services(playht): ignore message from a different request id

pipeline(task): cleanup Sink processor

.github/workflows/android.yaml

@@ -0,0 +1,48 @@
+name: android
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - "examples/simple-chatbot/client/android/**"
+  pull_request:
+    branches:
+      - "**"
+    paths:
+      - "examples/simple-chatbot/client/android/**"
+  workflow_dispatch:
+    inputs:
+      sdk_git_ref:
+        type: string
+        description: "Which git ref of the app to build"
+
+concurrency:
+  group: build-android-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  sdk:
+    name: "Simple chatbot demo"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.sdk_git_ref || github.ref }}
+
+      - name: "Install Java"
+        uses: actions/setup-java@v4
+        with:
+          distribution: 'temurin'
+          java-version: '17'
+
+      - name: Build demo app
+        working-directory: examples/simple-chatbot/client/android
+        run: ./gradlew :simple-chatbot-client:assembleDebug
+
+      - name: Upload demo APK
+        uses: actions/upload-artifact@v4
+        with:
+          name: Simple Chatbot Android Client
+          path: examples/simple-chatbot/client/android/simple-chatbot-client/build/outputs/apk/debug/simple-chatbot-client-debug.apk

.github/workflows/format.yaml

@@ -35,7 +35,12 @@ jobs:
           python -m pip install --upgrade pip
           pip install -r dev-requirements.txt
       - name: Ruff formatter
-        id: ruff
+        id: ruff-format
         run: |
           source .venv/bin/activate
           ruff format --diff
+      - name: Ruff import linter
+        id: ruff-check
+        run: |
+          source .venv/bin/activate
+          ruff check --select I

CHANGELOG.md

@@ -9,19 +9,140 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `DeepSeekLLMService` for DeepSeek integration with an OpenAI-compatible
+  interface. Added foundational example `14l-function-calling-deepseek.py`.
+
+- Added `FunctionCallResultProperties` dataclass to provide a structured way to
+  control function call behavior, including:
+
+  - `run_llm`: Controls whether to trigger LLM completion
+  - `on_context_updated`: Optional callback triggered after context update
+
+- Added a new foundational example `07e-interruptible-playht-http.py` for easy
+  testing of `PlayHTHttpTTSService`.
+
+- Added support for Google TTS Journey voices in `GoogleTTSService`.
+
+- Added `29-livekit-audio-chat.py`, as a new foundational examples for
+  `LiveKitTransportLayer`.
+
+- Added `enable_prejoin_ui`, `max_participants` and `start_video_off` params
+  to `DailyRoomProperties`.
+
+- Added `session_timeout` to `FastAPIWebsocketTransport` and
+  `WebsocketServerTransport` for configuring session timeouts (in
+  seconds). Triggers `on_session_timeout` for custom timeout handling.
+  See [examples/websocket-server/bot.py](https://github.com/pipecat-ai/pipecat/blob/main/examples/websocket-server/bot.py).
+
+- Added the new modalities option and helper function to set Gemini output
+  modalities.
+
+- Added `examples/foundational/26d-gemini-multimodal-live-text.py` which is
+  using Gemini as TEXT modality and using another TTS provider for TTS process.
+
+### Changed
+
+- Modified `OpenAIAssistantContextAggregator` to support controlled completions
+  and to emit context update callbacks via `FunctionCallResultProperties`.
+
+- Added `aws_session_token` to the `PollyTTSService`.
+
+- Changed the default model for `PlayHTHttpTTSService` to `Play3.0-mini-http`.
+
+- `api_key`, `aws_access_key_id` and `region` are no longer required parameters
+  for the PollyTTSService (AWSTTSService)
+
+- Added `session_timeout` example in `examples/websocket-server/bot.py` to
+  handle session timeout event.
+
+- Changed `InputParams` in
+  `src/pipecat/services/gemini_multimodal_live/gemini.py` to support different
+  modalities.
+
+### Fixed
+
+- Fixed a `PipelineTask` issue that would cause a dangling task after stopping
+  the pipeline with an `EndFrame`.
+
+- Fixed an import issue for `PlayHTHttpTTSService`.
+
+- Fixed an issue where languages couldn't be used with the `PlayHTHttpTTSService`.
+
+- Fixed an issue where `OpenAIRealtimeBetaLLMService` audio chunks were hitting
+  an error when truncating audio content.
+
+- Fixed an issue where setting the voice and model for `RimeHttpTTSService`
+  wasn't working.
+
+## [0.0.52] - 2024-12-24
+
+### Added
+
+- Constructor arguments for GoogleLLMService to directly set tools and tool_config.
+
+- Smart turn detection example (`22d-natural-conversation-gemini-audio.py`) that
+  leverages Gemini 2.0 capabilities ().
+  (see https://x.com/kwindla/status/1870974144831275410)
+
+- Added `DailyTransport.send_dtmf()` to send dial-out DTMF tones.
+
+- Added `DailyTransport.sip_call_transfer()` to forward SIP and PSTN calls to
+  another address or number. For example, transfer a SIP call to a different
+  SIP address or transfer a PSTN phone number to a different PSTN phone number.
+
+- Added `DailyTransport.sip_refer()` to transfer incoming SIP/PSTN calls from
+  outside Daily to another SIP/PSTN address.
+
+- Added an `auto_mode` input parameter to `ElevenLabsTTSService`. `auto_mode`
+  is set to `True` by default. Enabling this setting disables the chunk
+  schedule and all buffers, which reduces latency.
+
+- Added `KoalaFilter` which implement on device noise reduction using Koala
+  Noise Suppression.
+  (see https://picovoice.ai/platform/koala/)
+
+- Added `CerebrasLLMService` for Cerebras integration with an OpenAI-compatible
+  interface. Added foundational example `14k-function-calling-cerebras.py`.
+
+- Pipecat now supports Python 3.13. We had a dependency on the `audioop` package
+  which was deprecated and now removed on Python 3.13. We are now using
+  `audioop-lts` (https://github.com/AbstractUmbra/audioop) to provide the same
+  functionality.
+
+- Added timestamped conversation transcript support:
+
+  - New `TranscriptProcessor` factory provides access to user and assistant
+    transcript processors.
+  - `UserTranscriptProcessor` processes user speech with timestamps from
+    transcription.
+  - `AssistantTranscriptProcessor` processes assistant responses with LLM
+    context timestamps.
+  - Messages emitted with ISO 8601 timestamps indicating when they were spoken.
+  - Supports all LLM formats (OpenAI, Anthropic, Google) via standard message
+    format.
+  - New examples: `28a-transcription-processor-openai.py`,
+    `28b-transcription-processor-anthropic.py`, and
+    `28c-transcription-processor-gemini.py`.
+
 - Add support for more languages to ElevenLabs (Arabic, Croatian, Filipino,
   Tamil) and PlayHT (Afrikans, Albanian, Amharic, Arabic, Bengali, Croatian,
   Galician, Hebrew, Mandarin, Serbian, Tagalog, Urdu, Xhosa).
 
 ### Changed
 
-- It's no longer necessary to call `super().start/stop/cancel(frame)` if you
-  subclass and implement `AIService.start/stop/cancel()`. This is all now done
-  internally and will avoid possible issues if you forget to add it.
+- `PlayHTTTSService` uses the new v4 websocket API, which also fixes an issue
+  where text inputted to the TTS didn't return audio.
 
-- It's no longer necessary to call `super().process_frame(frame, direction)` if
-  you subclass and implement `FrameProcessor.process_frame()`. This is all now
-  done internally and will avoid possible issues if you forget to add it.
+- The default model for `ElevenLabsTTSService` is now `eleven_flash_v2_5`.
+
+- `OpenAIRealtimeBetaLLMService` now takes a `model` parameter in the
+  constructor.
+
+- Updated the default model for the `OpenAIRealtimeBetaLLMService`.
+
+- Room expiration (`exp`) in `DailyRoomProperties` is now optional (`None`) by
+  default instead of automatically setting a 5-minute expiration time. You must
+  explicitly set expiration time if desired.
 
 ### Deprecated
 
@@ -29,12 +150,33 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Fixed token counting in `GoogleLLMService`. Tokens were summed incorrectly
+  (double-counted in many cases).
+
+- Fixed an issue that could cause the bot to stop talking if there was a user
+  interruption before getting any audio from the TTS service.
+
+- Fixed an issue that would cause `ParallelPipeline` to handle `EndFrame`
+  incorrectly causing the main pipeline to not terminate or terminate too early.
+
+- Fixed an audio stuttering issue in `FastPitchTTSService`.
+
 - Fixed a `BaseOutputTransport` issue that was causing non-audio frames being
   processed before the previous audio frames were played. This will allow, for
   example, sending a frame `A` after a `TTSSpeakFrame` and the frame `A` will
   only be pushed downstream after the audio generated from `TTSSpeakFrame` has
   been spoken.
 
