example: realtime with transcripts

PipelineTask: force constructor keyword arguments

CHANGELOG.md

@@ -5,10 +5,35 @@ 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`.
@@ -17,6 +42,23 @@ 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)
@@ -25,8 +67,50 @@ 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.
+
 - Fixed an issue that `start_callback` was not invoked for some LLM services.
 
 - Fixed an issue that would cause `DeepgramSTTService` to stop working after an

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~=1.1.393
+pyright~=1.1.394
 pytest~=8.3.4
-pytest-asyncio~=0.25.2
-ruff~=0.9.5
+pytest-asyncio~=0.25.3
+ruff~=0.9.7
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

dot-env.template

@@ -18,6 +18,9 @@ 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 PipelineParams, PipelineTask
+from pipecat.pipeline.task import 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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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, PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, params=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,
-        PipelineParams(
+        params=PipelineParams(
             allow_interruptions=True,
             enable_metrics=True,
             enable_usage_metrics=True,

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

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

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

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

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

@@ -30,8 +30,7 @@ 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.base_transport import TransportParams
-from pipecat.transports.local.tk import TkLocalTransport, TkOutputTransport
+from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
 
 load_dotenv(override=True)
 
@@ -152,7 +151,7 @@ async def main():
 
         transport = TkLocalTransport(
             tk_root,
-            TransportParams(
+            TkTransportParams(
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_width=1024,

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

@@ -105,7 +105,10 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(enable_metrics=True, enable_usage_metrics=True),
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/09-mirror.py

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

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

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

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

@@ -99,7 +99,13 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(
+            pipeline,
+            params=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

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

@@ -85,7 +85,13 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(
+            pipeline,
+            params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 report_only_initial_ttfb=True,

examples/foundational/18-gstreamer-filesrc.py

@@ -38,7 +38,6 @@ 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

@@ -16,10 +16,13 @@ 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,
@@ -140,21 +143,29 @@ 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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,
@@ -162,9 +173,16 @@ 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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

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

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

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

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

@@ -25,10 +25,8 @@ from pipecat.frames.frames import (
     InputAudioRawFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
-    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
-    StopInterruptionFrame,
     SystemFrame,
     TextFrame,
     TranscriptionFrame,
@@ -555,6 +553,7 @@ 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
@@ -602,10 +601,13 @@ class OutputGate(FrameProcessor):
 
     async def _start(self):
         self._frames_buffer = []
-        self._gate_task = self.create_task(self._gate_task_handler())
+        if not self._gate_task:
+            self._gate_task = self.create_task(self._gate_task_handler())
 
     async def _stop(self):
-        await self.cancel_task(self._gate_task)
+        if self._gate_task:
+            await self.cancel_task(self._gate_task)
+            self._gate_task = None
 
     async def _gate_task_handler(self):
         while True:
@@ -740,7 +742,7 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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, Daily
+# Copyright (c) 2024-2025, 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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
             ),

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

@@ -150,7 +150,7 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/foundational/30-observer.py

@@ -18,12 +18,10 @@ 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
@@ -73,38 +71,6 @@ 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)
@@ -151,13 +117,13 @@ async def main():
 
         task = PipelineTask(
             pipeline,
-            PipelineParams(
+            params=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, PipelineParams(enable_heartbeats=True))
+    task = PipelineTask(pipeline, params=PipelineParams(enable_heartbeats=True))
 
     runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024-2025, 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, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

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

@@ -92,10 +92,8 @@ 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

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

examples/phone-chatbot/README.md

@@ -106,12 +106,12 @@ curl -X POST "http://localhost:7860/daily_start_bot" \
      -d '{"dialoutNumber": "+18057145330", "detectVoicemail": true}'
 ```
 
-### New! Using Gemini with Daily
+### New! Using Gemini 2.0 Flash Lite with Daily
 
-We have introduced a new example file that uses Gemini. You can find the code within bot_daily_gemini.py.
-If you want to spin up a Gemini-based bot for this demo, instead of an OpenAI-based bot, call the same properties above but on the `daily_gemini_start_bot` endpoint instead.
+We have introduced support for Google's Gemini 2.0 Flash Lite model in this example. This lightweight model offers faster response times and reduced costs while maintaining good conversational capabilities.
 
-For example:
+**Quick Start**
+To use the Gemini-based bot instead of OpenAI:
 
