tiny bit more cleanup

services(elevenlabs): add elevenlabs package and use streaming

.dockerignore

@@ -0,0 +1,30 @@
+# flyctl launch added from .gitignore
+**/.vscode
+**/env
+**/__pycache__
+**/*~
+**/venv
+#*#
+
+# Distribution / packaging
+**/.Python
+**/build
+**/develop-eggs
+**/dist
+**/downloads
+**/eggs
+**/.eggs
+**/lib
+**/lib64
+**/parts
+**/sdist
+**/var
+**/wheels
+**/share/python-wheels
+**/*.egg-info
+**/.installed.cfg
+**/*.egg
+**/MANIFEST
+**/.DS_Store
+**/.env
+fly.toml

.github/workflows/build.yaml

@@ -0,0 +1,44 @@
+name: build
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    name: "Build and Install"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Install project and other Python dependencies
+        run: |
+          source .venv/bin/activate
+          pip install --editable .

.github/workflows/lint.yaml

@@ -0,0 +1,44 @@
+name: lint
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-lint-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  autopep8:
+    name: "Formatting lints"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install development Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: autopep8
+        id: autopep8
+        run: |
+          source .venv/bin/activate
+          autopep8 --max-line-length 100 --exit-code -r -d --exclude "*_pb2.py" -a -a src/
+      - name: Fail if autopep8 requires changes
+        if: steps.autopep8.outputs.exit-code == 2
+        run: exit 1

.github/workflows/publish.yaml

@@ -0,0 +1,84 @@
+name: publish
+
+on:
+  workflow_dispatch:
+    inputs:
+      gitref:
+        type: string
+        description: "what git ref to build"
+        required: true
+
+jobs:
+  build:
+    name: "Build and upload wheels"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.gitref }}
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+
+  publish-to-pypi:
+    name: "Publish to PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+
+  publish-to-test-pypi:
+    name: "Publish to Test PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: testpypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/

.github/workflows/publish_test.yaml

@@ -0,0 +1,58 @@
+name: publish-test
+
+on: workflow_dispatch
+
+jobs:
+  build:
+    name: "Build and upload wheels"
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          fetch-tags: true
+          fetch-depth: 100
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Build project
+        run: |
+          source .venv/bin/activate
+          python -m build
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+
+  publish-to-test-pypi:
+    name: "Publish to Test PyPI"
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    environment:
+      name: testpypi
+      url: https://pypi.org/p/pipecat-ai
+    permissions:
+      id-token: write
+    steps:
+      - name: Download wheels
+        uses: actions/download-artifact@v4
+        with:
+          name: wheels
+          path: ./dist
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          verbose: true
+          print-hash: true
+          repository-url: https://test.pypi.org/legacy/

.github/workflows/tests.yaml

@@ -0,0 +1,42 @@
+name: test
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+    paths-ignore:
+      - "docs/**"
+
+concurrency:
+  group: build-test-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: "Unit and Integration Tests"
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        id: setup_python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install system packages
+        run: sudo apt-get install -y portaudio19-dev
+      - name: Setup virtual environment
+        run: |
+          python -m venv .venv
+      - name: Install basic Python dependencies
+        run: |
+          source .venv/bin/activate
+          python -m pip install --upgrade pip
+          pip install -r dev-requirements.txt
+      - name: Test with pytest
+        run: |
+          source .venv/bin/activate
+          pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests

.gitignore

@@ -3,6 +3,7 @@ env/
 __pycache__/
 *~
 venv
+.venv
 #*#
 
 # Distribution / packaging
@@ -26,3 +27,4 @@ share/python-wheels/
 MANIFEST
 .DS_Store
 .env
+fly.toml

CHANGELOG.md

@@ -0,0 +1,941 @@
+# Changelog
+
+All notable changes to **pipecat** will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+### Added
+
+- Interruptions support has been added to `TwilioFrameSerializer` when using
+  `FastAPIWebsocketTransport`.
+
+- Added new `LmntTTSService` text-to-speech service.
+  (see https://www.lmnt.com/)
+
+- Added `TTSModelUpdateFrame`, `TTSLanguageUpdateFrame`, `STTModelUpdateFrame`,
+  and `STTLanguageUpdateFrame` frames to allow you to switch models, language
+  and voices in TTS and STT services.
+
+- Added new `transcriptions.Language` enum.
+
+### Changed
+
+- `DailyTransport.on_joined` event now returns the full session data instead of
+  just the participant.
+
+- `CartesiaTTSService` is now a subclass of `TTSService`.
+
+- `DeepgramSTTService` is now a subclass of `STTService`.
+
+- `WhisperSTTService` is now a subclass of `SegmentedSTTService`. A
+  `SegmentedSTTService` is a `STTService` where the provided audio is given in a
+  big chunk (i.e. from when the user starts speaking until the user stops
+  speaking) instead of a continous stream.
+
+### Fixed
+
+- `StartFrame` should be the first frame every processor receives to avoid
+  situations where things are not initialized (because initialization happens on
+  `StartFrame`) and other frames come in resulting in undesired behavior.
+
+### Performance
+
+- `obj_id()` and `obj_count()` now use `itertools.count` avoiding the need of
+  `threading.Lock`.
+
+## [0.0.41] - 2024-08-22
+
+### Added
+
+- Added `LivekitFrameSerializer` audio frame serializer.
+
+### Fixed
+
+- Fix `FastAPIWebsocketOutputTransport` variable name clash with subclass.
+
+- Fix an `AnthropicLLMService` issue with empty arguments in function calling.
+
+### Other
+
+- Fixed `studypal` example errors.
+
+## [0.0.40] - 2024-08-20
+
+### Added
+
+- VAD parameters can now be dynamicallt updated using the
+  `VADParamsUpdateFrame`.
+
+- `ErrorFrame` has now a `fatal` field to indicate the bot should exit if a
+  fatal error is pushed upstream (false by default). A new `FatalErrorFrame`
+  that sets this flag to true has been added.
+
+- `AnthropicLLMService` now supports function calling and initial support for
+  prompt caching.
+  (see https://www.anthropic.com/news/prompt-caching)
+
+- `ElevenLabsTTSService` can now specify ElevenLabs input parameters such as
+  `output_format`.
+
+- `TwilioFrameSerializer` can now specify Twilio's and Pipecat's desired sample
+  rates to use.
+
+- Added new `on_participant_updated` event to `DailyTransport`.
+
+- Added `DailyRESTHelper.delete_room_by_name()` and
+  `DailyRESTHelper.delete_room_by_url()`.
+
+- Added LLM and TTS usage metrics. Those are enabled when
+  `PipelineParams.enable_usage_metrics` is True.
+
+- `AudioRawFrame`s are now pushed downstream from the base output
+  transport. This allows capturing the exact words the bot says by adding an STT
+  service at the end of the pipeline.
+
+- Added new `GStreamerPipelineSource`. This processor can generate image or
+  audio frames from a GStreamer pipeline (e.g. reading an MP4 file, and RTP
+  stream or anything supported by GStreamer).
+
+- Added `TransportParams.audio_out_is_live`. This flag is False by default and
+  it is useful to indicate we should not synchronize audio with sporadic images.
+
+- Added new `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame` control
+  frames. These frames are pushed upstream and they should wrap
+  `BotSpeakingFrame`.
+
+- Transports now allow you to register event handlers without decorators.
+
+### Changed
+
+- Support RTVI message protocol 0.1. This includes new messages, support for
+  messages responses, support for actions, configuration, webhooks and a bunch
+  of new cool stuff.
+  (see https://docs.rtvi.ai/)
+
+- `SileroVAD` dependency is now imported via pip's `silero-vad` package.
+
+- `ElevenLabsTTSService` now uses `eleven_turbo_v2_5` model by default.
+
+- `BotSpeakingFrame` is now a control frame.
+
+- `StartFrame` is now a control frame similar to `EndFrame`.
+
+- `DeepgramTTSService` now is more customizable. You can adjust the encoding and
+  sample rate.
+
+### Fixed
+
+- `TTSStartFrame` and `TTSStopFrame` are now sent when TTS really starts and
+  stops. This allows for knowing when the bot starts and stops speaking even
+  with asynchronous services (like Cartesia).
+
+- Fixed `AzureSTTService` transcription frame timestamps.
+
+- Fixed an issue with `DailyRESTHelper.create_room()` expirations which would
+  cause this function to stop working after the initial expiration elapsed.
+
+- Improved `EndFrame` and `CancelFrame` handling. `EndFrame` should end things
+  gracefully while a `CancelFrame` should cancel all running tasks as soon as
+  possible.
+
+- Fixed an issue in `AIService` that would cause a yielded `None` value to be
+  processed.
+
+- RTVI's `bot-ready` message is now sent when the RTVI pipeline is ready and
+  a first participant joins.
+
+- Fixed a `BaseInputTransport` issue that was causing incoming system frames to
+  be queued instead of being pushed immediately.
+
+- Fixed a `BaseInputTransport` issue that was causing start/stop interruptions
+  incoming frames to not cancel tasks and be processed properly.
+
+### Other
+
+- Added `studypal` example (from to the Cartesia folks!).
+
+- Most examples now use Cartesia.
+
+- Added examples `foundational/19a-tools-anthropic.py`,
+  `foundational/19b-tools-video-anthropic.py` and
+  `foundational/19a-tools-togetherai.py`.
+
+- Added examples `foundational/18-gstreamer-filesrc.py` and
+  `foundational/18a-gstreamer-videotestsrc.py` that show how to use
+  `GStreamerPipelineSource`
+
+- Remove `requests` library usage.
+
+- Cleanup examples and use `DailyRESTHelper`.
+
+## [0.0.39] - 2024-07-23
+
+### Fixed
+
+- Fixed a regression introduced in 0.0.38 that would cause Daily transcription
+  to stop the Pipeline.
+
+## [0.0.38] - 2024-07-23
+
+### Added
+
+- Added `force_reload`, `skip_validation` and `trust_repo` to `SileroVAD` and
+  `SileroVADAnalyzer`. This allows caching and various GitHub repo validations.
+
+- Added `send_initial_empty_metrics` flag to `PipelineParams` to request for
+  initial empty metrics (zero values). True by default.
+
+### Fixed
+
+- Fixed initial metrics format. It was using the wrong keys name/time instead of
+  processor/value.
+
+- STT services should be using ISO 8601 time format for transcription frames.
+
+- Fixed an issue that would cause Daily transport to show a stop transcription
+  error when actually none occurred.
+
+## [0.0.37] - 2024-07-22
+
+### Added
+
+- Added `RTVIProcessor` which implements the RTVI-AI standard.
+  See https://github.com/rtvi-ai
+
+- Added `BotInterruptionFrame` which allows interrupting the bot while talking.
+
+- Added `LLMMessagesAppendFrame` which allows appending messages to the current
+  LLM context.
+
+- Added `LLMMessagesUpdateFrame` which allows changing the LLM context for the
+  one provided in this new frame.
+
+- Added `LLMModelUpdateFrame` which allows updating the LLM model.
+
+- Added `TTSSpeakFrame` which causes the bot say some text. This text will not
+  be part of the LLM context.
+
+- Added `TTSVoiceUpdateFrame` which allows updating the TTS voice.
+
+### Removed
+
+- We remove the `LLMResponseStartFrame` and `LLMResponseEndFrame` frames. These
+  were added in the past to properly handle interruptions for the
+  `LLMAssistantContextAggregator`. But the `LLMContextAggregator` is now based
+  on `LLMResponseAggregator` which handles interruptions properly by just
+  processing the `StartInterruptionFrame`, so there's no need for these extra
+  frames any more.
+
+### Fixed
+
+- Fixed an issue with `StatelessTextTransformer` where it was pushing a string
+  instead of a `TextFrame`.
+
+- `TTSService` end of sentence detection has been improved. It now works with
+  acronyms, numbers, hours and others.
+
+- Fixed an issue in `TTSService` that would not properly flush the current
+  aggregated sentence if an `LLMFullResponseEndFrame` was found.
+
+### Performance
+
+- `CartesiaTTSService` now uses websockets which improves speed. It also
+  leverages the new Cartesia contexts which maintains generated audio prosody
+  when multiple inputs are sent, therefore improving audio quality a lot.
+
+## [0.0.36] - 2024-07-02
+
+### Added
+
+- Added `GladiaSTTService`.
+  See https://docs.gladia.io/chapters/speech-to-text-api/pages/live-speech-recognition
+
+- Added `XTTSService`. This is a local Text-To-Speech service.
+  See https://github.com/coqui-ai/TTS
+
+- Added `UserIdleProcessor`. This processor can be used to wait for any
+  interaction with the user. If the user doesn't say anything within a given
+  timeout a provided callback is called.
+
+- Added `IdleFrameProcessor`. This processor can be used to wait for frames
+  within a given timeout. If no frame is received within the timeout a provided
+  callback is called.
+
+- Added new frame `BotSpeakingFrame`. This frame will be continuously pushed
+  upstream while the bot is talking.
+
+- It is now possible to specify a Silero VAD version when using `SileroVADAnalyzer`
+  or `SileroVAD`.
+
+- Added `AysncFrameProcessor` and `AsyncAIService`.  Some services like
+  `DeepgramSTTService` need to process things asynchronously. For example, audio
+  is sent to Deepgram but transcriptions are not returned immediately. In these
+  cases we still require all frames (except system frames) to be pushed
+  downstream from a single task. That's what `AsyncFrameProcessor` is for. It
+  creates a task and all frames should be pushed from that task. So, whenever a
+  new Deepgram transcription is ready that transcription will also be pushed
+  from this internal task.
+
+- The `MetricsFrame` now includes processing metrics if metrics are enabled. The
+  processing metrics indicate the time a processor needs to generate all its
+  output. Note that not all processors generate these kind of metrics.
+
+### Changed
+
+- `WhisperSTTService` model can now also be a string.
+
+- Added missing * keyword separators in services.
+
+### Fixed
+
+- `WebsocketServerTransport` doesn't try to send frames anymore if serializers
+  returns `None`.
+
+- Fixed an issue where exceptions that occurred inside frame processors were
+  being swallowed and not displayed.
+
+- Fixed an issue in `FastAPIWebsocketTransport` where it would still try to send
+  data to the websocket after being closed.
+
+### Other
+
+- Added Fly.io deployment example in `examples/deployment/flyio-example`.
+
+- Added new `17-detect-user-idle.py` example that shows how to use the new
+  `UserIdleProcessor`.
+
+## [0.0.35] - 2024-06-28
+
+### Changed
+
+- `FastAPIWebsocketParams` now require a serializer.
+
+- `TwilioFrameSerializer` now requires a `streamSid`.
+
+### Fixed
+
+- Silero VAD number of frames needs to be 512 for 16000 sample rate or 256 for
+  8000 sample rate.
+
+## [0.0.34] - 2024-06-25
+
+### Fixed
+
+- Fixed an issue with asynchronous STT services (Deepgram and Azure) that could
+  interruptions to ignore transcriptions.
+
+- Fixed an issue introduced in 0.0.33 that would cause the LLM to generate
+  shorter output.
+
+## [0.0.33] - 2024-06-25
+
+### Changed
+
+- Upgraded to Cartesia's new Python library 1.0.0. `CartesiaTTSService` now
+  expects a voice ID instead of a voice name (you can get the voice ID from
+  Cartesia's playground). You can also specify the audio `sample_rate` and
+  `encoding` instead of the previous `output_format`.
+
+### Fixed
+
+- Fixed an issue with asynchronous STT services (Deepgram and Azure) that could
+  cause static audio issues and interruptions to not work properly when dealing
+  with multiple LLMs sentences.
+
+- Fixed an issue that could mix new LLM responses with previous ones when
+  handling interruptions.
+
+- Fixed a Daily transport blocking situation that occurred while reading audio
+  frames after a participant left the room. Needs daily-python >= 0.10.1.
+
+## [0.0.32] - 2024-06-22
+
+### Added
+
+- Allow specifying a `DeepgramSTTService` url which allows using on-prem
+  Deepgram.
+
+- Added new `FastAPIWebsocketTransport`. This is a new websocket transport that
+  can be integrated with FastAPI websockets.
+
+- Added new `TwilioFrameSerializer`. This is a new serializer that knows how to
+  serialize and deserialize audio frames from Twilio.
+
+- Added Daily transport event: `on_dialout_answered`.  See
+  https://reference-python.daily.co/api_reference.html#daily.EventHandler
+
+- Added new `AzureSTTService`. This allows you to use Azure Speech-To-Text.
+
+### Performance
+
+- Convert `BaseOutputTransport` and `BaseOutputTransport` to fully use asyncio
+  and remove the use of threads.
+
+### Other
+
+- Added `twilio-chatbot`. This is an example that shows how to integrate Twilio
+  phone numbers with a Pipecat bot.
+
+- Updated `07f-interruptible-azure.py` to use `AzureLLMService`,
+  `AzureSTTService` and `AzureTTSService`.
+
+## [0.0.31] - 2024-06-13
+
+### Performance
+
+- Break long audio frames into 20ms chunks instead of 10ms.
+
+## [0.0.30] - 2024-06-13
+
+### Added
+
+- Added `report_only_initial_ttfb` to `PipelineParams`. This will make it so
+  only the initial TTFB metrics after the user stops talking are reported.
+
+- Added `OpenPipeLLMService`. This service will let you run OpenAI through
+  OpenPipe's SDK.
+
+- Allow specifying frame processors' name through a new `name` constructor
+  argument.
+
+- Added `DeepgramSTTService`. This service has an ongoing websocket
+  connection. To handle this, it subclasses `AIService` instead of
+  `STTService`. The output of this service will be pushed from the same task,
+  except system frames like `StartFrame`, `CancelFrame` or
+  `StartInterruptionFrame`.
+
+### Changed
+
+- `FrameSerializer.deserialize()` can now return `None` in case it is not
+  possible to desearialize the given data.
+
+- `daily_rest.DailyRoomProperties` now allows extra unknown parameters.
+
+### Fixed
+
+- Fixed an issue where `DailyRoomProperties.exp` always had the same old
+  timestamp unless set by the user.
+
+- Fixed a couple of issues with `WebsocketServerTransport`. It needed to use
+  `push_audio_frame()` and also VAD was not working properly.
+
+- Fixed an issue that would cause LLM aggregator to fail with small
+  `VADParams.stop_secs` values.
+
+- Fixed an issue where `BaseOutputTransport` would send longer audio frames
+  preventing interruptions.
+
+### Other
+
+- Added new `07h-interruptible-openpipe.py` example. This example shows how to
+  use OpenPipe to run OpenAI LLMs and get the logs stored in OpenPipe.