+- Fixed a `DeepgramSTTService` issue that was causing language to be passed as
+  an object instead of a string resulting in the connection to fail.
+
+## [0.0.51] - 2024-12-16
+
+### Fixed
+
+- Fixed an issue in websocket-based TTS services that was causing infinite
+  reconnections (Cartesia, ElevenLabs, PlayHT and LMNT).
+
 ## [0.0.50] - 2024-12-11
 
 ### Added

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024, Daily
+Copyright (c) 2024–2025, Daily
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -2,7 +2,7 @@
  <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
 </div></h1>
 
-[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) <a href="https://app.commanddash.io/agent/github_pipecat-ai_pipecat"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>
+[![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat) <a href="https://app.commanddash.io/agent/github_pipecat-ai_pipecat"><img src="https://img.shields.io/badge/AI-Code%20Agent-EB9FDA"></a>
 
 Pipecat is an open source Python framework for building voice and multimodal conversational agents. It handles the complex orchestration of AI services, network transport, audio processing, and multimodal interactions, letting you focus on creating engaging experiences.
 
@@ -55,19 +55,19 @@ pip install "pipecat-ai[option,...]"
 
 Available options include:
 
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | Install Command Example                 |
-| ------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/api-reference/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/api-reference/services/stt/azure), [Deepgram](https://docs.pipecat.ai/api-reference/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/api-reference/services/stt/gladia), [Whisper](https://docs.pipecat.ai/api-reference/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                               | `pip install "pipecat-ai[deepgram]"`    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/api-reference/services/llm/anthropic), [Azure](https://docs.pipecat.ai/api-reference/services/llm/azure), [Fireworks AI](https://docs.pipecat.ai/api-reference/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/api-reference/services/llm/gemini), [Grok](https://docs.pipecat.ai/api-reference/services/llm/grok), [Groq](https://docs.pipecat.ai/api-reference/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/api-reference/services/llm/nim), [Ollama](https://docs.pipecat.ai/api-reference/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/api-reference/services/llm/openai), [Together AI](https://docs.pipecat.ai/api-reference/services/llm/together)                                                     | `pip install "pipecat-ai[openai]"`      |
-| Text-to-Speech      | [AWS](https://docs.pipecat.ai/api-reference/services/tts/aws), [Azure](https://docs.pipecat.ai/api-reference/services/tts/azure), [Cartesia](https://docs.pipecat.ai/api-reference/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/api-reference/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/api-reference/services/tts/elevenlabs), [Google](https://docs.pipecat.ai/api-reference/services/tts/google), [LMNT](https://docs.pipecat.ai/api-reference/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/api-reference/services/tts/openai), [PlayHT](https://docs.pipecat.ai/api-reference/services/tts/playht), [Rime](https://docs.pipecat.ai/api-reference/services/tts/rime), [XTTS](https://docs.pipecat.ai/api-reference/services/tts/xtts) | `pip install "pipecat-ai[cartesia]"`    |
-| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/api-reference/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | `pip install "pipecat-ai[openai]"`      |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/api-reference/services/transport/daily), WebSocket, Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                | `pip install "pipecat-ai[daily]"`       |
-| Video               | [Tavus](https://docs.pipecat.ai/api-reference/services/video/tavus), [Simli](https://docs.pipecat.ai/api-reference/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[tavus,simli]"` |
-| Vision & Image      | [Moondream](https://docs.pipecat.ai/api-reference/services/vision/moondream), [fal](https://docs.pipecat.ai/api-reference/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[moondream]"`   |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/api-reference/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/api-reference/utilities/audio/krisp-filter), [Noisereduce](https://docs.pipecat.ai/api-reference/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[silero]"`      |
-| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/api-reference/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/api-reference/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[canonical]"`   |
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | Install Command Example                 |
+| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                                                                                                                                                            | `pip install "pipecat-ai[deepgram]"`    |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
+| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                              | `pip install "pipecat-ai[cartesia]"`    |
+| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[openai]"`      |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[daily]"`       |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[tavus,simli]"` |
+| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | `pip install "pipecat-ai[moondream]"`   |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[silero]"`      |
+| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             | `pip install "pipecat-ai[canonical]"`   |
 
-📚 [View full services documentation →](https://docs.pipecat.ai/api-reference/services/supported-services)
+📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 
 ## Code examples
 
@@ -197,9 +197,7 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :hook ((python-mode . lazy-ruff-mode))
   :config
   (setq lazy-ruff-format-command "ruff format")
-  (setq lazy-ruff-only-format-block t)
-  (setq lazy-ruff-only-format-region t)
-  (setq lazy-ruff-only-format-buffer t))
+  (setq lazy-ruff-check-command "ruff check --select I"))
 ```
 
 `ruff` was installed in the `venv` environment described before, so you should be able to use [pyvenv-auto](https://github.com/ryotaro612/pyvenv-auto) to automatically load that environment inside Emacs.
@@ -209,7 +207,6 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :ensure t
   :defer t
   :hook ((python-mode . pyvenv-auto-run)))
-
 ```
 