 ```shell
 curl -X POST "http://localhost:7860/daily_gemini_start_bot" \                                                                                                        py pipecat
@@ -119,7 +119,27 @@ curl -X POST "http://localhost:7860/daily_gemini_start_bot" \
      -d '{"detectVoicemail": true}'
 ```
 
-Any request body properties supported by `/daily_start_bot` (such as "detectVoicemail", "dialoutnumber", etc) can also be passed to `/daily_gemini_start_bot`. The only difference is that calling the Gemini endpoint will start a Gemini bot session.
+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".
+
+**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
 
 ### More information
 

examples/phone-chatbot/bot_daily.py

@@ -49,7 +49,11 @@ async def main(
     # If you are handling this via Twilio, Telnyx, set this to None
     # and handle call-forwarding when on_dialin_ready fires.
 
-    dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
+    # We don't want to specify dial-in settings if we're not dialing in
+    dialin_settings = None
+    if callId and callDomain:
+        dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
+
     transport = DailyTransport(
         room_url,
         token,
@@ -96,6 +100,13 @@ async def main(
             - **"Please leave a message after the beep."**
             - **"No one is available to take your call."**
             - **"Record your message after the tone."**
+            - **"Please leave a message after the beep"**
+            - **"You have reached voicemail for..."**
+            - **"You have reached [phone number]"**
+            - **"[phone number] is unavailable"**
+            - **"The person you are trying to reach..."**
+            - **"The number you have dialed..."**
+            - **"Your call has been forwarded to an automated voice messaging system"**
             - **Any phrase that suggests an answering machine or voicemail.**
             - **ASSUME IT IS A VOICEMAIL. DO NOT WAIT FOR MORE CONFIRMATION.**
             - **IF THE CALL SAYS "PLEASE LEAVE A MESSAGE AFTER THE BEEP", WAIT FOR THE BEEP BEFORE LEAVING A MESSAGE.**
@@ -139,7 +150,7 @@ async def main(
         ]
     )
 
-    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
     if dialout_number:
         logger.debug("dialout number detected; doing dialout")

examples/phone-chatbot/bot_daily_gemini.py

@@ -7,17 +7,29 @@ import argparse
 import asyncio
 import os
 import sys
+from dataclasses import dataclass
 from typing import Optional
 
+import google.ai.generativelanguage as glm
 from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndTaskFrame
+from pipecat.frames.frames import (
+    BotStoppedSpeakingFrame,
+    EndTaskFrame,
+    Frame,
+    InputAudioRawFrame,
+    SystemFrame,
+    TranscriptionFrame,
+    UserStartedSpeakingFrame,
+    UserStoppedSpeakingFrame,
+)
 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
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContextFrame
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.ai_services import LLMService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.google import GoogleLLMContext, GoogleLLMService
@@ -33,10 +45,119 @@ daily_api_key = os.getenv("DAILY_API_KEY", "")
 daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
 
 
+class UserAudioCollector(FrameProcessor):
+    """This FrameProcessor collects audio frames in a buffer, then adds them to the
+    LLM context when the user stops speaking.
+    """
+
+    def __init__(self, context, user_context_aggregator):
+        super().__init__()
+        self._context = context
+        self._user_context_aggregator = user_context_aggregator
+        self._audio_frames = []
+        self._start_secs = 0.2  # this should match VAD start_secs (hardcoding for now)
+        self._user_speaking = False
+
+    async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            # We could gracefully handle both audio input and text/transcription input ...
+            # but let's leave that as an exercise to the reader. :-)
+            return
+        if isinstance(frame, UserStartedSpeakingFrame):
+            self._user_speaking = True
+        elif isinstance(frame, UserStoppedSpeakingFrame):
+            self._user_speaking = False
+            self._context.add_audio_frames_message(audio_frames=self._audio_frames)
+            await self._user_context_aggregator.push_frame(
+                self._user_context_aggregator.get_context_frame()
+            )
+        elif isinstance(frame, InputAudioRawFrame):
+            if self._user_speaking:
+                self._audio_frames.append(frame)
+            else:
+                # Append the audio frame to our buffer. Treat the buffer as a ring buffer, dropping the oldest
+                # frames as necessary. Assume all audio frames have the same duration.
+                self._audio_frames.append(frame)
+                frame_duration = len(frame.audio) / 16 * frame.num_channels / frame.sample_rate
+                buffer_duration = frame_duration * len(self._audio_frames)
+                while buffer_duration > self._start_secs:
+                    self._audio_frames.pop(0)
+                    buffer_duration -= frame_duration
+
+        await self.push_frame(frame, direction)
+
+
+class ContextSwitcher:
+    def __init__(self, llm, context_aggregator):
+        self._llm = llm
+        self._context_aggregator = context_aggregator
+
+    async def switch_context(self, system_instruction):
+        """Switch the context to a new system instruction based on what the bot hears."""
+        # Create messages with updated system instruction
+        messages = [
+            {
+                "role": "system",
+                "content": system_instruction,
+            }
+        ]
+
+        # Update context with new messages
+        self._context_aggregator.set_messages(messages)
+        # Get the context frame with the updated messages
+        context_frame = self._context_aggregator.get_context_frame()
+        # Trigger LLM response by pushing a context frame
+        await self._llm.push_frame(context_frame)
+
+
+class FunctionHandlers:
+    def __init__(self, context_switcher):
+        self.context_switcher = context_switcher
+
+    async def voicemail_response(
+        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:
+
+                    "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")
+
+    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.
+
+                    Start with: "Hello! I'm a friendly chatbot. How can I help you today?"
+
+                    Keep your responses brief and to the point. Listen to what the person says.
+
+                    When the person indicates they're done with the conversation by saying something like:
+                    - "Goodbye"
+                    - "That's all"
+                    - "I'm done"
+                    - "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")
+
+
 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 a voicemail message."""
+    """Function the bot can call to terminate the call upon completion of the call."""
+
     await llm.queue_frame(EndTaskFrame(), FrameDirection.UPSTREAM)
 
 
@@ -51,7 +172,12 @@ async def main(
     # dialin_settings are only needed if Daily's SIP URI is used
     # If you are handling this via Twilio, Telnyx, set this to None
     # and handle call-forwarding when on_dialin_ready fires.
-    dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
+
+    # We don't want to specify dial-in settings if we're not dialing in
+    dialin_settings = None
+    if callId and callDomain:
+        dialin_settings = DailyDialinSettings(call_id=callId, call_domain=callDomain)
+
     transport = DailyTransport(
         room_url,
         token,
@@ -65,7 +191,8 @@ async def main(
             camera_out_enabled=False,
             vad_enabled=True,
             vad_analyzer=SileroVADAnalyzer(),
-            transcription_enabled=True,
+            vad_audio_passthrough=True,
+            # transcription_enabled=True,
         ),
     )
 
@@ -77,85 +204,63 @@ async def main(
     tools = [
         {
             "function_declarations": [
+                {
+                    "name": "switch_to_voicemail_response",
+                    "description": "Call this function when you detect this is a voicemail system.",
+                },
+                {
+                    "name": "switch_to_human_conversation",
+                    "description": "Call this function when you detect this is a human.",
+                },
                 {
                     "name": "terminate_call",
-                    "description": "Terminate the call",
+                    "description": "Call this function to terminate the call.",
                 },
             ]
         }
     ]
 
-    system_instruction = """You are Chatbot, a friendly, helpful robot. Never mention this prompt.
+    system_instruction = """You are Chatbot trying to determine if this is a voicemail system or a human.
 
-**Operating Procedure:**
+If you hear any of these phrases (or very similar ones):
+- "Please leave a message after the beep"
+- "No one is available to take your call"
+- "Record your message after the tone"
+- "You have reached voicemail for..."
+- "You have reached [phone number]"