+
+- Added new `dialin-chatbot` example. This examples shows how to call the bot
+  using a phone number.
+
+## [0.0.29] - 2024-06-07
+
+### Added
+
+- Added a new `FunctionFilter`. This filter will let you filter frames based on
+  a given function, except system messages which should never be filtered.
+
+- Added `FrameProcessor.can_generate_metrics()` method to indicate if a
+  processor can generate metrics. In the future this might get an extra argument
+  to ask for a specific type of metric.
+
+- Added `BasePipeline`. All pipeline classes should be based on this class. All
+  subclasses should implement a `processors_with_metrics()` method that returns
+  a list of all `FrameProcessor`s in the pipeline that can generate metrics.
+
+- Added `enable_metrics` to `PipelineParams`.
+
+- Added `MetricsFrame`. The `MetricsFrame` will report different metrics in the
+  system. Right now, it can report TTFB (Time To First Byte) values for
+  different services, that is the time spent between the arrival of a `Frame` to
+  the processor/service until the first `DataFrame` is pushed downstream. If
+  metrics are enabled an intial `MetricsFrame` with all the services in the
+  pipeline will be sent.
+
+- Added TTFB metrics and debug logging for TTS services.
+
+### Changed
+
+- Moved `ParallelTask` to `pipecat.pipeline.parallel_task`.
+
+### Fixed
+
+- Fixed PlayHT TTS service to work properly async.
+
+## [0.0.28] - 2024-06-05
+
+### Fixed
+
+- Fixed an issue with `SileroVADAnalyzer` that would cause memory to keep
+  growing indefinitely.
+
+## [0.0.27] - 2024-06-05
+
+### Added
+
+- Added `DailyTransport.participants()` and `DailyTransport.participant_counts()`.
+
+## [0.0.26] - 2024-06-05
+
+### Added
+
+- Added `OpenAITTSService`.
+
+- Allow passing `output_format` and `model_id` to `CartesiaTTSService` to change
+  audio sample format and the model to use.
+
+- Added `DailyRESTHelper` which helps you create Daily rooms and tokens in an
+  easy way.
+
+- `PipelineTask` now has a `has_finished()` method to indicate if the task has
+  completed. If a task is never ran `has_finished()` will return False.
+
+- `PipelineRunner` now supports SIGTERM. If received, the runner will be
+  canceled.
+
+### Fixed
+
+- Fixed an issue where `BaseInputTransport` and `BaseOutputTransport` where
+  stopping push tasks before pushing `EndFrame` frames could cause the bots to
+  get stuck.
+
+- Fixed an error closing local audio transports.
+
+- Fixed an issue with Deepgram TTS that was introduced in the previous release.
+
+- Fixed `AnthropicLLMService` interruptions. If an interruption occurred, a
+  `user` message could be appended after the previous `user` message. Anthropic
+  does not allow that because it requires alternate `user` and `assistant`
+  messages.
+
+### Performance
+
+- The `BaseInputTransport` does not pull audio frames from sub-classes any
+  more. Instead, sub-classes now push audio frames into a queue in the base
+  class. Also, `DailyInputTransport` now pushes audio frames every 20ms instead
+  of 10ms.
+
+- Remove redundant camera input thread from `DailyInputTransport`. This should
+  improve performance a little bit when processing participant videos.
+
+- Load Cartesia voice on startup.
+
+## [0.0.25] - 2024-05-31
+
+### Added
+
+- Added WebsocketServerTransport. This will create a websocket server and will
+  read messages coming from a client. The messages are serialized/deserialized
+  with protobufs. See `examples/websocket-server` for a detailed example.
+
+- Added function calling (LLMService.register_function()). This will allow the
+  LLM to call functions you have registered when needed. For example, if you
+  register a function to get the weather in Los Angeles and ask the LLM about
+  the weather in Los Angeles, the LLM will call your function.
+  See https://platform.openai.com/docs/guides/function-calling
+
+- Added new `LangchainProcessor`.
+
+- Added Cartesia TTS support (https://cartesia.ai/)
+
+### Fixed
+
+- Fixed SileroVAD frame processor.
+
+- Fixed an issue where `camera_out_enabled` would cause the highg CPU usage if
+  no image was provided.
+
+### Performance
+
+- Removed unnecessary audio input tasks.
+
+## [0.0.24] - 2024-05-29
+
+### Added
+
+- Exposed `on_dialin_ready` for Daily transport SIP endpoint handling. This
+  notifies when the Daily room SIP endpoints are ready. This allows integrating
+  with third-party services like Twilio.
+
+- Exposed Daily transport `on_app_message` event.
+
+- Added Daily transport `on_call_state_updated` event.
+
+- Added Daily transport `start_recording()`, `stop_recording` and
+  `stop_dialout`.
+
+### Changed
+
+- Added `PipelineParams`. This replaces the `allow_interruptions` argument in
+  `PipelineTask` and will allow future parameters in the future.
+
+- Fixed Deepgram Aura TTS base_url and added ErrorFrame reporting.
+
+- GoogleLLMService `api_key` argument is now mandatory.
+
+### Fixed
+
+- Daily tranport `dialin-ready` doesn't not block anymore and it now handles
+  timeouts.
+
+- Fixed AzureLLMService.
+
+## [0.0.23] - 2024-05-23
+
+### Fixed
+
+- Fixed an issue handling Daily transport `dialin-ready` event.
+
+## [0.0.22] - 2024-05-23
+
+### Added
+
+- Added Daily transport `start_dialout()` to be able to make phone or SIP calls.
+  See https://reference-python.daily.co/api_reference.html#daily.CallClient.start_dialout
+
+- Added Daily transport support for dial-in use cases.
+
+- Added Daily transport events: `on_dialout_connected`, `on_dialout_stopped`,
+  `on_dialout_error` and `on_dialout_warning`.  See
+  https://reference-python.daily.co/api_reference.html#daily.EventHandler
+
+## [0.0.21] - 2024-05-22
+
+### Added
+
+- Added vision support to Anthropic service.
+
+- Added `WakeCheckFilter` which allows you to pass information downstream only
+  if you say a certain phrase/word.
+
+### Changed
+
+- `Filter` has been renamed to `FrameFilter` and it's now under
+  `processors/filters`.
+
+### Fixed
+
+- Fixed Anthropic service to use new frame types.
+
+- Fixed an issue in `LLMUserResponseAggregator` and `UserResponseAggregator`
+  that would cause frames after a brief pause to not be pushed to the LLM.
+
+- Clear the audio output buffer if we are interrupted.
+
+- Re-add exponential smoothing after volume calculation. This makes sure the
+  volume value being used doesn't fluctuate so much.
+
+## [0.0.20] - 2024-05-22
+
+### Added
+
+- In order to improve interruptions we now compute a loudness level using
+  [pyloudnorm](https://github.com/csteinmetz1/pyloudnorm). The audio coming
+  WebRTC transports (e.g. Daily) have an Automatic Gain Control (AGC) algorithm
+  applied to the signal, however we don't do that on our local PyAudio
+  signals. This means that currently incoming audio from PyAudio is kind of
+  broken. We will fix it in future releases.
+
+### Fixed
+
+- Fixed an issue where `StartInterruptionFrame` would cause
+  `LLMUserResponseAggregator` to push the accumulated text causing the LLM
+  respond in the wrong task. The `StartInterruptionFrame` should not trigger any
+  new LLM response because that would be spoken in a different task.
+
+- Fixed an issue where tasks and threads could be paused because the executor
+  didn't have more tasks available. This was causing issues when cancelling and
+  recreating tasks during interruptions.
+
+## [0.0.19] - 2024-05-20
+
+### Changed
+
+- `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator` internal
+  messages are now exposed through the `messages` property.
+
+### Fixed
+
+- Fixed an issue where `LLMAssistantResponseAggregator` was not accumulating the
+  full response but short sentences instead. If there's an interruption we only
+  accumulate what the bot has spoken until now in a long response as well.
+
+## [0.0.18] - 2024-05-20
+
+### Fixed
+
+- Fixed an issue in `DailyOuputTransport` where transport messages were not
+  being sent.
+
+## [0.0.17] - 2024-05-19
+
+### Added
+
+- Added `google.generativeai` model support, including vision. This new `google`
+  service defaults to using `gemini-1.5-flash-latest`. Example in
+  `examples/foundational/12a-describe-video-gemini-flash.py`.
+
+- Added vision support to `openai` service. Example in
+  `examples/foundational/12a-describe-video-gemini-flash.py`.
+
+- Added initial interruptions support. The assistant contexts (or aggregators)
+  should now be placed after the output transport. This way, only the completed
+  spoken context is added to the assistant context.
+
+- Added `VADParams` so you can control voice confidence level and others.
+
+- `VADAnalyzer` now uses an exponential smoothed volume to improve speech
+  detection. This is useful when voice confidence is high (because there's
+  someone talking near you) but volume is low.
+
+### Fixed
+
+- Fixed an issue where TTSService was not pushing TextFrames downstream.
+
+- Fixed issues with Ctrl-C program termination.
+
+- Fixed an issue that was causing `StopTaskFrame` to actually not exit the
+  `PipelineTask`.
+
+## [0.0.16] - 2024-05-16
+
+### Fixed
+
+- `DailyTransport`: don't publish camera and audio tracks if not enabled.
+
+- Fixed an issue in `BaseInputTransport` that was causing frames pushed
+  downstream not pushed in the right order.
+
+## [0.0.15] - 2024-05-15
+
+### Fixed
+
+- Quick hot fix for receiving `DailyTransportMessage`.
+
+## [0.0.14] - 2024-05-15
+
+### Added
+
+- Added `DailyTransport` event `on_participant_left`.
+
+- Added support for receiving `DailyTransportMessage`.
+
+### Fixed
+
+- Images are now resized to the size of the output camera. This was causing
+  images not being displayed.
+
+- Fixed an issue in `DailyTransport` that would not allow the input processor to
+  shutdown if no participant ever joined the room.
+
+- Fixed base transports start and stop. In some situation processors would halt
+  or not shutdown properly.
+
+## [0.0.13] - 2024-05-14
+
+### Changed
+
+- `MoondreamService` argument `model_id` is now `model`.
+
+- `VADAnalyzer` arguments have been renamed for more clarity.
+
+### Fixed
+
+- Fixed an issue with `DailyInputTransport` and `DailyOutputTransport` that
+  could cause some threads to not start properly.
+
+- Fixed `STTService`. Add `max_silence_secs` and `max_buffer_secs` to handle
+  better what's being passed to the STT service. Also add exponential smoothing
+  to the RMS.
+
+- Fixed `WhisperSTTService`. Add `no_speech_prob` to avoid garbage output text.
+
+## [0.0.12] - 2024-05-14
+
+### Added
+
+- Added `DailyTranscriptionSettings` to be able to specify transcription
+  settings much easier (e.g. language).
+
+### Other
+
+- Updated `simple-chatbot` with Spanish.
+
+- Add missing dependencies in some of the examples.
+
+## [0.0.11] - 2024-05-13
+
+### Added
+
+- Allow stopping pipeline tasks with new `StopTaskFrame`.
+
+### Changed
+
+- TTS, STT and image generation service now use `AsyncGenerator`.
+
+### Fixed
+
+- `DailyTransport`: allow registering for participant transcriptions even if
+  input transport is not initialized yet.
+
+### Other
+
+- Updated `storytelling-chatbot`.
+
+## [0.0.10] - 2024-05-13
+
+### Added
+
+- Added Intel GPU support to `MoondreamService`.
+
+- Added support for sending transport messages (e.g. to communicate with an app
+  at the other end of the transport).
+
+- Added `FrameProcessor.push_error()` to easily send an `ErrorFrame` upstream.
+
+### Fixed
+
+- Fixed Azure services (TTS and image generation).
+
+### Other
+
+- Updated `simple-chatbot`, `moondream-chatbot` and `translation-chatbot`
+  examples.
+
+## [0.0.9] - 2024-05-12
+
+### Changed
+
+Many things have changed in this version. Many of the main ideas such as frames,
+processors, services and transports are still there but some things have changed
+a bit.
+
+- `Frame`s describe the basic units for processing. For example, text, image or
+  audio frames. Or control frames to indicate a user has started or stopped
+  speaking.
+
+- `FrameProcessor`s process frames (e.g. they convert a `TextFrame` to an
+  `ImageRawFrame`) and push new frames downstream or upstream to their linked
+  peers.
+
+- `FrameProcessor`s can be linked together. The easiest wait is to use the
+  `Pipeline` which is a container for processors. Linking processors allow
+  frames to travel upstream or downstream easily.
+
+- `Transport`s are a way to send or receive frames. There can be local
+  transports (e.g. local audio or native apps), network transports
+  (e.g. websocket) or service transports (e.g. https://daily.co).
+
+- `Pipeline`s are just a processor container for other processors.
+
+- A `PipelineTask` know how to run a pipeline.
+
+- A `PipelineRunner` can run one or more tasks and it is also used, for example,
+  to capture Ctrl-C from the user.
+
+## [0.0.8] - 2024-04-11
+
+### Added
+
+- Added `FireworksLLMService`.
+
+- Added `InterimTranscriptionFrame` and enable interim results in
+  `DailyTransport` transcriptions.
+
+### Changed
+
+- `FalImageGenService` now uses new `fal_client` package.
+
+### Fixed
+
+- `FalImageGenService`: use `asyncio.to_thread` to not block main loop when
+  generating images.
+
+- Allow `TranscriptionFrame` after an end frame (transcriptions can be delayed
+  and received after `UserStoppedSpeakingFrame`).
+
+## [0.0.7] - 2024-04-10
+
+### Added
+
+- Add `use_cpu` argument to `MoondreamService`.
+
+## [0.0.6] - 2024-04-10
+
+### Added
+
+- Added `FalImageGenService.InputParams`.
+
+- Added `URLImageFrame` and `UserImageFrame`.
+
+- Added `UserImageRequestFrame` and allow requesting an image from a participant.
+
+- Added base `VisionService` and `MoondreamService`
+
+### Changed
+
+- Don't pass `image_size` to `ImageGenService`, images should have their own size.
+
+- `ImageFrame` now receives a tuple`(width,height)` to specify the size.
+
+- `on_first_other_participant_joined` now gets a participant argument.
+
+### Fixed
+
+- Check if camera, speaker and microphone are enabled before writing to them.
+
+### Performance
+
+- `DailyTransport` only subscribe to desired participant video track.
+
+## [0.0.5] - 2024-04-06
+
+### Changed
+
+- Use `camera_bitrate` and `camera_framerate`.
+
+- Increase `camera_framerate` to 30 by default.
+
+### Fixed
+
+- Fixed `LocalTransport.read_audio_frames`.
+
+## [0.0.4] - 2024-04-04
+
+### Added
+
+- Added project optional dependencies `[silero,openai,...]`.
+
+### Changed
+
+- Moved thransports to its own directory.
+
+- Use `OPENAI_API_KEY` instead of `OPENAI_CHATGPT_API_KEY`.
+
+### Fixed
+
+- Don't write to microphone/speaker if not enabled.
+
+### Other
+
+- Added live translation example.
+
+- Fix foundational examples.
+
+## [0.0.3] - 2024-03-13
+
+### Other
+
+- Added `storybot` and `chatbot` examples.
+
+## [0.0.2] - 2024-03-12
+
+Initial public release.