 ### Visual Studio Code
@@ -224,6 +221,16 @@ Install the
 }
 ```
 
+### PyCharm
+
+`ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
+
+1. **Name**: `Ruff formatter`
+2. **File type**: `Python`
+3. **Working directory**: `$ContentRoot$`
+4. **Arguments**: `format $FilePath$`
+5. **Program**: `$PyInterpreterDirectory$/ruff`
+
 ## Contributing
 
 We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:

dev-requirements.txt

@@ -1,8 +1,9 @@
-build~=1.2.1
-grpcio-tools~=1.65.4
+build~=1.2.2
+grpcio-tools~=1.68.1
 pip-tools~=7.4.1
-pyright~=1.1.376
-pytest~=8.3.2
-ruff~=0.6.7
-setuptools~=72.2.0
+pyright~=1.1.390
+pytest~=8.3.4
+ruff~=0.8.3
+setuptools~=75.6.0
 setuptools_scm~=8.1.0
+python-dotenv~=1.0.1

dot-env.template

@@ -60,3 +60,24 @@ SIMLI_FACE_ID=...
 
 # Krisp
 KRISP_MODEL_PATH=...
+
+# DeepSeek
+DEEPSEEK_API_KEY=...
+
+# Groq
+GROQ_API_KEY=...
+
+# Grok
+GROK_API_KEY=...
+
+# Together.ai
+TOGETHER_API_KEY=...
+
+# Cerebras
+CEREBRAS_API_KEY=...
+
+# Fish Audio
+FISH_API_KEY=...
+
+# Assembly AI
+ASSEMBLYAI_API_KEY=...

examples/canonical-metrics/bot.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -15,7 +15,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -124,7 +124,7 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):

examples/canonical-metrics/runner.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/canonical-metrics/server.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/chatbot-audio-recording/bot.py

@@ -1,24 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiofiles
 import asyncio
+import datetime
 import io
 import os
 import sys
-
-import aiohttp
-import datetime
 import wave
+
+import aiofiles
+import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -134,7 +134,7 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):

examples/chatbot-audio-recording/runner.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/chatbot-audio-recording/server.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/deployment/flyio-example/bot.py

@@ -1,22 +1,21 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -76,7 +75,7 @@ async def main(room_url: str, token: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/deployment/flyio-example/bot_runner.py

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import argparse
-import subprocess
 import os
-
+import subprocess
 from contextlib import asynccontextmanager
 
-from fastapi import FastAPI, Request, HTTPException
+import aiohttp
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse
 
 from pipecat.transports.services.helpers.daily_rest import (
     DailyRESTHelper,
     DailyRoomObject,
-    DailyRoomProperties,
     DailyRoomParams,
+    DailyRoomProperties,
 )
 
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 

examples/deployment/modal-example/app.py

@@ -2,12 +2,11 @@ import os
 
 import aiohttp
 import modal
+from bot import _voice_bot_process
 from fastapi import HTTPException
 from fastapi.responses import JSONResponse
 from loguru import logger
 
-from bot import _voice_bot_process
-
 MAX_SESSION_TIME = 15 * 60  # 15 minutes
 
 app = modal.App("pipecat-modal")

examples/deployment/modal-example/bot.py

@@ -13,7 +13,7 @@ logger.add(sys.stderr, level="DEBUG")
 
 async def main(room_url: str, token: str):
     from pipecat.audio.vad.silero import SileroVADAnalyzer
-    from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+    from pipecat.frames.frames import EndFrame
     from pipecat.pipeline.pipeline import Pipeline
     from pipecat.pipeline.runner import PipelineRunner
     from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -75,7 +75,7 @@ async def main(room_url: str, token: str):
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/deployment/modal-example/requirements.txt

@@ -1,5 +1,5 @@
 python-dotenv==1.0.1
-modal==0.65.48
-pipecat-ai[daily,silero,cartesia,openai]==0.0.48
-fastapi==0.115.4
-aiohttp==3.11.9
+modal==0.71.3
+pipecat-ai[daily,silero,cartesia,openai]==0.0.52
+fastapi==0.115.6
+aiohttp==3.11.11

examples/dialin-chatbot/bot_daily.py

@@ -1,21 +1,20 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyDialinSettings
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyDialinSettings, DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -82,7 +81,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/dialin-chatbot/bot_runner.py

@@ -7,14 +7,14 @@ provisioning a room and starting a Pipecat bot in response.
 Refer to README for more information.
 """
 
-import aiohttp
-import os
 import argparse
+import os
 import subprocess
-
 from contextlib import asynccontextmanager
 
-from fastapi import FastAPI, Request, HTTPException
+import aiohttp
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse, PlainTextResponse
 from twilio.twiml.voice_response import VoiceResponse
@@ -22,13 +22,11 @@ from twilio.twiml.voice_response import VoiceResponse
 from pipecat.transports.services.helpers.daily_rest import (
     DailyRESTHelper,
     DailyRoomObject,
+    DailyRoomParams,
     DailyRoomProperties,
     DailyRoomSipParams,
-    DailyRoomParams,
 )
 
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 

examples/dialin-chatbot/bot_twilio.py

@@ -1,24 +1,22 @@
+import argparse
 import asyncio
 import os
 import sys
-import argparse
+
+from dotenv import load_dotenv
+from loguru import logger
+from twilio.rest import Client
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.frames.frames import LLMMessagesFrame, EndFrame
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from twilio.rest import Client
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -85,7 +83,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
         await transport.capture_participant_transcription(participant["id"])
-        await task.queue_frames([LLMMessagesFrame(messages)])
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
     @transport.event_handler("on_participant_left")
     async def on_participant_left(transport, participant, reason):

examples/foundational/01-say-one-thing.py

@@ -1,26 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import EndFrame, TTSSpeakFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.task import PipelineTask
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
 from runner import configure
 
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 

examples/foundational/01a-local-audio.py

@@ -1,14 +1,16 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,10 +19,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.audio import LocalAudioTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/01b-livekit-audio.py

@@ -4,6 +4,9 @@ import os
 import sys
 
 import aiohttp
+from dotenv import load_dotenv
+from livekit import api
+from loguru import logger
 
 from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -12,12 +15,6 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
 
-from livekit import api
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/01c-fastpitch.py

@@ -1,26 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import EndFrame, TTSSpeakFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.task import PipelineTask
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.services.riva import FastPitchTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
 from runner import configure
 
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.riva import FastPitchTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 

examples/foundational/02-llm-say-one-thing.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,12 +21,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/03-still-frame.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import EndFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,12 +20,6 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.services.fal import FalImageGenService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,16 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,10 +21,6 @@ from pipecat.services.fal import FalImageGenService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/04-utterance-and-speech.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -8,27 +8,24 @@
 # This example broken on latest pipecat and needs updating.
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
-from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
-from pipecat.pipeline.pipeline import Pipeline
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
 
 from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
+from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.azure import AzureLLMService, AzureTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.transport_services import TransportServiceOutput
 from pipecat.services.transports.daily_transport import DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,16 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
-
 from dataclasses import dataclass
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
     DataFrame,
     Frame,
@@ -22,19 +25,13 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.aggregators.sentence import SentenceAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.fal import FalImageGenService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -56,6 +53,8 @@ class MonthPrepender(FrameProcessor):
         self.prepend_to_next_text_frame = False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, MonthFrame):
             self.most_recent_month = frame.month
         elif self.prepend_to_next_text_frame and isinstance(frame, TextFrame):

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

@@ -1,23 +1,25 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import (
     Frame,
+    LLMMessagesFrame,
     OutputAudioRawFrame,
+    TextFrame,
     TTSAudioRawFrame,
     URLImageRawFrame,
-    LLMMessagesFrame,
-    TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -26,15 +28,11 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.sentence import SentenceAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
-from pipecat.services.openai import OpenAILLMService
 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 loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -62,6 +60,8 @@ async def main():
                     self.text = ""
 
                 async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    await super().process_frame(frame, direction)
+
                     if isinstance(frame, TextFrame):
                         self.text = frame.text
                     await self.push_frame(frame, direction)
@@ -73,6 +73,8 @@ async def main():
                     self.frame = None
 
                 async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    await super().process_frame(frame, direction)
+
                     if isinstance(frame, TTSAudioRawFrame):
                         self.audio.extend(frame.audio)
                         self.frame = OutputAudioRawFrame(
@@ -86,6 +88,8 @@ async def main():
                     self.frame = None
 
                 async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    await super().process_frame(frame, direction)
+
                     if isinstance(frame, URLImageRawFrame):
                         self.frame = frame
                     await self.push_frame(frame, direction)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, LLMMessagesFrame, MetricsFrame
+from pipecat.frames.frames import EndFrame, Frame, MetricsFrame
 from pipecat.metrics.metrics import (
     LLMUsageMetricsData,
     ProcessingMetricsData,
@@ -113,7 +113,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,18 +1,21 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
 from PIL import Image
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, OutputImageRawFrame, SystemFrame, TextFrame
+from pipecat.frames.frames import EndFrame, Frame, OutputImageRawFrame, SystemFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -20,14 +23,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyTransport
-
-from pipecat.transports.services.daily import DailyParams
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -47,6 +43,8 @@ class ImageSyncAggregator(FrameProcessor):
         self._waiting_image_bytes = self._waiting_image.tobytes()
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if not isinstance(frame, SystemFrame) and direction == FrameDirection.DOWNSTREAM:
             await self.push_frame(
                 OutputImageRawFrame(
@@ -128,6 +126,10 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
 
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

examples/foundational/07-interruptible-vad.py

