -142,9 +142,7 @@ async def run_client(client_name: str, server_url: str, duration_secs: int):
     task = PipelineTask(
         pipeline,
         params=PipelineParams(
-            audio_in_sample_rate=8000,
-            audio_out_sample_rate=8000,
-            allow_interruptions=True,
+            audio_in_sample_rate=8000, audio_out_sample_rate=8000, allow_interruptions=True
         ),
     )