CHANGELOG.md.template

@@ -0,0 +1,62 @@
+# Changelog
+
+All notable changes to the **<project name>** SDK will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+Please make sure to add your changes to the appropriate categories:
+
+## [Unreleased]
+
+### Added
+
+<!-- for new functionality -->
+
+- n/a
+
+### Changed
+
+<!-- for changed functionality -->
+
+- n/a
+
+### Deprecated
+
+<!-- for soon-to-be removed functionality -->
+
+- n/a
+
+### Removed
+
+<!-- for removed functionality -->
+
+- n/a
+
+### Fixed
+
+<!-- for fixed bugs -->
+
+- n/a
+
+### Performance
+
+<!-- for performance-relevant changes -->
+
+- n/a
+
+### Security
+
+<!-- for security-relevant changes -->
+
+- n/a
+
+### Other
+
+<!-- for everything else -->
+
+- n/a
+
+## [0.1.0] - YYYY-MM-DD
+
+Initial release.

Dockerfile

@@ -7,13 +7,14 @@ COPY *.py /app
 COPY pyproject.toml /app
 
 COPY src/ /app/src/
+COPY examples/ /app/examples/
 
 WORKDIR /app
 RUN ls --recursive /app/
 RUN pip3 install --upgrade -r requirements.txt
 RUN python -m build .
 RUN pip3 install .
-
+RUN pip3 install gunicorn
 # If running on Ubuntu, Azure TTS requires some extra config
 # https://learn.microsoft.com/en-us/azure/ai-services/speech-service/quickstarts/setup-platform?pivots=programming-language-python&tabs=linux%2Cubuntu%2Cdotnetcli%2Cdotnet%2Cjre%2Cmaven%2Cnodejs%2Cmac%2Cpypi
 
@@ -36,4 +37,4 @@ WORKDIR /app
 
 EXPOSE 8000
 # run
-CMD ["gunicorn", "--workers=2", "--log-level", "debug", "--capture-output", "daily-bot-manager:app", "--bind=0.0.0.0:8000"]
+CMD ["gunicorn", "--workers=2", "--log-level", "debug", "--chdir", "examples/server", "--capture-output", "daily-bot-manager:app", "--bind=0.0.0.0:8000"]

README.md

@@ -1,159 +1,219 @@
-# Daily AI SDK
+<div align="center">
+ <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
+</div>
 
-Build conversational, multi-modal AI apps with real-time voice and video, like this:
+# Pipecat
 
-_Demo Video to come_
+[![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>
 
-With built-in support for many of the best AI platforms (or [add your own](/docs)):
+`pipecat` is a framework for building voice (and multimodal) conversational agents. Things like personal coaches, meeting assistants, [story-telling toys for kids](https://storytelling-chatbot.fly.dev/), customer support bots, [intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0), and snarky social companions.
 
-- Azure - DALL-E, ChatGPT, and Azure AI Text-to-Speech
-- Deepgram - Speech-to-text, and Aura text-to-speech
-- Eleven Labs text-to-speech
-- Fal.ai image generation
-- OpenAI DALL-E and ChatGPT
-- Whisper local speech-to-text
+Take a look at some example apps:
 
-## Step 1: Get Started
+<p float="left">
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/storytelling-chatbot/image.png" width="280" /></a>
+    <br/>
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/moondream-chatbot/image.png" width="280" /></a>
+</p>
 
-## Build/Install
+## Getting started with voice agents
+
+You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.
+
+```shell
+# install the module
+pip install pipecat-ai
+
+# set up an .env file with API keys
+cp dot-env.template .env
+```
+
+By default, in order to minimize dependencies, only the basic framework functionality is available. Some third-party AI services require additional dependencies that you can install with:
+
+```shell
+pip install "pipecat-ai[option,...]"
+```
+
+Your project may or may not need these, so they're made available as optional requirements. Here is a list:
+
+- **AI services**: `anthropic`, `azure`, `deepgram`, `gladia`, `google`, `fal`, `lmnt`, `moondream`, `openai`, `openpipe`, `playht`, `silero`, `whisper`, `xtts`
+- **Transports**: `local`, `websocket`, `daily`
+
+## Code examples
+
+- [foundational](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational) — small snippets that build on each other, introducing one or two concepts at a time
+- [example apps](https://github.com/pipecat-ai/pipecat/tree/main/examples/) — complete applications that you can use as starting points for development
+
+## A simple voice agent running locally
+
+Here is a very basic Pipecat bot that greets a user when they join a real-time session. We'll use [Daily](https://daily.co) for real-time media transport, and [Cartesia](https://cartesia.ai/) for text-to-speech.
+
+```python
+#app.py
+
+import asyncio
+import aiohttp
+
+from pipecat.frames.frames import EndFrame, TextFrame
+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
+
+async def main():
+  async with aiohttp.ClientSession() as session:
+    # Use Daily as a real-time media transport (WebRTC)
+    transport = DailyTransport(
+      room_url=...,
+      token=...,
+      bot_name="Bot Name",
+      params=DailyParams(audio_out_enabled=True))
+
+    # Use Cartesia for Text-to-Speech
+    tts = CartesiaTTSService(
+        api_key=...,
+        voice_id=...
+      )
+
+    # Simple pipeline that will process text to speech and output the result
+    pipeline = Pipeline([tts, transport.output()])
+
+    # Create Pipecat processor that can run one or more pipelines tasks
+    runner = PipelineRunner()
+
+    # Assign the task callable to run the pipeline
+    task = PipelineTask(pipeline)
+
+    # Register an event handler to play audio when a
+    # participant joins the transport WebRTC session
+    @transport.event_handler("on_participant_joined")
+    async def on_new_participant_joined(transport, participant):
+      participant_name = participant["info"]["userName"] or ''
+      # Queue a TextFrame that will get spoken by the TTS service (Cartesia)
+      await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
+
+    # Run the pipeline task
+    await runner.run(task)
+
+if __name__ == "__main__":
+  asyncio.run(main())
+```
+
+Run it with:
+
+```shell
+python app.py
+```
+
+Daily provides a prebuilt WebRTC user interface. Whilst the app is running, you can visit at `https://<yourdomain>.daily.co/<room_url>` and listen to the bot say hello!
+
+
+## WebRTC for production use
+
+WebSockets are fine for server-to-server communication or for initial development. But for production use, you’ll need client-server audio to use a protocol designed for real-time media transport. (For an explanation of the difference between WebSockets and WebRTC, see [this post.](https://www.daily.co/blog/how-to-talk-to-an-llm-with-your-voice/#webrtc))
+
+One way to get up and running quickly with WebRTC is to sign up for a Daily developer account. Daily gives you SDKs and global infrastructure for audio (and video) routing. Every account gets 10,000 audio/video/transcription minutes free each month.
+
+Sign up [here](https://dashboard.daily.co/u/signup) and [create a room](https://docs.daily.co/reference/rest-api/rooms) in the developer Dashboard.
+
+## What is VAD?
+
+Voice Activity Detection &mdash; very important for knowing when a user has finished speaking to your bot. If you are not using press-to-talk, and want Pipecat to detect when the user has finished talking, VAD is an essential component for a natural feeling conversation.
+
+Pipecat makes use of WebRTC VAD by default when using a WebRTC transport layer. Optionally, you can use Silero VAD for improved accuracy at the cost of higher CPU usage.
+
+```shell
+pip install pipecat-ai[silero]
+```
+
+The first time your run your bot with Silero, startup may take a while whilst it downloads and caches the model in the background. You can check the progress of this in the console.
+
+
+## Hacking on the framework itself
 
 _Note that you may need to set up a virtual environment before following the instructions below. For instance, you might need to run the following from the root of the repo:_
 
-```
-python3 -m venv env
-source env/bin/activate
+```shell
+python3 -m venv venv
+source venv/bin/activate
 ```
 
 From the root of this repo, run the following:
 
-```
-pip install -r requirements.txt
+```shell
+pip install -r dev-requirements.txt
 python -m build
 ```
 
-This builds the package. To use the package locally (eg to run sample files), run
+This builds the package. To use the package locally (e.g. to run sample files), run
 
-```
-pip install --editable .
+```shell
+pip install --editable ".[option,...]"
 ```
 
 If you want to use this package from another directory, you can run:
 
-```
-pip install path_to_this_repo
+```shell
+pip install "path_to_this_repo[option,...]"
 ```
 
-## Running the samples
+### Running tests
 
-Tou can run the simple sample like so:
+From the root directory, run:
 
-```
-python src/examples/theoretical-to-real/01-say-one-thing.py -u <url of your Daily meeting> -k <your Daily API Key>
-```
-## Overview
-
-The Daily AI SDK allows you to build applications that can participate in WebRTC sessions and interact with AI Services. Some examples of what you can build with this:
-
-- conversational bots that interact 1:1 with a user, using voice recognition and text-to-speech
-- assistant bots that aggregate transcriptions from multiple participants in a meeting and provide realtime summaries or other AI-generated output.
-- image-recognition bots
-- etc
-
-## Concepts
-
-### Transport Service
-
-The SDK provides one “transport service”, which is a wrapper around Daily’s `daily-python` client (tk add link). You can use this service to listen for events related to a WebRTC session, such as “a participant joined the meeting”.
-The transport service also exposes a send queue, and a receive queue. You can use the send queue to send audio and video to the WebRTC session, and you can listen to the receive queue to see audio, video and transcription data from the WebRTC session.
-
-### AI Services
-
-The AI Service classes provide wrappers around various AI providers, and allow you to query LLMs, convert text to speech and make images from text. The audio and images can then be placed on the transport service’s send queue, where they’ll be sent to the WebRTC session.
-
-### Queue Frames
-
-Communication between the transport service and AI services, and between various AI services, takes place in Queue Frames. These frames contain an indication of the type of data as well as the data itself.
-
-## Using Transports, AI Services and Frames
-
-AI Services all define a `.run` method. This method consumes and generates `QueueFrame` frames. The kind of frames that can be consumed and generated depend on the kind of service. For instance, an LLM AI Service consumes `LLM_MESSAGE` frames (which define a history of interaction with an LLM) and emit `TEXT` frames (the response from the LLM).
-
-The `.run` method is an `AsyncIterable`, and it takes an `iterable`, `AsyncIterable` or `asyncio.Queue` that produces QueueFrames as a parameter. This makes it easy to chain AI Services, and consume input from the Transport’s `receive_queue` .
-
-AI Services also have a `.run_to_queue` method. This method is not an AsyncIterable, but instead sends processed QueueFrames to a queue. This makes it easy to send the output of an AI Service to the Transport’s `send_queue`.
-
-AI Services also define convenience functions that let you bypass creating QueueFrames for some simple cases (eg. using the TTS service to convert a string to audio output and send that audio to the transport’s `send_queue`). See below for examples.
-
-## Examples
-
-### Say Something
-
-The base TTS AI service exposes a `.say` method. After creating a transport and TTS service, you can use this method like so:
-
-```
-transport = DailyTransportService(...)
-tts = AzureTTSService()
-await tts.say("hello world", transport.send_queue)
+```shell
+pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests
 ```
 
-This will call the TTS service to render the text to audio frames, then put the audio frames on the transport’s send queue. The transport will then send those frames along to the WebRTC session.
+## Setting up your editor
 
-### Speak an LLM response
+This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting.
 
-Given a system prompt contained in a `messages` array, you can emit the LLM’s response as audio with a chain like this:
+### Emacs
 
-```
-transport = DailyTransportService(...) # setup parameters omitted
-tts = AzureTTSService()
-llm = AzureLLMService()
-messages = [...] # system prompt omitted for brevity
+You can use [use-package](https://github.com/jwiegley/use-package) to install [py-autopep8](https://codeberg.org/ideasman42/emacs-py-autopep8) package and configure `autopep8` arguments:
 
-await tts.run_to_queue(
-  transport.send_queue,
-  llm.run([QueueFrame.LLM_MESSAGES, messages])
-)
+```elisp
+(use-package py-autopep8
+  :ensure t
+  :defer t
+  :hook ((python-mode . py-autopep8-mode))
+  :config
+  (setq py-autopep8-options '("-a" "-a", "--max-line-length=100")))
 ```
 
-In this code, the LLM service object sends the messages to Azure’s OpenAI implementation, which streams chunks back asynchronously. Those chunks are aggregated by the TTS Service to ensure the best audio response (TTS works best when it gets complete sentence, so it can inflect correctly), then sent to Azure’s TTS service, converted to audio frames, and sent to the WebRTC session via the Daily transport.
+`autopep8` 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.
 