@@ -1,30 +1,28 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import LLMMessagesFrame
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.audio.vad.silero import SileroVAD
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.audio.vad.silero import SileroVAD
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -92,7 +90,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

examples/foundational/07-interruptible.py

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -90,7 +88,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -78,13 +78,25 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -9,9 +9,17 @@ import os
 import sys
 
 import aiohttp
+from dotenv import load_dotenv
+from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain_core.chat_history import BaseChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+from langchain_openai import ChatOpenAI
+from loguru import logger
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -23,18 +31,6 @@ from pipecat.processors.frameworks.langchain import LangchainProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain_community.chat_message_histories import ChatMessageHistory
-from langchain_core.chat_history import BaseChatMessageHistory
-from langchain_core.runnables.history import RunnableWithMessageHistory
-from langchain_openai import ChatOpenAI
-
-from loguru import logger
-
-from runner import configure
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 
@@ -105,7 +101,15 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
@@ -118,6 +122,10 @@ async def main():
             messages = [({"content": "Please briefly introduce yourself to the user."})]
             await task.queue_frames([LLMMessagesFrame(messages)])
 
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -16,7 +16,7 @@ from runner import configure
 
 from pipecat.frames.frames import (
     BotInterruptionFrame,
-    LLMMessagesFrame,
+    EndFrame,
     StopInterruptionFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
@@ -80,7 +80,15 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @stt.event_handler("on_speech_started")
         async def on_speech_started(stt, *args, **kwargs):
@@ -94,7 +102,11 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -73,13 +73,25 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,14 +11,14 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 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.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
@@ -88,7 +88,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -0,0 +1,105 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.services.openai import OpenAILLMService
+from pipecat.services.playht import PlayHTHttpTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = PlayHTHttpTTSService(
+            user_id=os.getenv("PLAYHT_USER_ID"),
+            api_key=os.getenv("PLAYHT_API_KEY"),
+            voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -91,7 +91,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -18,13 +22,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.azure import AzureLLMService, AzureSTTService, AzureTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -85,14 +82,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -11,14 +11,14 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 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.services.openai import OpenAILLMService, OpenAITTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
@@ -70,14 +70,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,21 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
+import time
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,13 +24,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openpipe import OpenPipeLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-import time
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -82,14 +80,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.openai import OpenAILLMService
 from pipecat.services.xtts import XTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -76,14 +74,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import EndFrame, LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,22 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         # Register an event handler to exit the application when the user leaves.
         @transport.event_handler("on_participant_left")

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

@@ -1,16 +1,20 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,12 +23,6 @@ from pipecat.services.lmnt import LmntTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -73,14 +71,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -90,7 +90,10 @@ async def main():
         task = PipelineTask(
             pipeline,
             PipelineParams(
-                allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
             ),
         )
 
@@ -98,7 +101,11 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -80,14 +80,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,6 +22,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.google import GoogleTTSService
 from pipecat.services.openai import OpenAILLMService
+from pipecat.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -50,8 +51,8 @@ async def main():
         stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
         tts = GoogleTTSService(
-            voice_id="en-US-Neural2-J",
-            params=GoogleTTSService.InputParams(language="en-US", rate="1.05"),
+            voice_id="en-US-Journey-F",
+            params=GoogleTTSService.InputParams(language=Language.EN_US),
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -78,14 +79,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -79,14 +79,26 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -13,19 +13,16 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.audio.filters.krisp_filter import KrispFilter
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 from pipecat.vad.silero import SileroVADAnalyzer
-from pipecat.audio.filters.krisp_filter import KrispFilter
 
 load_dotenv(override=True)
 
@@ -63,28 +60,40 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -89,7 +89,11 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,7 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -81,7 +81,11 @@ async def main():
         async def on_first_participant_joined(transport, participant):
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

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

@@ -1,41 +1,41 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
-
-import google.ai.generativelanguage as glm
-
 from dataclasses import dataclass
+
+import aiohttp
+import google.ai.generativelanguage as glm
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-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.services.cartesia import CartesiaTTSService
-from pipecat.services.google import GoogleLLMService
-from pipecat.processors.frame_processor import FrameProcessor
-from pipecat.transports.services.daily import DailyParams, DailyTransport
 from pipecat.frames.frames import (
-    LLMFullResponseStartFrame,
-    LLMFullResponseEndFrame,
-    InputAudioRawFrame,
+    EndFrame,
     Frame,
+    InputAudioRawFrame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
     StartInterruptionFrame,
     TextFrame,
     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.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.frame_processor import FrameProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.google import GoogleLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -82,6 +82,8 @@ class UserAudioCollector(FrameProcessor):
         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. :-)
@@ -124,6 +126,7 @@ class TranscriptExtractor(FrameProcessor):
         self._accumulating_transcript = False
 
     async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
         if isinstance(frame, LLMFullResponseStartFrame):
             self._processing_llm_response = True
             self._accumulating_transcript = True
@@ -177,6 +180,8 @@ class TanscriptionContextFixup(FrameProcessor):
             self._context.messages[-1].parts[-1].text += f"\n\n{marker}\n{self._transcript}\n"
 
     async def process_frame(self, frame, direction):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, MagicDemoTranscriptionFrame):
             self._transcript = frame.text
         elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(
@@ -264,6 +269,10 @@ async def main():
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

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

@@ -0,0 +1,103 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
+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.services.fish import FishAudioTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = FishAudioTTSService(
+            api_key=os.getenv("FISH_API_KEY"),
+            model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/08-bots-arguing.py

@@ -1,20 +1,19 @@
-from typing import Tuple
-import aiohttp
 import asyncio
 import logging
 import os
-from pipecat.processors.aggregators import SentenceAggregator
-from pipecat.pipeline.pipeline import Pipeline
+from typing import Tuple
 
-from pipecat.transports.services.daily import DailyTransport
+import aiohttp
+from dotenv import load_dotenv
+from runner import configure
+
+from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.processors.aggregators import SentenceAggregator
 from pipecat.services.azure import AzureLLMService, AzureTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.fal import FalImageGenService
-from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
-
-from runner import configure
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyTransport
 
 load_dotenv(override=True)
 

examples/foundational/09-mirror.py

@@ -1,13 +1,17 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
@@ -19,13 +23,7 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.transports.services.daily import DailyTransport, DailyParams
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -35,6 +33,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class MirrorProcessor(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, InputAudioRawFrame):
             await self.push_frame(
                 OutputAudioRawFrame(

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

@@ -1,15 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
-
 import tkinter as tk
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
@@ -25,12 +28,6 @@ from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -39,6 +36,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class MirrorProcessor(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, InputAudioRawFrame):
             await self.push_frame(
                 OutputAudioRawFrame(

examples/foundational/10-wake-phrase.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,12 +23,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/11-sound-effects.py

@@ -1,15 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 import wave
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
@@ -29,12 +33,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -60,6 +58,8 @@ for file in sound_files:
 
 class OutboundSoundEffectWrapper(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, LLMFullResponseEndFrame):
             await self.push_frame(sounds["ding1.wav"])
             # In case anything else downstream needs it
@@ -70,6 +70,8 @@ class OutboundSoundEffectWrapper(FrameProcessor):
 
 class InboundSoundEffectWrapper(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, OpenAILLMContextFrame):
             await self.push_frame(sounds["ding2.wav"])
             # In case anything else downstream needs it

examples/foundational/12-describe-video.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.moondream import MoondreamService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -42,6 +40,8 @@ class UserImageRequester(FrameProcessor):
         self._participant_id = participant_id
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
                 UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM

examples/foundational/12a-describe-video-gemini-flash.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.google import GoogleLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -42,6 +40,8 @@ class UserImageRequester(FrameProcessor):
         self._participant_id = participant_id
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
                 UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM

examples/foundational/12b-describe-video-gpt-4o.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,12 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -42,6 +40,8 @@ class UserImageRequester(FrameProcessor):
         self._participant_id = participant_id
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
                 UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM

examples/foundational/12c-describe-video-anthropic.py

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -17,16 +21,10 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
 from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -42,6 +40,8 @@ class UserImageRequester(FrameProcessor):
         self._participant_id = participant_id
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
                 UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM

examples/foundational/13-whisper-transcription.py

@@ -1,13 +1,17 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,12 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper import WhisperSTTService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -30,6 +28,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class TranscriptionLogger(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -7,6 +7,9 @@
 import asyncio
 import sys
 
+from dotenv import load_dotenv
+from loguru import logger
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -16,10 +19,6 @@ from pipecat.services.whisper import WhisperSTTService
 from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.audio import LocalAudioTransport
 
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -28,6 +27,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class TranscriptionLogger(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 

examples/foundational/13b-deepgram-transcription.py

@@ -1,28 +1,26 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.deepgram import DeepgramSTTService, LiveOptions, Language
+from pipecat.services.deepgram import DeepgramSTTService, Language, LiveOptions
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -31,6 +29,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class TranscriptionLogger(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 

examples/foundational/13c-gladia-transcription.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -29,6 +29,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class TranscriptionLogger(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 

examples/foundational/13d-assemblyai-transcription.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -29,6 +29,8 @@ logger.add(sys.stderr, level="DEBUG")
 
 class TranscriptionLogger(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 

examples/foundational/14-function-calling.py

@@ -1,14 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,14 +22,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 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.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,29 +1,27 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 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.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/14c-function-calling-together.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/foundational/14d-function-calling-video.py

@@ -1,14 +1,19 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -17,14 +22,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -18,12 +22,6 @@ from pipecat.services.google import GoogleLLMService
 from pipecat.services.openai import OpenAILLMContext
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -65,7 +65,7 @@ async def main():
         )
 
         llm = NimLLMService(
-            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
+            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.3-70b-instruct"
         )
         # Register a function_name of None to get all functions
         # sent to the same callback with an additional function_name parameter.
@@ -76,18 +76,18 @@ async def main():
                 type="function",
                 function={
                     "name": "get_current_weather",
-                    "description": "Get the current weather",
+                    "description": "Returns the current weather at a location, if one is specified, and defaults to the user's location.",
                     "parameters": {
                         "type": "object",
                         "properties": {
                             "location": {
                                 "type": "string",
-                                "description": "The city and state, e.g. San Francisco, CA",
+                                "description": "The location to find the weather of, or if not provided, it's the default location.",
                             },
                             "format": {
                                 "type": "string",
                                 "enum": ["celsius", "fahrenheit"],
-                                "description": "The temperature unit to use. Infer this from the users location.",
+                                "description": "Whether to use SI or USCS units (celsius or fahrenheit).",
                             },
                         },
                         "required": ["location", "format"],

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

@@ -0,0 +1,148 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.cerebras import CerebrasLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = CerebrasLLMService(api_key=os.getenv("CEREBRAS_API_KEY"), model="llama-3.3-70b")
+        # Register a function_name of None to get all functions
+        # sent to the same callback with an additional function_name parameter.
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather for a specific location. You MUST use this function whenever asked about weather.",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Use fahrenheit for US locations, celsius for others.",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 
+
+You have one functions available:
+
+1. get_current_weather is used to get current weather information.
+
+Infer whether to use Fahrenheit or Celsius automatically based on the location, unless the user specifies a preference.
+
+Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
+
+        Respond to what the user said in a creative and helpful way.""",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,148 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepseek import DeepSeekLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    # note: we can't push a frame to the LLM here. the bot
+    # can interrupt itself and/or cause audio overlapping glitches.
+    # possible question for Aleix and Chad about what the right way
+    # to trigger speech is, now, with the new queues/async/sync refactors.
+    # await llm.push_frame(TextFrame("Let me check on that."))
+    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    await result_callback({"conditions": "nice", "temperature": "75"})
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = DeepSeekLLMService(api_key=os.getenv("DEEPSEEK_API_KEY"), model="deepseek-chat")
+        # Register a function_name of None to get all functions
+        # sent to the same callback with an additional function_name parameter.
+        llm.register_function(None, fetch_weather_from_api, start_callback=start_fetch_weather)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current weather for a specific location. You MUST use this function whenever asked about weather.",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "location": {
+                                "type": "string",
+                                "description": "The city and state, e.g. San Francisco, CA",
+                            },
+                            "format": {
+                                "type": "string",
+                                "enum": ["celsius", "fahrenheit"],
+                                "description": "The temperature unit to use. Use fahrenheit for US locations, celsius for others.",
+                            },
+                        },
+                        "required": ["location", "format"],
+                    },
+                },
+            )
+        ]
+        messages = [
+            {
+                "role": "system",
+                "content": """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. 
+
+You have one functions available:
+
+1. get_current_weather is used to get current weather information.
+
+Infer whether to use Fahrenheit or Celsius automatically based on the location, unless the user specifies a preference.
+
+Start by asking me for my location. Then, use 'get_weather_current' to give me a forecast.
+
+        Respond to what the user said in a creative and helpful way.""",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/15-switch-voices.py

@@ -1,18 +1,22 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
-from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+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
@@ -21,14 +25,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -149,7 +145,7 @@ async def main():
                     "content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {current_voice}.",
                 }
             )
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         runner = PipelineRunner()
 

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

@@ -1,20 +1,23 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
 from deepgram import LiveOptions
+from dotenv import load_dotenv
+from loguru import logger
+from openai.types.chat import ChatCompletionToolParam
+from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
-from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+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
@@ -24,14 +27,6 @@ from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from openai.types.chat import ChatCompletionToolParam
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -143,7 +138,7 @@ async def main():
                     "content": f"Please introduce yourself to the user and let them know the languages you speak. Your initial responses should be in {current_language}.",
                 }
             )
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         runner = PipelineRunner()
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -14,7 +14,6 @@ from loguru import logger
 from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -98,7 +97,7 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         # Handle "latency-ping" messages. The client will send app messages that look like
         # this:

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

@@ -1,14 +1,18 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -20,12 +24,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -102,7 +100,7 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         runner = PipelineRunner()
 

examples/foundational/18-gstreamer-filesrc.py

@@ -1,26 +1,24 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
-import aiohttp
 import argparse
+import asyncio
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure_with_args
+
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.gstreamer.pipeline_source import GStreamerPipelineSource
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure_with_args
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

examples/foundational/18a-gstreamer-videotestsrc.py

@@ -1,25 +1,23 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.gstreamer.pipeline_source import GStreamerPipelineSource
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -24,9 +24,8 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
 )
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.cartesia import CartesiaTTSService
-
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -24,9 +24,8 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import (
     OpenAILLMContext,
 )
-from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
-
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -26,7 +26,6 @@ from pipecat.processors.aggregators.openai_llm_context import (
 )
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.google import GoogleLLMService
-
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)

examples/foundational/21-tavus-layer.py

@@ -1,34 +1,29 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
-
 from typing import Any, Mapping
 
-from pipecat.frames.frames import LLMMessagesFrame
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.openai import OpenAILLMService