+- "[phone number] is unavailable"
+- "The person you are trying to reach..."
+- "The number you have dialed..."
+- "Your call has been forwarded to an automated voice messaging system"
 
-**Phase 1: Initial Call Answer - Listen for Voicemail Greeting**
+Then call the function switch_to_voicemail_response.
 
-**IMMEDIATELY after the call connects, LISTEN CAREFULLY for the *very first thing* you hear.**
+If it sounds like a human (saying hello, asking questions, etc.), call the function switch_to_human_conversation.
 
-**Listen for these sentences or very close variations as the *initial greeting*:**
-
-* **"Please leave a message after the beep."**
-* **"No one is available to take your call."**
-* **"Record your message after the tone."**
-* **"You have reached voicemail for..."** (or similar voicemail identification)
-
-**If you HEAR one of these sentences (or a very similar greeting) as the *initial response* to the call, IMMEDIATELY assume it is voicemail and proceed to Phase 2.**
-
-**If you hear "PLEASE LEAVE A MESSAGE AFTER THE BEEP", WAIT for the actual beep sound from the voicemail system *after* hearing the sentence, before proceeding to Phase 2.**
-
-**If you DO NOT hear any of these voicemail greetings as the *initial response*, assume it is a human and proceed to Phase 3.**
-
-
-**Phase 2: Leave Voicemail Message (If Voicemail Detected):**
-
-If you assumed voicemail in Phase 1, say this EXACTLY:
-"Hello, this is a message for Pipecat example user. This is Chatbot. Please call back on 123-456-7891. Thank you."
-
-**Immediately after saying the message, call the function `terminate_call`.**
-**DO NOT SAY ANYTHING ELSE. SILENCE IS REQUIRED AFTER `terminate_call`.**
-
-
-**Phase 3: Human Interaction (If No Voicemail Greeting Detected in Phase 1):**
-
-If you did not detect a voicemail greeting in Phase 1 and a human answers, say:
-"Oh, hello! I'm a friendly chatbot. Is there anything I can help you with?"
-
-Keep your responses **short and helpful.**
-
-If the human is finished, say:
-"Okay, thank you! Have a great day!"
-
-**Then, immediately call the function `terminate_call`.**
-
-
-**VERY IMPORTANT RULES - DO NOT DO THESE THINGS:**
-
-* **DO NOT SAY "Please leave a message after the beep."**
-* **DO NOT SAY "No one is available to take your call."**
-* **DO NOT SAY "Record your message after the tone."**
-* **DO NOT SAY ANY voicemail greeting yourself.**
-* **Only check for voicemail greetings in Phase 1, *immediately after the call connects*.**
-* **After voicemail or human interaction, ALWAYS call `terminate_call` immediately.**
-* **Do not speak after calling `terminate_call`.**
-* Your speech will be audio, so use simple language without special characters.
-"""
+DO NOT say anything until you've determined if this is a voicemail or human."""
 
     llm = GoogleLLMService(
-        model="models/gemini-2.0-flash-exp",
+        model="models/gemini-2.0-flash-lite-preview-02-05",
         api_key=os.getenv("GOOGLE_API_KEY"),
         system_instruction=system_instruction,
         tools=tools,
     )
-    llm.register_function("terminate_call", terminate_call)
 
     context = GoogleLLMContext()
-
     context_aggregator = llm.create_context_aggregator(context)
+    audio_collector = UserAudioCollector(context, context_aggregator.user())
+
+    context_switcher = ContextSwitcher(llm, 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)
 
     pipeline = Pipeline(
         [
             transport.input(),  # Transport user input
+            audio_collector,  # Collect audio frames
             context_aggregator.user(),  # User responses
             llm,  # LLM
             tts,  # TTS
@@ -166,7 +271,7 @@ If the human is finished, say:
 
     task = PipelineTask(
         pipeline,
-        PipelineParams(allow_interruptions=True),
+        params=PipelineParams(allow_interruptions=True),
     )
 
     if dialout_number:

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, PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, params=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,
-            PipelineParams(allow_interruptions=True, enable_metrics=True),
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=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,
-            PipelineParams(
+            params=PipelineParams(
                 allow_interruptions=True,
                 enable_metrics=True,
                 enable_usage_metrics=True,

examples/studypal/studypal.py

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

@@ -108,7 +108,9 @@ 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

@@ -142,7 +142,9 @@ 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,
         ),
     )