-### Pre-cache an LLM response
-
-Sometimes LLMs can be slower than we’d like for natural-feeling communication. Here’s an example where we take advantage of the time it takes to speak some pre-defined text to get a head start on the LLM response:
-
-(TK link to 04- sample)
-
-In this sample, we set up a buffer queue to receive the audio frames from the LLM response before while we are joining the call and start an asynchronous task to start filling this buffer:
-
-```
-    buffer_queue = asyncio.Queue()
-    llm_response_task = asyncio.create_task(
-        elevenlabs_tts.run_to_queue(
-            buffer_queue,
-            llm.run([QueueFrame(FrameType.LLM_MESSAGE, messages)]),
-            True,
-        )
-    )
-```
-
-Then, when we’ve joined the call, we speak the static text:
-
-```
-        await azure_tts.say("My friend...", transport.send_queue)
-```
-
-As that text is being spoken, the asynchronous LLM task continues in the background. When the text is done, we pull the frames off the buffer queue and put them in the transport’s `send_queue`:
-
-```
-        async def buffer_to_send_queue():
-            while True:
-                frame = await buffer_queue.get()
-                await transport.send_queue.put(frame)
-                buffer_queue.task_done()
-                if frame.frame_type == FrameType.END_STREAM:
-                    break
-
-        await asyncio.gather(llm_response_task, buffer_to_send_queue())
+```elisp
+(use-package pyvenv-auto
+  :ensure t
+  :defer t
+  :hook ((python-mode . pyvenv-auto-run)))
 
 ```
 
-One thing to note here is the last parameter to `run_to_queue` in the first code clause above: this causes the `run_to_queue` method to send an `END_STREAM` frame when it’s done rendering. This lets us know when to stop our `buffer_to_send_queue` task above.
+### Visual Studio Code
+
+Install the
+[autopep8](https://marketplace.visualstudio.com/items?itemName=ms-python.autopep8) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, enable formatting on save and configure `autopep8` arguments:
+
+```json
+"[python]": {
+    "editor.defaultFormatter": "ms-python.autopep8",
+    "editor.formatOnSave": true
+},
+"autopep8.args": [
+    "-a",
+    "-a",
+    "--max-line-length=100"
+],
+```
+
+## Getting help
+
+➡️ [Join our Discord](https://discord.gg/pipecat)
+
+➡️ [Reach us on X](https://x.com/pipecat_ai)

dev-requirements.txt

@@ -0,0 +1,8 @@
+autopep8~=2.3.1
+build~=1.2.1
+grpcio-tools~=1.62.2
+pip-tools~=7.4.1
+pyright~=1.1.376
+pytest~=8.3.2
+setuptools~=72.2.0
+setuptools_scm~=8.1.0

docs/README.md

@@ -1,13 +1,10 @@
-# Daily AI SDK Docs
+# Pipecat Docs
 
 ## [Architecture Overview](architecture.md)
 
-Learn about the thinking behind the SDK's design.
+Learn about the thinking behind the framework's design.
 
-## [Example Code](examples/)
+## [A Frame's Progress](frame-progress.md)
 
-The repo includes several example apps in the `src/examples` directory. The docs explain how they work.
+See how a Frame is processed through a Transport, a Pipeline, and a series of Frame Processors.
 
-## [API Reference](api/)
-
-Complete documentation of the available classes and methods in the SDK.

docs/architecture.md

@@ -1,2 +1,17 @@
-# Daily AI SDK Architecture Guide
+# Pipecat architecture guide
 
+## Frames
+
+Frames can represent discrete chunks of data, for instance a chunk of text, a chunk of audio, or an image. They can also be used to as control flow, for instance a frame that indicates that there is no more data available, or that a user started or stopped talking. They can also represent more complex data structures, such as a message array used for an LLM completion.
+
+## FrameProcessors
+
+Frame processors operate on frames. Every frame processor implements a `process_frame` method that consumes one frame and produces zero or more frames. Frame processors can do simple transforms, such as concatenating text fragments into sentences, or they can treat frames as input for an AI Service, and emit chat completions based on message arrays or transform text into audio or images.
+
+## Pipelines
+
+Pipelines are lists of frame processors linked together. Frame processors can push frames upstream or downstream to their peers. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport as an output.
+
+## Transports
+
+Transports provide input and output frame processors to receive or send frames respectively. For example, the `DailyTransport` does this with a WebRTC session joined to a Daily.co room.

docs/examples/01-say-one-thing.md

@@ -1,119 +0,0 @@
-# 01: Say One Thing
-
-_video here - youtube?_
-
-This example uses a text-to-speech (TTS) service to say one predefined sentence. But first, a quick overview of the general structure of these examples.
-
-## Running the demos
-
-All of the demos have something like this at the bottom of the file:
-
-```python
-if __name__ == "__main__":
-    (url, token) = configure()
-    asyncio.run(main(url, token))
-```
-
-### `configure()`
-
-The `configure()` function comes from `src/examples/foundational/support/runner.py`, and it allows you to configure the examples from the command line directly, or using environment variables:
-
-```bash
-python 01-say-one-thing.py -u https://YOUR_DOMAIN.daily.co/YOUR_ROOM -k YOUR_API_KEY
-# or
-DAILY_ROOM_URL=https://YOUR_DOMAIN.daily.co/YOUR_ROOM DAILY_API_KEY=YOUR_API_KEY python 01-say-one-thing.py
-# or set DAILY_ROOM_URL and DAILY_API_KEY in a .env file
-python 01-say-one-thing.py
-```
-
-You'll need a Daily account to run these demos. You can sign up for free at [daily.co](https://daily.co). Once you've signed up you can create a room from the [Dashboard](https://dashboard.daily.co/rooms), and grab [your API key](https://dashboard.daily.co/developers) while you're there.
-
-Some functionality (such as transcription) requires the bot to have owner privileges in the room. `runner.py` uses the Daily REST API to create a meeting token with owner privileges. You can learn more about meeting tokens in the [Daily docs](https://docs.daily.co/reference/rest-api/meeting-tokens).
-
-### `asyncio.run()`
-
-The AI SDK makes heavy use of Python's `asyncio` module. [This is a reasonable intro to the topic](https://builtin.com/data-science/asyncio) if you haven't worked with `asyncio` and coroutines before.
-
-You can learn a bit more about the specifics of how the Daily AI SDK uses coroutines in the [Architecture Guide](../architecture.md).
-
-## The `main()` function
-
-All of the examples have a `main()` function with a similar structure:
-
-- Configure the transport
-- Configure the AI service(s) used in the demo
-- Configure any event listeners
-- Define a processing pipeline
-- Run the example's coroutine(s)
-
-### Configuring the transport
-
-The first section of the `main()` function configures the transport object:
-
-```python
-meeting_duration_minutes = 5
-transport = DailyTransportService(
-    room_url,
-    None,
-    "Say One Thing",
-    meeting_duration_minutes,
-)
-transport.mic_enabled = True
-```
-
-The [Architecture Guide](../architecture.md) explains the transport object in more detail. In this case, we're configuring a Daily transport object and enabling the virtual microphone, so our bot can play audio.
-
-### Configuring the services
-
-As described in the [Architecture Guide](../architecture.md), 'a 'Service' is a class that processes 'Frames' as part of a 'Pipeline'. In this demo app, we'll only need one service: a text-to-speech generator. We can create an instance of the `ElevenLabsTTSService` class with this line of code:
-
-```python
-tts = ElevenLabsTTSService(aiohttp_session=session, api_key=os.getenv("ELEVENLABS_API_KEY"), voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
-```
-
-You'll need to make sure and set those environment variables somewhere. The easiest way to do that is to copy the `example.env` file in the repo and rename it to `.env`, and then add your credentials to that file. `runner.py` loads the `python-dotenv` module and initializes it, making the values in that file available in the environment.
-
-### Configuring event listeners
-
-This part isn't strictly necessary for an app like this. You could include the contents of the `on_participant_joined` function directly in the body of the `main()` function, and it would run as soon as you started the script from the command line.
-
-Instead, we can use an event handler to wait to run that code until someone else joins the meeting. We'll define a function called `greet_user()`, and use the `@transport.event_handler("on_participant_joined")` decorator to tell the SDK that we want to run that function whenever a user joins the room.
-
-```python
-@transport.event_handler("on_participant_joined")
-async def greet_user(transport, participant):
-    if participant["info"]["isLocal"]:
-        return
-
-    await tts.say(
-        "Hello there, " + participant["info"]["userName"] + "!",
-        transport.send_queue,
-    )
-
-    # wait for the output queue to be empty, then leave the meeting
-    await transport.stop_when_done()
-```
-
-### Defining a processing pipeline
-
-In this example, we don't actually have much of a processing pipeline! In fact, we're doing the whole thing inside the `greet_user()` function already.
-
-Pipelines usually look like a bunch of nested calls to the `run()` or `run_to_queue()` function from different Services. In this example, we're using the `say()` function from the TTS service. This is effectively a convenience wrapper around the `run_to_queue()` function, which we'll discuss more later. It's important to `await` this function to ensure that the speech frames are queued for playback before the next line of code, because of the `stop_when_done()` function being called immediately afterward.
-
-The output of the `say()` function goes to the transport's `send_queue`. This queue is the all-important connection between the world of the Services pipeline that's generating frames asynchronously and the ordered playback of audio and visual media in the WebRTC call.
-
-### Running the coroutines
-
-In this example, we don't actually have any separate processing pipelines—everything happens as a result of an event from the transport. So we only need to run the transport's coroutine, and await its completion:
-
-```python
-await transport.run()
-```
-
-In future examples, we'll run more processes in parallel. For now, this script can run until the transport exits—which will happen based on calling `stop_when_done()` in the `greet_user()` function.
-
-## Next Steps
-
-Next, we'll start connecting multiple AI services together by building a service pipeline.
-
-## [02 - LLM Say One Thing »](02-llm-say-one-thing.md)

docs/examples/README.md

@@ -1,5 +0,0 @@
-# Daily AI SDK Examples
-
-The docs in this folder pair with the example apps located in `src/examples/foundational`. They are designed to serve as a quick references for building different kinds of AI apps. But the examples also build on one another, so it can be really helpful to walk through them in order.
-
-To start, you can learn about the overall structure of the examples in [01 - Say One Thing](01-say-one-thing.md).

docs/frame-progress.md

@@ -0,0 +1,46 @@
+# A Frame's Progress
+
+1. A user says “Hello, LLM” and the cloud transcription service delivers a transcription to the Transport.
+![A transcript frame arrives](images/frame-progress-01.png)
+
+2. The Transport places a Transcription frame in the Pipeline’s source queue.
+![Frame in source queue](images/frame-progress-02.png)
+
+3. The Pipeline passes the Transcription frame to the first Frame Processor in its list, the LLM User Message Aggregator.
+![To UMA](images/frame-progress-03.png)
+
+4. The LLM User Message Aggregator updates the LLM Context with a `{“user”: “Hello LLM”}` message.
+![Update context](images/frame-progress-04.png)
+
+5. The LLM User Message Aggregator yields an LLM Message Frame, containing the updated LLM Context. The Pipeline passes this frame to the LLM Frame Processor.
+![Update context](images/frame-progress-05.png)