 from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.services.tavus import TavusVideoService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-
-from loguru import logger
-
-from dotenv import load_dotenv
 
 load_dotenv(override=True)
 
@@ -41,7 +36,6 @@ async def main():
         tavus = TavusVideoService(
             api_key=os.getenv("TAVUS_API_KEY"),
             replica_id=os.getenv("TAVUS_REPLICA_ID"),
-            persona_id=os.getenv("TAVUS_PERSONA_ID", "pipecat0"),
             session=session,
         )
 
@@ -76,19 +70,19 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 tavus,  # Tavus output layer
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -122,7 +116,11 @@ async def main():
                 messages.append(
                     {"role": "system", "content": "Please introduce yourself to the user."}
                 )
-                await task.queue_frames([LLMMessagesFrame(messages)])
+                await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         runner = PipelineRunner()
 

examples/foundational/22-natural-conversation.py

@@ -1,18 +1,22 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
+from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.gated_openai_llm_context import GatedOpenAILLMContextAggregator
@@ -26,12 +30,6 @@ from pipecat.services.openai import OpenAILLMService
 from pipecat.sync.event_notifier import EventNotifier
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -157,7 +155,7 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         runner = PipelineRunner()
 

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

@@ -1,53 +1,51 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 import time
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.parallel_pipeline import ParallelPipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import (
-    OpenAILLMContext,
-)
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.deepgram import DeepgramSTTService
-from pipecat.services.openai import OpenAILLMService
-from pipecat.sync.event_notifier import EventNotifier
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.processors.frame_processor import FrameProcessor, FrameDirection
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
     Frame,
+    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
     StopInterruptionFrame,
     SystemFrame,
+    TextFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContextFrame
-from pipecat.sync.base_notifier import BaseNotifier
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+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,
+    OpenAILLMContextFrame,
+)
 from pipecat.processors.filters.function_filter import FunctionFilter
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.user_idle_processor import UserIdleProcessor
-
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.sync.base_notifier import BaseNotifier
+from pipecat.sync.event_notifier import EventNotifier
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -64,6 +62,7 @@ class StatementJudgeContextFilter(FrameProcessor):
         self._notifier = notifier
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
         # We must not block system frames.
         if isinstance(frame, SystemFrame):
             await self.push_frame(frame, direction)
@@ -117,6 +116,7 @@ class CompletenessCheck(FrameProcessor):
         self._notifier = notifier
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
         if isinstance(frame, TextFrame) and frame.text == "YES":
             logger.debug("Completeness check YES")
             await self.push_frame(UserStoppedSpeakingFrame())
@@ -139,6 +139,8 @@ class OutputGate(FrameProcessor):
         self._gate_open = True
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         # We must not block system frames.
         if isinstance(frame, SystemFrame):
             if isinstance(frame, StartFrame):
@@ -309,7 +311,7 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_app_message")
         async def on_app_message(transport, message, sender):

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -101,12 +101,12 @@ HIGH PRIORITY SIGNALS:
 
 Examples:
 # Complete Wh-question
-[{"role": "assistant", "content": "I can help you learn."},
+[{"role": "assistant", "content": "I can help you learn."}, 
  {"role": "user", "content": "What's the fastest way to learn Spanish"}]
 Output: YES
 
 # Complete Yes/No question despite STT error
-[{"role": "assistant", "content": "I know about planets."},
+[{"role": "assistant", "content": "I know about planets."}, 
  {"role": "user", "content": "Is is Jupiter the biggest planet"}]
 Output: YES
 
@@ -118,12 +118,12 @@ Output: YES
 
 Examples:
 # Direct instruction
-[{"role": "assistant", "content": "I can explain many topics."},
+[{"role": "assistant", "content": "I can explain many topics."}, 
  {"role": "user", "content": "Tell me about black holes"}]
 Output: YES
 
 # Action demand
-[{"role": "assistant", "content": "I can help with math."},
+[{"role": "assistant", "content": "I can help with math."}, 
  {"role": "user", "content": "Solve this equation x plus 5 equals 12"}]
 Output: YES
 
@@ -134,12 +134,12 @@ Output: YES
 
 Examples:
 # Specific answer
-[{"role": "assistant", "content": "What's your favorite color?"},
+[{"role": "assistant", "content": "What's your favorite color?"}, 
  {"role": "user", "content": "I really like blue"}]
 Output: YES
 
 # Option selection
-[{"role": "assistant", "content": "Would you prefer morning or evening?"},
+[{"role": "assistant", "content": "Would you prefer morning or evening?"}, 
  {"role": "user", "content": "Morning"}]
 Output: YES
 
@@ -153,17 +153,17 @@ MEDIUM PRIORITY SIGNALS:
 
 Examples:
 # Self-correction reaching completion
-[{"role": "assistant", "content": "What would you like to know?"},
+[{"role": "assistant", "content": "What would you like to know?"}, 
  {"role": "user", "content": "Tell me about... no wait, explain how rainbows form"}]
 Output: YES
 
 # Topic change with complete thought
-[{"role": "assistant", "content": "The weather is nice today."},
+[{"role": "assistant", "content": "The weather is nice today."}, 
  {"role": "user", "content": "Actually can you tell me who invented the telephone"}]
 Output: YES
 
 # Mid-sentence completion
-[{"role": "assistant", "content": "Hello I'm ready."},
+[{"role": "assistant", "content": "Hello I'm ready."}, 
  {"role": "user", "content": "What's the capital of? France"}]
 Output: YES
 
@@ -175,12 +175,12 @@ Output: YES
 
 Examples:
 # Acknowledgment
-[{"role": "assistant", "content": "Should we talk about history?"},
+[{"role": "assistant", "content": "Should we talk about history?"}, 
  {"role": "user", "content": "Sure"}]
 Output: YES
 
 # Disagreement with completion
-[{"role": "assistant", "content": "Is that what you meant?"},
+[{"role": "assistant", "content": "Is that what you meant?"}, 
  {"role": "user", "content": "No not really"}]
 Output: YES
 
@@ -194,12 +194,12 @@ LOW PRIORITY SIGNALS:
 
 Examples:
 # Word repetition but complete
-[{"role": "assistant", "content": "I can help with that."},
+[{"role": "assistant", "content": "I can help with that."}, 
  {"role": "user", "content": "What what is the time right now"}]
 Output: YES
 
 # Missing punctuation but complete
-[{"role": "assistant", "content": "I can explain that."},
+[{"role": "assistant", "content": "I can explain that."}, 
  {"role": "user", "content": "Please tell me how computers work"}]
 Output: YES
 
@@ -211,12 +211,12 @@ Output: YES
 
 Examples:
 # Filler words but complete
-[{"role": "assistant", "content": "What would you like to know?"},
+[{"role": "assistant", "content": "What would you like to know?"}, 
  {"role": "user", "content": "Um uh how do airplanes fly"}]
 Output: YES
 
 # Thinking pause but incomplete
-[{"role": "assistant", "content": "I can explain anything."},
+[{"role": "assistant", "content": "I can explain anything."}, 
  {"role": "user", "content": "Well um I want to know about the"}]
 Output: NO
 
@@ -241,17 +241,17 @@ DECISION RULES:
 
 Examples:
 # Incomplete despite corrections
-[{"role": "assistant", "content": "What would you like to know about?"},
+[{"role": "assistant", "content": "What would you like to know about?"}, 
  {"role": "user", "content": "Can you tell me about"}]
 Output: NO
 
 # Complete despite multiple artifacts
-[{"role": "assistant", "content": "I can help you learn."},
+[{"role": "assistant", "content": "I can help you learn."}, 
  {"role": "user", "content": "How do you I mean what's the best way to learn programming"}]
 Output: YES
 
 # Trailing off incomplete
-[{"role": "assistant", "content": "I can explain anything."},
+[{"role": "assistant", "content": "I can explain anything."}, 
  {"role": "user", "content": "I was wondering if you could tell me why"}]
 Output: NO
 """
@@ -268,6 +268,7 @@ class StatementJudgeContextFilter(FrameProcessor):
         self._notifier = notifier
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
         # We must not block system frames.
         if isinstance(frame, SystemFrame):
             await self.push_frame(frame, direction)
@@ -319,6 +320,8 @@ class CompletenessCheck(FrameProcessor):
         self._notifier = notifier
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         if isinstance(frame, TextFrame) and frame.text == "YES":
             logger.debug("!!! Completeness check YES")
             await self.push_frame(UserStoppedSpeakingFrame())
@@ -341,6 +344,8 @@ class OutputGate(FrameProcessor):
         self._gate_open = True
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         # We must not block system frames.
         if isinstance(frame, SystemFrame):
             if isinstance(frame, StartFrame):
@@ -520,7 +525,7 @@ async def main():
                     "content": "Start by just saying \"Hello I'm ready.\" Don't say anything else.",
                 }
             )
-            await task.queue_frames([LLMMessagesFrame(messages)])
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
 
         @transport.event_handler("on_app_message")
         async def on_app_message(transport, message, sender):

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

@@ -1,95 +1,381 @@
 #
-# Copyright (c) 2024, Daily
+# Copyright (c) 2024–2025, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import aiohttp
 import asyncio
 import os
 import sys
 import time
 
+import aiohttp
+import google.ai.generativelanguage as glm
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame, TextFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.parallel_pipeline import ParallelPipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.services.deepgram import DeepgramSTTService
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import (
-    OpenAILLMContext,
-)
-from pipecat.services.cartesia import CartesiaTTSService
-from pipecat.services.google import GoogleLLMService, GoogleLLMContext
-from pipecat.sync.event_notifier import EventNotifier
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.processors.frame_processor import FrameProcessor, FrameDirection
 from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
     Frame,
     InputAudioRawFrame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMMessagesFrame,
     StartFrame,
     StartInterruptionFrame,
     StopInterruptionFrame,
     SystemFrame,
+    TextFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContextFrame
-from pipecat.sync.base_notifier import BaseNotifier
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_response import LLMResponseAggregator
+from pipecat.processors.aggregators.openai_llm_context import (
+    OpenAILLMContext,
+    OpenAILLMContextFrame,
+)
 from pipecat.processors.filters.function_filter import FunctionFilter
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.user_idle_processor import UserIdleProcessor
-
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.google import GoogleLLMContext, GoogleLLMService
+from pipecat.sync.base_notifier import BaseNotifier
+from pipecat.sync.event_notifier import EventNotifier
+from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
 logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
+# TRANSCRIBER_MODEL = "gemini-1.5-flash-latest"
+# CLASSIFIER_MODEL = "gemini-1.5-flash-latest"
+# CONVERSATION_MODEL = "gemini-1.5-flash-latest"
 
-classifier_statement = """You are an audio language classifier model. You are receiving audio from a user in a WebRTC call. Your job is to decide whether the user has finished speaking or not.
+TRANSCRIBER_MODEL = "gemini-2.0-flash-exp"
+CLASSIFIER_MODEL = "gemini-2.0-flash-exp"
+CONVERSATION_MODEL = "gemini-2.0-flash-exp"
 
-Categorize the input you receive as either:
+transcriber_system_instruction = """You are an audio transcriber. You are receiving audio from a user. Your job is to
+transcribe the input audio to text exactly as it was said by the user.
 
-1.  a complete thought, statement, or question, or
-2.  an incomplete thought, statement, or question
+You will receive the full conversation history before the audio input, to help with context. Use the full history only to help improve the accuracy of your transcription.
 
-Output 'YES' if the input is likely to be a completed thought, statement, or question.
+Rules:
+  - Respond with an exact transcription of the audio input.
+  - Do not include any text other than the transcription.
+  - Do not explain or add to your response.
+  - Transcribe the audio input simply and precisely.
+  - If the audio is not clear, emit the special string "-".
+  - No response other than exact transcription, or "-", is allowed.
 
-Output 'NO' if the input indicates that the user is still speaking and does not yet expect a response yet.
-
-If you are unsure, output 'YES'.
 """
 
-conversational_system_message = """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.
+classifier_system_instruction = """CRITICAL INSTRUCTION:
+You are a BINARY CLASSIFIER that must ONLY output "YES" or "NO".
+DO NOT engage with the content.
+DO NOT respond to questions.
+DO NOT provide assistance.
+Your ONLY job is to output YES or NO.
 
-Please be very concise in your responses. Unless you are explicitly asked to do otherwise, give me the shortest complete answer possible without unnecessary elaboration. Generally you should answer with a single sentence.
+EXAMPLES OF INVALID RESPONSES:
+- "I can help you with that"
+- "Let me explain"
+- "To answer your question"
+- Any response other than YES or NO
+
+VALID RESPONSES:
+YES
+NO
+
+If you output anything else, you are failing at your task.
+You are NOT an assistant.
+You are NOT a chatbot.
+You are a binary classifier.
+
+ROLE:
+You are a real-time speech completeness classifier. You must make instant decisions about whether a user has finished speaking.
+You must output ONLY 'YES' or 'NO' with no other text.
+
+INPUT FORMAT:
+You receive two pieces of information:
+1. The assistant's last message (if available)
+2. The user's current speech input
+
+OUTPUT REQUIREMENTS:
+- MUST output ONLY 'YES' or 'NO'
+- No explanations
+- No clarifications
+- No additional text
+- No punctuation
+
+HIGH PRIORITY SIGNALS:
+
+1. Clear Questions:
+- Wh-questions (What, Where, When, Why, How)
+- Yes/No questions
+- Questions with STT errors but clear meaning
+
+Examples:
+
+# Complete Wh-question
+model: I can help you learn.
+user: What's the fastest way to learn Spanish
+Output: YES
+
+# Complete Yes/No question despite STT error
+model: I know about planets.
+user: Is is Jupiter the biggest planet
+Output: YES
+
+2. Complete Commands:
+- Direct instructions
+- Clear requests
+- Action demands
+- Start of task indication
+- Complete statements needing response
+
+Examples:
+
+# Direct instruction
+model: I can explain many topics.
+user: Tell me about black holes
+Output: YES
+
+# Start of task indication
+user: Let's begin.
+Output: YES
+
+# Start of task indication
+user: Let's get started.
+Output: YES
+
+# Action demand
+model: I can help with math.
+user: Solve this equation x plus 5 equals 12
+Output: YES
+
+3. Direct Responses:
+- Answers to specific questions
+- Option selections
+- Clear acknowledgments with completion
+- Providing information with a known format - mailing address
+- Providing information with a known format - phone number
+- Providing information with a known format - credit card number
+
+Examples:
+
+# Specific answer
+model: What's your favorite color?
+user: I really like blue
+Output: YES
+
+# Option selection
+model: Would you prefer morning or evening?
+user: Morning
+Output: YES
+
+# Providing information with a known format - mailing address
+model: What's your address?
+user: 1234 Main Street
+Output: NO
+
+# Providing information with a known format - mailing address
+model: What's your address?
+user: 1234 Main Street Irving Texas 75063
+Output: Yes
+
+# Providing information with a known format - phone number
+model: What's your phone number?
+user: 41086753
+Output: NO
+
+# Providing information with a known format - phone number
+model: What's your phone number?
+user: 4108675309
+Output: Yes
+
+# Providing information with a known format - phone number
+model: What's your phone number?
+user: 220
+Output: No
+
+# Providing information with a known format - credit card number
+model: What's your credit card number?
+user: 5556
+Output: NO
+
+# Providing information with a known format - phone number
+model: What's your credit card number?
+user: 5556710454680800
+Output: Yes
+
+model: What's your credit card number?
+user: 414067
+Output: NO
+
+
+MEDIUM PRIORITY SIGNALS:
+
+1. Speech Pattern Completions:
+- Self-corrections reaching completion
+- False starts with clear ending
+- Topic changes with complete thought
+- Mid-sentence completions
+
+Examples:
+
+# Self-correction reaching completion
+model: What would you like to know?
+user: Tell me about... no wait, explain how rainbows form
+Output: YES
+
+# Topic change with complete thought
+model: The weather is nice today.
+user: Actually can you tell me who invented the telephone
+Output: YES
+
+# Mid-sentence completion
+model: Hello I'm ready.
+user: What's the capital of? France
+Output: YES
+
+2. Context-Dependent Brief Responses:
+- Acknowledgments (okay, sure, alright)
+- Agreements (yes, yeah)
+- Disagreements (no, nah)
+- Confirmations (correct, exactly)
+
+Examples:
+
+# Acknowledgment
+model: Should we talk about history?
+user: Sure
+Output: YES
+
+# Disagreement with completion
+model: Is that what you meant?
+user: No not really
+Output: YES
+
+LOW PRIORITY SIGNALS:
+
+1. STT Artifacts (Consider but don't over-weight):
+- Repeated words
+- Unusual punctuation
+- Capitalization errors
+- Word insertions/deletions
+
+Examples:
+
+# Word repetition but complete
+model: I can help with that.
+user: What what is the time right now
+Output: YES
+
+# Missing punctuation but complete
+model: I can explain that.
+user: Please tell me how computers work
+Output: YES
+
+2. Speech Features:
+- Filler words (um, uh, like)
+- Thinking pauses
+- Word repetitions
+- Brief hesitations
+
+Examples:
+
+# Filler words but complete
+model: What would you like to know?
+user: Um uh how do airplanes fly
+Output: YES
+
+# Thinking pause but incomplete
+model: I can explain anything.
+user: Well um I want to know about the
+Output: NO
+
+DECISION RULES:
+
+1. Return YES if:
+- ANY high priority signal shows clear completion
+- Medium priority signals combine to show completion
+- Meaning is clear despite low priority artifacts
+
+2. Return NO if:
+- No high priority signals present
+- Thought clearly trails off
+- Multiple incomplete indicators
+- User appears mid-formulation
+
+3. When uncertain:
+- If you can understand the intent → YES
+- If meaning is unclear → NO
+- Always make a binary decision
+- Never request clarification
+
+Examples:
+
+# Incomplete despite corrections
+model: What would you like to know about?
+user: Can you tell me about
+Output: NO
+
+# Complete despite multiple artifacts
+model: I can help you learn.
+user: How do you I mean what's the best way to learn programming
+Output: YES
+
+# Trailing off incomplete
+model: I can explain anything.
+user: I was wondering if you could tell me why
+Output: NO
+"""
+
+conversation_system_instruction = """You are a helpful assistant participating in a voice converation.
+
+Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.
+
+If you know that a number string is a phone number from the context of the conversation, write it as a phone number. For example 210-333-4567.
+
+If you know that a number string is a credit card number, write it as a credit card number. For example 4111-1111-1111-1111.
+
+Please be very concise in your responses. Unless you are explicitly asked to do otherwise, give me shortest complete answer possible without unnecessary elaboration. Generally you should answer with a single sentence.
 """
 
 
-class StatementJudgeAudioContextAccumulator(FrameProcessor):
-    def __init__(self, *, notifier: BaseNotifier, **kwargs):
+class AudioAccumulator(FrameProcessor):
+    """Buffers user audio until the user stops speaking.
+
+    Always pushes a fresh context with a single audio message.
+    """
+
+    def __init__(self, **kwargs):
         super().__init__(**kwargs)
-        self._notifier = notifier
-        self._audio_frames = []
         self._audio_frames = []
         self._start_secs = 0.2  # this should match VAD start_secs (hardcoding for now)
-        self._user_speaking = False
+        self._max_buffer_size_secs = 30
+        self._user_speaking_vad_state = False
+        self._user_speaking_utterance_state = False
 
     async def reset(self):
         self._audio_frames = []
-        self._user_speaking = False
+        self._user_speaking_vad_state = False
+        self._user_speaking_utterance_state = False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         # ignore context frame
         if isinstance(frame, OpenAILLMContextFrame):
             return
@@ -99,22 +385,33 @@ class StatementJudgeAudioContextAccumulator(FrameProcessor):
             # but let's leave that as an exercise to the reader. :-)
             return
         if isinstance(frame, UserStartedSpeakingFrame):
-            self._user_speaking = True
+            self._user_speaking_vad_state = True
+            self._user_speaking_utterance_state = True
+
         elif isinstance(frame, UserStoppedSpeakingFrame):
+            data = b"".join(frame.audio for frame in self._audio_frames)
+            logger.debug(
+                f"Processing audio buffer seconds: ({len(self._audio_frames)}) ({len(data)}) {len(data) / 2 / 16000}"
+            )
             self._user_speaking = False
             context = GoogleLLMContext()
-            context.set_messages([{"role": "system", "content": classifier_statement}])
-            context.add_audio_frames_message(audio_frames=self._audio_frames)
+            context.add_audio_frames_message(text="Audio follows", audio_frames=self._audio_frames)
             await self.push_frame(OpenAILLMContextFrame(context=context))
         elif isinstance(frame, InputAudioRawFrame):
-            if self._user_speaking:
-                self._audio_frames.append(frame)
+            # Append the audio frame to our buffer. Treat the buffer as a ring buffer, dropping the oldest
+            # frames as necessary.
+            # Use a small buffer size when an utterance is not in progress. Just big enough to backfill the start_secs.
+            # Use a larger buffer size when an utterance is in progress.
+            # Assume all audio frames have the same duration.
+            self._audio_frames.append(frame)
+            frame_duration = len(frame.audio) / 2 * frame.num_channels / frame.sample_rate
+            buffer_duration = frame_duration * len(self._audio_frames)
+            #  logger.debug(f"!!! Frame duration: {frame_duration}")
+            if self._user_speaking_utterance_state:
+                while buffer_duration > self._max_buffer_size_secs:
+                    self._audio_frames.pop(0)
+                    buffer_duration -= frame_duration
             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
@@ -123,30 +420,143 @@ class StatementJudgeAudioContextAccumulator(FrameProcessor):
 
 
 class CompletenessCheck(FrameProcessor):
-    def __init__(
-        self, notifier: BaseNotifier, audio_accumulator: StatementJudgeAudioContextAccumulator
-    ):
+    """Checks the result of the classifier LLM to determine if the user has finished speaking.
+
+    Triggers the notifier if the user has finished speaking. Also triggers the notifier if an
+    idle timeout is reached.
+    """
+
+    wait_time = 5.0
+
+    def __init__(self, notifier: BaseNotifier, audio_accumulator: AudioAccumulator, **kwargs):
         super().__init__()
         self._notifier = notifier
         self._audio_accumulator = audio_accumulator
+        self._idle_task = None
+        self._wakeup_time = 0
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
-        if isinstance(frame, TextFrame) and frame.text.startswith("YES"):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserStartedSpeakingFrame):