+
+6. The LLM Frame Processor creates a streaming chat completion based on the LLM context and yields the first chunk of a response, Text Frame with the value “Hi, “. The Pipeline passes this frame to the TTS Frame Processor. The TTS Frame Processor aggregates this response but doesn’t yield anything, yet, because it’s waiting for a full sentence.
+![LLM yields Text](images/frame-progress-06.png)
+
+7. The LLM Frame Processor yields another Text Frame with the value “there.”. The Pipeline passes this frame to the TTS Frame Processor.
+![LLM yields more Text](images/frame-progress-07.png)
+
+8. The TTS Frame Processor now has a full sentence, so it starts streaming audio based on “Hi, there.” It yields the first chunk of streaming audio as an Audio frame, which the Pipeline passes to the LLM Assistant Message Aggregator.
+![TTS yields Audio](images/frame-progress-08.png)
+
+9. The LLM Assistant Message Aggregator doesn’t do anything with Audio frames, so it immediately yields the frame, unchanged. This is the convention for all Frame Processors: frames that the processor doesn’t process should be immediately yielded.
+![pass-through](images/frame-progress-09.png)
+
+10. The Pipeline places the first Audio frame in its sink queue, which is being watched by the Transport. Since the frame is now in a queue, the Pipeline can continue processing other frames. Note that the source and sink queues form a sort of “boundary of concurrent processing” between a Pipeline and the outside world. In a Pipeline, Frames are processed sequentially; once a Frame is on a queue it can be processed in parallel with the frames being processed by the Pipeline. TODO: link to a more in-depth section about this.
+![sink queue](images/frame-progress-10.png)
+
+11. The TTS Frame Processor yields another Audio frame as the Transport transmits the first Audio frame.
+![parallel audio](images/frame-progress-11.png)
+
+12. As before, the LLM Assistant Message Aggregator immediately yields the Audio frame and the Pipeline places the Audio frame in the sink queue.
+![sink queue 2](images/frame-progress-12.png)
+
+13. The TTS Frame Processor has no more frames to yield. The LLM Frame Processor emits an LLM Response End Frame, which the Pipeline passes to the TTS Frame Processor.
+![response end](images/frame-progress-13.png)
+
+14. The TTS Frame Processor immediately yields the LLM Response End Frame, so the Pipeline passes it along to the LLM Assistant Message Aggregator. The LLM Assistant Message Aggregator updates the LLM Context with the full response from the LLM. TODO TODO: I realized I forgot that the TSS Frame Processor also yields the Text frames that the LLM emitted so that the LLM Assistant Message Aggregator could accumulate them, arrggh.
+![response end](images/frame-progress-14.png)
+
+15. The system is quiet, and waiting for the next message from the Transport.
+![response end](images/frame-progress-15.png)

dot-env.template

@@ -0,0 +1,45 @@
+# Anthropic
+ANTHROPIC_API_KEY=...
+
+# Azure
+AZURE_SPEECH_REGION=...
+AZURE_SPEECH_API_KEY=...
+
+AZURE_CHATGPT_API_KEY=...
+AZURE_CHATGPT_ENDPOINT=https://...
+AZURE_CHATGPT_MODEL=...
+
+AZURE_DALLE_API_KEY=...
+AZURE_DALLE_ENDPOINT=https://...
+AZURE_DALLE_MODEL=...
+
+# Daily
+DAILY_API_KEY=...
+DAILY_SAMPLE_ROOM_URL=https://...
+
+# ElevenLabs
+ELEVENLABS_API_KEY=...
+ELEVENLABS_VOICE_ID=...
+
+# Fal
+FAL_KEY=...
+
+# Fireworks
+FIREWORKS_API_KEY=...
+
+# Gladia
+GLADIA_API_KEY=...
+
+# LMNT
+LMNT_API_KEY=...
+LMNT_VOICE_ID=...
+
+# PlayHT
+PLAY_HT_USER_ID=...
+PLAY_HT_API_KEY=...
+
+# OpenAI
+OPENAI_API_KEY=...
+
+#OpenPipe
+OPENPIPE_API_KEY=...

examples/README.md

@@ -0,0 +1,87 @@
+
+
+# Pipecat — Examples
+
+## Foundational snippets
+Small snippets that build on each other, introducing one or two concepts at a time.
+
+➡️ [Take a look](https://github.com/pipecat-ai/pipecat/tree/main/examples/foundational)
+
+## Chatbot examples
+Collection of self-contained real-time voice and video AI demo applications built with Pipecat.
+
+### Quickstart
+
+Each project has its own set of dependencies and configuration variables. They intentionally avoids shared code across projects — you can grab whichever demo folder you want to work with as a starting point.
+
+We recommend you start with a virtual environment:
+
+```shell
+cd pipecat-ai/examples/simple-chatbot
+
+python -m venv venv
+
+source venv/bin/activate
+
+pip install -r requirements.txt
+```
+
+Next, follow the steps in the README for each demo.
+
+ℹ️ Make sure you `pip install -r requirements.txt` for each demo project, so you can be sure to have the necessary service dependencies that extend the functionality of Pipecat. You can read more about the framework architecture [here](https://github.com/pipecat-ai/pipecat/tree/main/docs).
+
+## Projects:
+
+| Project                                      | Description                                                                                                                                | Services                                                          |
+|----------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------|
+| [Simple Chatbot](simple-chatbot)             | Basic voice-driven conversational bot. A good starting point for learning the flow of the framework.                                       | Deepgram, ElevenLabs, OpenAI, Daily, Daily Prebuilt UI            |
+| [Storytelling Chatbot](storytelling-chatbot) | Stitches together multiple third-party services to create a collaborative storytime experience.                                            | Deepgram, ElevenLabs, OpenAI, Fal, Daily, Custom UI               |
+| [Translation Chatbot](translation-chatbot)   | Listens for user speech, then translates that speech to Spanish and speaks the translation back. Demonstrates multi-participant use-cases. | Deepgram, Azure, OpenAI, Daily, Daily Prebuilt UI                 |
+| [Moondream Chatbot](moondream-chatbot)       | Demonstrates how to add vision capabilities to GPT4. **Note: works best with a GPU**                                                       | Deepgram, ElevenLabs, OpenAI, Moondream, Daily, Daily Prebuilt UI |
+| [Patient intake](patient-intake)             | A chatbot that can call functions in response to user input.                                                                               | Deepgram, ElevenLabs, OpenAI, Daily, Daily Prebuilt UI            |
+| [Dialin Chatbot](dialin-chatbot)             | A chatbot that connects to an incoming phone call from Daily or Twilio.                                                                    | Deepgram, ElevenLabs, OpenAI, Daily, Twilio                       |
+| [Twilio Chatbot](twilio-chatbot)             | A chatbot that connects to an incoming phone call from Twilio.                                                                             | Deepgram, ElevenLabs, OpenAI, Daily, Twilio                       |
+| [studypal](studypal)                         | A chatbot to have a conversation about any article on the web                                                                              |                                                                   |
+
+> [!IMPORTANT]
+> These example projects use Daily as a WebRTC transport and can be joined using their hosted Prebuilt UI.
+> It provides a quick way to join a real-time session with your bot and test your ideas without building any frontend code. If you'd like to see an example of a custom UI, try Storybot.
+
+
+## FAQ
+
+### Deployment
+
+For each of these demos we've included a `Dockerfile`. Out of the box, this should provide everything needed to get the respective demo running on a VM:
+
+```shell
+docker build username/app:tag .
+
+docker run -p 7860:7860 --env-file ./.env username/app:tag
+
+docker push ...
+```
+
+### SSL
+
+If you're working with a custom UI (such as with the Storytelling Chatbot), it's important to ensure your deployment platform supports HTTPS, as accessing user devices such as mics and webcams requires SSL.
+
+If you try to run a custom UI without SSL, you may see an error in the console telling you that `navigator` is undefined, or no devices are available.
+
+### Are these examples production ready?
+
+Yes, kind of.
+
+These demos attempt to keep things simple and are unopinionated regarding environment or scalability.
+
+We're using FastAPI to spawn a subprocess for the bots / agents — useful for small tests, but not so great for production grade apps with many concurrent users. You can see how this works in each project's `start` endpoint in `server.py`.
+
+Creating virtualized worker pools and on-demand instances is out of scope for these examples, but we hope to add some examples to this repo soon!
+
+For projects that have CUDA as a requirement, such as Moondream Chatbot, be sure to deploy to a GPU-powered platform (such as [fly.io](https://fly.io) or [Runpod](https://runpod.io).)
+
+## Getting help
+
+➡️ [Join our Discord](https://discord.gg/pipecat)
+
+➡️ [Reach us on Twitter](https://x.com/pipecat_ai)

examples/deployment/flyio-example/Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.11-bullseye
+
+# Open port 7860 for http service
+ENV FAST_API_PORT=7860
+EXPOSE 7860
+
+# Install Python dependencies
+COPY *.py .
+COPY ./requirements.txt requirements.txt
+RUN pip3 install --no-cache-dir --upgrade -r requirements.txt
+
+# Start the FastAPI server
+CMD python3 bot_runner.py --port ${FAST_API_PORT}

examples/deployment/flyio-example/README.md

@@ -0,0 +1,39 @@
+# Fly.io deployment example
+
+This project modifies the `bot_runner.py` server to launch a new machine for each user session. This is a recommended approach for production vs. running shell processess as your deployment will quickly run out of system resources under load.
+
+For this example, we are using Daily as a WebRTC transport and provisioning a new room and token for each session. You can use another transport, such as WebSockets, by modifying the `bot.py` and `bot_runner.py` files accordingly.
+
+## Setting up your fly.io deployment
+
+### Create your fly.toml file
+
+You can copy the `example-fly.toml` as a reference. Be sure to change the app name to something unique.
+
+### Create your .env file
+
+Copy the base `env.example` to `.env` and enter the necessary API keys.
+
+`FLY_APP_NAME` should match that in the `fly.toml` file.
+
+### Launch a new fly.io project
+
+`fly launch` or `fly launch --org your-org-name`
+
+### Set the necessary app secrets from your .env
+
+Note: you can do this manually via the fly.io dashboard under the "secrets" sub-section of your deployment (e.g. "https://fly.io/apps/fly-app-name/secrets") or run the following terminal command:
+
+`cat .env | tr '\n' ' ' | xargs flyctl secrets set`
+
+### Deploy your machine
+
+`fly deploy`
+
+## Connecting to your bot
+
+Send a post request to your running fly.io instance:
+
+`curl --location --request POST 'https://YOUR_FLY_APP_NAME/start_bot'`
+
+This request will wait until the machine enters into a `starting` state, before returning the a room URL and token to join.

examples/deployment/flyio-example/bot.py

@@ -0,0 +1,100 @@
+import asyncio
+import os
+import sys
+import argparse
+
+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.frames.frames import LLMMessagesFrame, EndFrame
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+daily_api_key = os.getenv("DAILY_API_KEY", "")
+daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
+
+
+async def main(room_url: str, token: str):
+    transport = DailyTransport(
+        room_url,
+        token,
+        "Chatbot",
+        DailyParams(
+            api_url=daily_api_url,
+            api_key=daily_api_key,
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=False,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            transcription_enabled=True,
+        )
+    )
+
+    tts = ElevenLabsTTSService(
+        api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        model="gpt-4o")
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are Chatbot, a friendly, helpful robot. Your output will be converted to audio so don't include special characters other than '!' or '?' in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by saying hello.",
+        },
+    ]
+
+    tma_in = LLMUserResponseAggregator(messages)
+    tma_out = LLMAssistantResponseAggregator(messages)
+
+    pipeline = Pipeline([
+        transport.input(),
+        tma_in,
+        llm,
+        tts,
+        transport.output(),
+        tma_out,
+    ])
+
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        transport.capture_participant_transcription(participant["id"])
+        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())
+
+    @transport.event_handler("on_call_state_updated")
+    async def on_call_state_updated(transport, state):
+        if state == "left":
+            await task.queue_frame(EndFrame())
+
+    runner = PipelineRunner()
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Pipecat Bot")
+    parser.add_argument("-u", type=str, help="Room URL")
+    parser.add_argument("-t", type=str, help="Token")
+    config = parser.parse_args()
+
+    asyncio.run(main(config.u, config.t))

examples/deployment/flyio-example/bot_runner.py

@@ -0,0 +1,215 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import argparse
+import subprocess
+import os
+
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI, Request, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+
+from pipecat.transports.services.helpers.daily_rest import (
+    DailyRESTHelper, DailyRoomObject, DailyRoomProperties, DailyRoomParams)
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+
+# ------------ Configuration ------------ #
+
+MAX_SESSION_TIME = 5 * 60  # 5 minutes
+REQUIRED_ENV_VARS = [
+    'DAILY_API_KEY',
+    'OPENAI_API_KEY',
+    'ELEVENLABS_API_KEY',
+    'ELEVENLABS_VOICE_ID',
+    'FLY_API_KEY',
+    'FLY_APP_NAME',]
+
+FLY_API_HOST = os.getenv("FLY_API_HOST", "https://api.machines.dev/v1")
+FLY_APP_NAME = os.getenv("FLY_APP_NAME", "pipecat-fly-example")
+FLY_API_KEY = os.getenv("FLY_API_KEY", "")
+FLY_HEADERS = {
+    'Authorization': f"Bearer {FLY_API_KEY}",
+    'Content-Type': 'application/json'
+}
+
+daily_helpers = {}
+
+
+# ----------------- API ----------------- #
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    aiohttp_session = aiohttp.ClientSession()
+    daily_helpers["rest"] = DailyRESTHelper(
+        daily_api_key=os.getenv("DAILY_API_KEY", ""),
+        daily_api_url=os.getenv("DAILY_API_URL", 'https://api.daily.co/v1'),
+        aiohttp_session=aiohttp_session
+    )
+    yield
+    await aiohttp_session.close()
+
+app = FastAPI(lifespan=lifespan)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"]
+)
+
+# ----------------- Main ----------------- #
+
+
+async def spawn_fly_machine(room_url: str, token: str):
+    async with aiohttp.ClientSession() as session:
+        # Use the same image as the bot runner
+        async with session.get(f"{FLY_API_HOST}/apps/{FLY_APP_NAME}/machines", headers=FLY_HEADERS) as r:
+            if r.status != 200:
+                text = await r.text()
+                raise Exception(f"Unable to get machine info from Fly: {text}")
+
+            data = await r.json()
+            image = data[0]['config']['image']
+
+        # Machine configuration
+        cmd = f"python3 bot.py -u {room_url} -t {token}"
+        cmd = cmd.split()
+        worker_props = {
+            "config": {
+                "image": image,
+                "auto_destroy": True,
+                "init": {
+                    "cmd": cmd
+                },
+                "restart": {
+                    "policy": "no"
+                },
+                "guest": {
+                    "cpu_kind": "shared",
+                    "cpus": 1,
+                    "memory_mb": 1024
+                }
+            },
+        }
+
+        # Spawn a new machine instance
+        async with session.post(f"{FLY_API_HOST}/apps/{FLY_APP_NAME}/machines", headers=FLY_HEADERS, json=worker_props) as r:
+            if r.status != 200:
+                text = await r.text()
+                raise Exception(f"Problem starting a bot worker: {text}")
+
+            data = await r.json()
+            # Wait for the machine to enter the started state
+            vm_id = data['id']
+
+        async with session.get(f"{FLY_API_HOST}/apps/{FLY_APP_NAME}/machines/{vm_id}/wait?state=started", headers=FLY_HEADERS) as r:
+            if r.status != 200:
+                text = await r.text()
+                raise Exception(f"Bot was unable to enter started state: {text}")
+
+    print(f"Machine joined room: {room_url}")
+
+
+@app.post("/start_bot")
+async def start_bot(request: Request) -> JSONResponse:
+    try:
+        data = await request.json()
+        # Is this a webhook creation request?
+        if "test" in data:
+            return JSONResponse({"test": True})
+    except Exception as e:
+        pass
+
+    # Use specified room URL, or create a new one if not specified
+    room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", "")
+
+    if not room_url:
+        params = DailyRoomParams(
+            properties=DailyRoomProperties()
+        )
+        try:
+            room: DailyRoomObject = await daily_helpers["rest"].create_room(params=params)
+        except Exception as e:
+            raise HTTPException(
+                status_code=500,
+                detail=f"Unable to provision room {e}")
+    else:
+        # Check passed room URL exists, we should assume that it already has a sip set up
+        try:
+            room: DailyRoomObject = await daily_helpers["rest"].get_room_from_url(room_url)
+        except Exception:
+            raise HTTPException(
+                status_code=500, detail=f"Room not found: {room_url}")
+
+    # Give the agent a token to join the session
+    token = await daily_helpers["rest"].get_token(room.url, MAX_SESSION_TIME)
+
+    if not room or not token:
+        raise HTTPException(
+            status_code=500, detail=f"Failed to get token for room: {room_url}")
+
+    # Launch a new fly.io machine, or run as a shell process (not recommended)
+    run_as_process = os.getenv("RUN_AS_PROCESS", False)
+
+    if run_as_process:
+        try:
+            subprocess.Popen(
+                [f"python3 -m bot -u {room.url} -t {token}"],
+                shell=True,
+                bufsize=1,
+                cwd=os.path.dirname(os.path.abspath(__file__)))
+        except Exception as e:
+            raise HTTPException(
+                status_code=500, detail=f"Failed to start subprocess: {e}")
+    else:
+        try:
+            await spawn_fly_machine(room.url, token)
+        except Exception as e:
+            raise HTTPException(
+                status_code=500, detail=f"Failed to spawn VM: {e}")
+
+    # Grab a token for the user to join with
+    user_token = await daily_helpers["rest"].get_token(room.url, MAX_SESSION_TIME)
+
+    return JSONResponse({
+        "room_url": room.url,
+        "token": user_token,
+    })
+
+if __name__ == "__main__":
+    # Check environment variables
+    for env_var in REQUIRED_ENV_VARS:
+        if env_var not in os.environ:
+            raise Exception(f"Missing environment variable: {env_var}.")
+
+    parser = argparse.ArgumentParser(description="Pipecat Bot Runner")
+    parser.add_argument("--host", type=str,
+                        default=os.getenv("HOST", "0.0.0.0"), help="Host address")
+    parser.add_argument("--port", type=int,
+                        default=os.getenv("PORT", 7860), help="Port number")
+    parser.add_argument("--reload", action="store_true",
+                        default=False, help="Reload code on change")
+
+    config = parser.parse_args()
+
+    try:
+        import uvicorn
+
+        uvicorn.run(
+            "bot_runner:app",
+            host=config.host,
+            port=config.port,
+            reload=config.reload
+        )
+    except KeyboardInterrupt:
+        print("Pipecat runner shutting down...")

examples/deployment/flyio-example/env.example

@@ -0,0 +1,8 @@
+DAILY_API_KEY=
+DAILY_SAMPLE_ROOM_URL= # Enter a Daily room URL to use a set room URL each time (useful for local testing)
+OPENAI_API_KEY=
+ELEVENLABS_API_KEY=
+ELEVENLABS_VOICE_ID=
+FLY_API_KEY=
+FLY_APP_NAME=
+RUN_AS_PROCESS= # Spawn fly.io machine for each session or run as local process

examples/deployment/flyio-example/example-fly.toml

@@ -0,0 +1,25 @@
+# fly.toml app configuration file generated for pipecat-fly-example on 2024-07-01T15:04:53+01:00
+#
+# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
+#
+
+app = 'pipecat-fly-example'
+primary_region = 'sjc'
+
+[build]
+
+[env]
+  FLY_APP_NAME = 'pipecat-fly-example'
+
+[http_service]
+  internal_port = 7860
+  force_https = true
+  auto_stop_machines = true
+  auto_start_machines = true
+  min_machines_running = 0
+  processes = ['app']
+
+[[vm]]
+  memory = 512
+  cpu_kind = 'shared'
+  cpus = 1

examples/deployment/flyio-example/requirements.txt

@@ -0,0 +1,5 @@
+pipecat-ai[daily,openai,silero]
+fastapi
+uvicorn
+python-dotenv
+loguru

examples/dialin-chatbot/.dockerignore

@@ -0,0 +1,3 @@
+**/.DS_Store
+.env
+.env.*

examples/dialin-chatbot/.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+runpod.toml
+
+# custom script to recursively upgrade items in requirements.py
+upgrade_requirements.py
+.DS_Store

examples/dialin-chatbot/Dockerfile

@@ -0,0 +1,40 @@
+FROM python:3.11-bullseye
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG USE_PERSISTENT_DATA
+ENV PYTHONUNBUFFERED=1
+# Expose FastAPI port
+ENV FAST_API_PORT=7860
+EXPOSE 7860
+
+# Install system dependencies
+RUN apt-get update && apt-get install --no-install-recommends -y \
+    build-essential \
+    git \
+    ffmpeg \
+    google-perftools \
+    ca-certificates curl gnupg \
+    && apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Set home to the user's home directory
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    PYTHONPATH=$HOME/app \
+    PYTHONUNBUFFERED=1
+
+# Switch to the "user" user
+USER user
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Install Python dependencies
+COPY *.py .
+COPY ./requirements.txt requirements.txt
+RUN pip3 install --no-cache-dir --upgrade -r requirements.txt
+
+# Start the FastAPI server
+CMD python3 bot_runner.py --host "0.0.0.0" --port ${FAST_API_PORT}

examples/dialin-chatbot/README.md

@@ -0,0 +1,85 @@
+<div align="center">
+ <img alt="pipecat" width="300px" height="auto" src="image.png">
+</div>
+
+# Dialin example
+
+Example project that demonstrates how to add phone number dialin to your Pipecat bots. We include examples for both Daily (`bot_daily.py`) and Twilio (`bot_twilio.py`), depending on who you want to use as a phone vendor.
+
+- 🔁 Transport: Daily WebRTC
+- 💬 Speech-to-Text: Deepgram via Daily transport
+- 🤖 LLM: GPT4-o / OpenAI
+- 🔉 Text-to-Speech: ElevenLabs
+
+#### Should I use Daily or Twilio as a vendor?
+
+If you're starting from scratch, using Daily to provision phone numbers alongside Daily as a transport offers some convenience (such as automatic call forwarding.)
+
+If you already have Twilio numbers and workflows that you want to connect to your Pipecat bots, there is some additional configuration required (you'll need to create a `on_dialin_ready` and use the Twilio client to trigger the forward.)
+
+You can read more about this, as well as see respective walkthroughs in our docs.
+
+## Setup
+
+```shell
+# Install the requirements
+pip install -r requirements.txt
+
+# Setup your env
+mv env.example .env
+```
+
+## Using Daily numbers
+
+Run `bot_runner.py` to handle incoming HTTP requests:
+
+`python bot_runner.py --host localhost`
+
+Then target the following URL:
+
+`POST /daily_start_bot`
+
+For more configuration options, please consult Daily's API documentation.
+
+
+## Using Twilio numbers
+
+As above, but target the following URL:
+
+`POST /twilio_start_bot`
+
+For more configuration options, please consult Twilio's API documentation.
+
+## Deployment example
+