+            if self._idle_task:
+                self._idle_task.cancel()
+        elif isinstance(frame, TextFrame) and frame.text.startswith("YES"):
             logger.debug("Completeness check YES")
+            if self._idle_task:
+                self._idle_task.cancel()
             await self.push_frame(UserStoppedSpeakingFrame())
             await self._audio_accumulator.reset()
             await self._notifier.notify()
         elif isinstance(frame, TextFrame):
             if frame.text.strip():
                 logger.debug(f"Completeness check NO - '{frame.text}'")
+                # start timer to wake up if necessary
+                if self._wakeup_time:
+                    self._wakeup_time = time.time() + self.wait_time
+                else:
+                    # logger.debug("!!! CompletenessCheck idle wait START")
+                    self._wakeup_time = time.time() + self.wait_time
+                    self._idle_task = self.get_event_loop().create_task(self._idle_task_handler())
+
+    async def _idle_task_handler(self):
+        try:
+            while time.time() < self._wakeup_time:
+                await asyncio.sleep(0.01)
+            # logger.debug(f"!!! CompletenessCheck idle wait OVER")
+            await self._audio_accumulator.reset()
+            await self._notifier.notify()
+        except asyncio.CancelledError:
+            # logger.debug(f"!!! CompletenessCheck idle wait CANCEL")
+            pass
+        except Exception as e:
+            logger.error(f"CompletenessCheck idle wait error: {e}")
+            raise e
+        finally:
+            # logger.debug(f"!!! CompletenessCheck idle wait FINALLY")
+            self._wakeup_time = 0
+            self._idle_task = None
+
+
+class UserAggregatorBuffer(LLMResponseAggregator):
+    """Buffers the output of the transcription LLM. Used by the bot output gate."""
+
+    def __init__(self, **kwargs):
+        super().__init__(
+            messages=None,
+            role=None,
+            start_frame=LLMFullResponseStartFrame,
+            end_frame=LLMFullResponseEndFrame,
+            accumulator_frame=TextFrame,
+            handle_interruptions=True,
+            expect_stripped_words=False,
+        )
+        self._transcription = ""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+        # parent method pushes frames
+        if isinstance(frame, UserStartedSpeakingFrame):
+            self._transcription = ""
+
+    async def _push_aggregation(self):
+        if self._aggregation:
+            self._transcription = self._aggregation
+            self._aggregation = ""
+
+            logger.debug(f"[Transcription] {self._transcription}")
+
+    async def wait_for_transcription(self):
+        while not self._transcription:
+            await asyncio.sleep(0.01)
+        tx = self._transcription
+        self._transcription = ""
+        return tx
+
+
+class ConversationAudioContextAssembler(FrameProcessor):
+    """Takes the single-message context generated by the AudioAccumulator and adds it to the conversation LLM's context."""
+
+    def __init__(self, context: OpenAILLMContext, **kwargs):
+        super().__init__(**kwargs)
+        self._context = context
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        # We must not block system frames.
+        if isinstance(frame, SystemFrame):
+            await self.push_frame(frame, direction)
+            return
+
+        if isinstance(frame, OpenAILLMContextFrame):
+            GoogleLLMContext.upgrade_to_google(self._context)
+            last_message = frame.context.messages[-1]
+            self._context._messages.append(last_message)
+            await self.push_frame(OpenAILLMContextFrame(context=self._context))
 
 
 class OutputGate(FrameProcessor):
-    def __init__(self, notifier: BaseNotifier, **kwargs):
+    """Buffers output frames until the notifier is triggered.
+
+    When the notifier fires, waits until a transcription is ready, then:
+      1. Replaces the last user audio message with the transcription.
+      2. Flushes the frames buffer.
+    """
+
+    def __init__(
+        self,
+        notifier: BaseNotifier,
+        context: OpenAILLMContext,
+        user_transcription_buffer: "UserAggregatorBuffer",
+        **kwargs,
+    ):
         super().__init__(**kwargs)
         self._gate_open = False
         self._frames_buffer = []
         self._notifier = notifier
+        self._context = context
+        self._transcription_buffer = user_transcription_buffer
 
     def close_gate(self):
         self._gate_open = False
@@ -155,6 +565,8 @@ class OutputGate(FrameProcessor):
         self._gate_open = True
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
         # We must not block system frames.
         if isinstance(frame, SystemFrame):
             if isinstance(frame, StartFrame):
@@ -172,6 +584,13 @@ class OutputGate(FrameProcessor):
             await self.push_frame(frame, direction)
             return
 
+        if isinstance(frame, LLMFullResponseStartFrame):
+            # Remove the audio message from the context. We will never need it again.
+            # If the completeness check fails, a new audio message will be appended to the context.
+            # If the completeness check succeeds, our notifier will fire and we will append the
+            # transcription to the context.
+            self._context._messages.pop()
+
         if self._gate_open:
             await self.push_frame(frame, direction)
             return
@@ -190,12 +609,22 @@ class OutputGate(FrameProcessor):
         while True:
             try:
                 await self._notifier.wait()
+
+                transcription = await self._transcription_buffer.wait_for_transcription() or "-"
+                self._context._messages.append(
+                    glm.Content(role="user", parts=[glm.Part(text=transcription)])
+                )
+
                 self.open_gate()
                 for frame, direction in self._frames_buffer:
                     await self.push_frame(frame, direction)
                 self._frames_buffer = []
             except asyncio.CancelledError:
                 break
+            except Exception as e:
+                logger.error(f"OutputGate error: {e}")
+                raise e
+                break
 
 
 async def main():
@@ -211,64 +640,63 @@ async def main():
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 vad_audio_passthrough=True,
+                audio_in_sample_rate=16000,
             ),
         )
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
 
-        # This is the LLM that will be used to detect if the user has finished a
-        # statement. This doesn't really need to be an LLM, we could use NLP
-        # libraries for that, but we have the machinery to use an LLM, so we might as well!
-        statement_llm = GoogleLLMService(
-            model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY")
+        # This is the LLM that will transcribe user speech.
+        tx_llm = GoogleLLMService(
+            name="Transcriber",
+            model=TRANSCRIBER_MODEL,
+            api_key=os.getenv("GOOGLE_API_KEY"),
+            temperature=0.0,
+            system_instruction=transcriber_system_instruction,
         )
 
-        # This is the regular LLM.
-        llm = GoogleLLMService(model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY"))
+        # This is the LLM that will classify user speech as complete or incomplete.
+        classifier_llm = GoogleLLMService(
+            name="Classifier",
+            model=CLASSIFIER_MODEL,
+            api_key=os.getenv("GOOGLE_API_KEY"),
+            temperature=0.0,
+            system_instruction=classifier_system_instruction,
+        )
 
-        messages = [
-            {
-                "role": "system",
-                "content": conversational_system_message,
-            },
-        ]
+        # This is the regular LLM that responds conversationally.
+        conversation_llm = GoogleLLMService(
+            name="Conversation",
+            model=CONVERSATION_MODEL,
+            api_key=os.getenv("GOOGLE_API_KEY"),
+            system_instruction=conversation_system_instruction,
+        )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+        context = OpenAILLMContext()
+        context_aggregator = conversation_llm.create_context_aggregator(context)
 
-        # We have instructed the LLM to return 'YES' if it thinks the user
-        # completed a sentence. So, if it's 'YES' we will return true in this
+        # We have instructed the LLM to return 'True' if it thinks the user
+        # completed a sentence. So, if it's 'True' we will return true in this
         # predicate which will wake up the notifier.
         async def wake_check_filter(frame):
-            return frame.text == "YES"
+            return frame.text == "True"
 
         # This is a notifier that we use to synchronize the two LLMs.
         notifier = EventNotifier()
 
         # This turns the LLM context into an inference request to classify the user's speech
         # as complete or incomplete.
-        statement_judge_context_filter = StatementJudgeAudioContextAccumulator(notifier=notifier)
+        # statement_judge_context_filter = StatementJudgeAudioContextAccumulator(notifier=notifier)
 
+        audio_accumulater = AudioAccumulator()
         # This sends a UserStoppedSpeakingFrame and triggers the notifier event
         completeness_check = CompletenessCheck(
-            notifier=notifier, audio_accumulator=statement_judge_context_filter
+            notifier=notifier, audio_accumulator=audio_accumulater
         )
 
-        # # Notify if the user hasn't said anything.
-        async def user_idle_notifier(frame):
-            await notifier.notify()
-
-        # Sometimes the LLM will fail detecting if a user has completed a
-        # sentence, this will wake up the notifier if that happens.
-        user_idle = UserIdleProcessor(callback=user_idle_notifier, timeout=5.0)
-
-        bot_output_gate = OutputGate(notifier=notifier)
-
         async def block_user_stopped_speaking(frame):
             return not isinstance(frame, UserStoppedSpeakingFrame)
 
@@ -280,9 +708,18 @@ async def main():
                 or isinstance(frame, StopInterruptionFrame)
             )
 
+        conversation_audio_context_assembler = ConversationAudioContextAssembler(context=context)
+
+        user_aggregator_buffer = UserAggregatorBuffer()
+
+        bot_output_gate = OutputGate(
+            notifier=notifier, context=context, user_transcription_buffer=user_aggregator_buffer
+        )
+
         pipeline = Pipeline(
             [
                 transport.input(),
+                audio_accumulater,
                 ParallelPipeline(
                     [
                         # Pass everything except UserStoppedSpeaking to the elements after
@@ -290,24 +727,28 @@ async def main():
                         FunctionFilter(filter=block_user_stopped_speaking),
                     ],
                     [
-                        statement_judge_context_filter,
-                        statement_llm,
-                        completeness_check,
+                        ParallelPipeline(
+                            [
+                                classifier_llm,
+                                completeness_check,
+                            ],
+                            [
+                                tx_llm,
+                                user_aggregator_buffer,
+                            ],
+                        )
                     ],
                     [
-                        stt,
-                        context_aggregator.user(),
-                        # Block everything except OpenAILLMContextFrame and LLMMessagesFrame
-                        FunctionFilter(filter=pass_only_llm_trigger_frames),
-                        llm,
-                        bot_output_gate,  # Buffer all llm/tts output until notified.
+                        conversation_audio_context_assembler,
+                        conversation_llm,
+                        bot_output_gate,  # buffer output until notified, then flush frames and update context
+                        # TempPrinter(),
                     ],
                 ),
                 tts,
-                user_idle,
                 transport.output(),
                 context_aggregator.assistant(),
-            ]
+            ],
         )
 
         task = PipelineTask(