+A Dockerfile is included in this demo for convenience. Here is an example of how to build and deploy your bot to [fly.io](https://fly.io).
+
+*Please note: This demo spawns agents as subprocesses for convenience / demonstration purposes. You would likely not want to do this in production as it would limit concurrency to available system resources. For more information on how to deploy your bots using VMs, refer to the Pipecat documentation.*
+
+### Build the docker image
+
+`docker build -t tag:project .`
+
+### Launch the fly project
+
+`mv fly.example.toml fly.toml`
+
+`fly launch` (using the included fly.toml)
+
+### Setup your secrets on Fly
+
+Set the necessary secrets (found in `env.example`)
+
+`fly secrets set DAILY_API_KEY=... OPENAI_API_KEY=... ELEVENLABS_API_KEY=... ELEVENLABS_VOICE_ID=...`
+
+If you're using Twilio as a number vendor:
+
+`fly secrets set TWILIO_ACCOUNT_SID=... TWILIO_AUTH_TOKEN=...`
+
+### Deploy!
+
+`fly deploy`
+
+## Need to do something more advanced?
+
+This demo covers the basics of bot telephony. If you want to know more about working with PSTN / SIP, please ping us on [Discord](https://discord.gg/pipecat).

examples/dialin-chatbot/bot_daily.py

@@ -0,0 +1,109 @@
+import asyncio
+import os
+import sys
+import argparse
+
+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.frames.frames import (
+    LLMMessagesFrame,
+    EndFrame
+)
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyDialinSettings
+from pipecat.vad.silero import SileroVADAnalyzer
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+daily_api_key = os.getenv("DAILY_API_KEY", "")
+daily_api_url = os.getenv("DAILY_API_URL", "https://api.daily.co/v1")
+
+
+async def main(room_url: str, token: str, callId: str, callDomain: str):
+    # diallin_settings are only needed if Daily's SIP URI is used
+    # If you are handling this via Twilio, Telnyx, set this to None
+    # and handle call-forwarding when on_dialin_ready fires.
+    diallin_settings = DailyDialinSettings(
+        call_id=callId,
+        call_domain=callDomain
+    )
+
+    transport = DailyTransport(
+        room_url,
+        token,
+        "Chatbot",
+        DailyParams(
+            api_url=daily_api_url,
+            api_key=daily_api_key,
+            dialin_settings=diallin_settings,
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=False,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            transcription_enabled=True,
+        )
+    )
+
+    tts = ElevenLabsTTSService(
+        api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        model="gpt-4o"
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by saying 'Oh, hello! Who dares dial me at this hour?!'.",
+        },
+    ]
+
+    tma_in = LLMUserResponseAggregator(messages)
+    tma_out = LLMAssistantResponseAggregator(messages)
+
+    pipeline = Pipeline([
+        transport.input(),
+        tma_in,
+        llm,
+        tts,
+        transport.output(),
+        tma_out,
+    ])
+
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        transport.capture_participant_transcription(participant["id"])
+        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)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Pipecat Simple ChatBot")
+    parser.add_argument("-u", type=str, help="Room URL")
+    parser.add_argument("-t", type=str, help="Token")
+    parser.add_argument("-i", type=str, help="Call ID")
+    parser.add_argument("-d", type=str, help="Call Domain")
+    config = parser.parse_args()
+
+    asyncio.run(main(config.u, config.t, config.i, config.d))

examples/dialin-chatbot/bot_runner.py

@@ -0,0 +1,238 @@
+"""
+bot_runner.py
+
+HTTP service that listens for incoming calls from either Daily or Twilio,
+provisioning a room and starting a Pipecat bot in response.
+
+Refer to README for more information.
+"""
+
+
+import aiohttp
+import os
+import argparse
+import subprocess
+
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI, Request, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse, PlainTextResponse
+from twilio.twiml.voice_response import VoiceResponse
+
+from pipecat.transports.services.helpers.daily_rest import (
+    DailyRESTHelper,
+    DailyRoomObject,
+    DailyRoomProperties,
+    DailyRoomSipParams,
+    DailyRoomParams)
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+
+# ------------ Configuration ------------ #
+
+MAX_SESSION_TIME = 5 * 60  # 5 minutes
+REQUIRED_ENV_VARS = ['OPENAI_API_KEY', 'DAILY_API_KEY',
+                     'ELEVENLABS_API_KEY', 'ELEVENLABS_VOICE_ID']
+
+daily_helpers = {}
+
+# ----------------- API ----------------- #
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    aiohttp_session = aiohttp.ClientSession()
+    daily_helpers["rest"] = DailyRESTHelper(
+        daily_api_key=os.getenv("DAILY_API_KEY", ""),
+        daily_api_url=os.getenv("DAILY_API_URL", 'https://api.daily.co/v1'),
+        aiohttp_session=aiohttp_session
+    )
+    yield
+    await aiohttp_session.close()
+
+app = FastAPI(lifespan=lifespan)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"]
+)
+
+"""
+Create Daily room, tell the bot if the room is created for Twilio's SIP or Daily's SIP (vendor).
+When the vendor is Daily, the bot handles the call forwarding automatically,
+i.e, forwards the call from the "hold music state" to the Daily Room's SIP URI.
+
+Alternatively, when the vendor is Twilio (not Daily), the bot is responsible for
+updating the state on Twilio. So when `dialin-ready` fires, it takes appropriate
+action using the Twilio Client library.
+"""
+
+
+async def _create_daily_room(room_url, callId, callDomain=None, vendor="daily"):
+    if not room_url:
+        params = DailyRoomParams(
+            properties=DailyRoomProperties(
+                # Note: these are the default values, except for the display name
+                sip=DailyRoomSipParams(
+                    display_name="dialin-user",
+                    video=False,
+                    sip_mode="dial-in",
+                    num_endpoints=1
+                )
+            )
+        )
+
+        print(f"Creating new room...")
+        room: DailyRoomObject = await daily_helpers["rest"].create_room(params=params)
+
+    else:
+        # Check passed room URL exist (we assume that it already has a sip set up!)
+        try:
+            print(f"Joining existing room: {room_url}")
+            room: DailyRoomObject = await daily_helpers["rest"].get_room_from_url(room_url)
+        except Exception:
+            raise HTTPException(
+                status_code=500, detail=f"Room not found: {room_url}")
+
+    print(f"Daily room: {room.url} {room.config.sip_endpoint}")
+
+    # Give the agent a token to join the session
+    token = await daily_helpers["rest"].get_token(room.url, MAX_SESSION_TIME)
+
+    if not room or not token:
+        raise HTTPException(
+            status_code=500, detail=f"Failed to get room or token token")
+
+    # Spawn a new agent, and join the user session
+    # Note: this is mostly for demonstration purposes (refer to 'deployment' in docs)
+    if vendor == "daily":
+        bot_proc = f"python3 - m bot_daily - u {room.url} - t {token} - i {
+            callId} - d {callDomain}"
+    else:
+        bot_proc = f"python3 - m bot_twilio - u {room.url} - t {
+            token} - i {callId} - s {room.config.sip_endpoint}"
+
+    try:
+        subprocess.Popen(
+            [bot_proc],
+            shell=True,
+            bufsize=1,
+            cwd=os.path.dirname(os.path.abspath(__file__))
+        )
+    except Exception as e:
+        raise HTTPException(
+            status_code=500, detail=f"Failed to start subprocess: {e}")
+
+    return room
+
+
+@app.post("/twilio_start_bot", response_class=PlainTextResponse)
+async def twilio_start_bot(request: Request):
+    print(f"POST /twilio_voice_bot")
+
+    # twilio_start_bot is invoked directly by Twilio (as a web hook).
+    # On Twilio, under Active Numbers, pick the phone number
+    # Click Configure and under Voice Configuration,
+    # "a call comes in" choose webhook and point the URL to
+    # where this code is hosted.
+    data = {}
+    try:
+        # shouldnt have received json, twilio sends form data
+        form_data = await request.form()
+        data = dict(form_data)
+    except Exception:
+        pass
+
+    room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", None)
+    callId = data.get('CallSid')
+
+    if not callId:
+        raise HTTPException(
+            status_code=500, detail="Missing 'CallSid' in request")
+
+    print("CallId: %s" % callId)
+
+    # create room and tell the bot to join the created room
+    # note: Twilio does not require a callDomain
+    room: DailyRoomObject = await _create_daily_room(room_url, callId, None, "twilio")
+
+    print(f"Put Twilio on hold...")
+    # We have the room and the SIP URI,
+    # but we do not know if the Daily SIP Worker and the Bot have joined the call
+    # put the call on hold until the 'on_dialin_ready' fires.
+    # Then, the bot will update the called sid with the sip uri.
+    # http://com.twilio.music.classical.s3.amazonaws.com/BusyStrings.mp3
+    resp = VoiceResponse()
+    resp.play(
+        url="http://com.twilio.sounds.music.s3.amazonaws.com/MARKOVICHAMP-Borghestral.mp3", loop=10)
+    return str(resp)
+
+
+@app.post("/daily_start_bot")
+async def daily_start_bot(request: Request) -> JSONResponse:
+    # The /daily_start_bot is invoked when a call is received on Daily's SIP URI
+    # daily_start_bot will create the room, put the call on hold until
+    # the bot and sip worker are ready. Daily will automatically
+    # forward the call to the SIP URi when dialin_ready fires.
+
+    # Use specified room URL, or create a new one if not specified
+    room_url = os.getenv("DAILY_SAMPLE_ROOM_URL", None)
+    # Get the dial-in properties from the request
+    try:
+        data = await request.json()
+        if "test" in data:
+            # Pass through any webhook checks
+            return JSONResponse({"test": True})
+        callId = data.get("callId", None)
+        callDomain = data.get("callDomain", None)
+    except Exception:
+        raise HTTPException(
+            status_code=500,
+            detail="Missing properties 'callId' or 'callDomain'")
+
+    print(f"CallId: {callId}, CallDomain: {callDomain}")
+    room: DailyRoomObject = await _create_daily_room(room_url, callId, callDomain, "daily")
+
+    # Grab a token for the user to join with
+    return JSONResponse({
+        "room_url": room.url,
+        "sipUri": room.config.sip_endpoint
+    })
+
+# ----------------- Main ----------------- #
+
+
+if __name__ == "__main__":
+    # Check environment variables
+    for env_var in REQUIRED_ENV_VARS:
+        if env_var not in os.environ:
+            raise Exception(f"Missing environment variable: {env_var}.")
+
+    parser = argparse.ArgumentParser(description="Pipecat Bot Runner")
+    parser.add_argument("--host", type=str,
+                        default=os.getenv("HOST", "0.0.0.0"), help="Host address")
+    parser.add_argument("--port", type=int,
+                        default=os.getenv("PORT", 7860), help="Port number")
+    parser.add_argument("--reload", action="store_true",
+                        default=True, help="Reload code on change")
+
+    config = parser.parse_args()
+
+    try:
+        import uvicorn
+
+        uvicorn.run(
+            "bot_runner:app",
+            host=config.host,
+            port=config.port,
+            reload=config.reload
+        )
+
+    except KeyboardInterrupt:
+        print("Pipecat runner shutting down...")

examples/dialin-chatbot/bot_twilio.py

@@ -0,0 +1,123 @@
+import asyncio
+import os
+import sys
+import argparse
+
+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.frames.frames import (
+    LLMMessagesFrame,
+    EndFrame
+)
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from twilio.rest import Client
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+twilio_account_sid = os.getenv('TWILIO_ACCOUNT_SID')
+twilio_auth_token = os.getenv('TWILIO_AUTH_TOKEN')
+twilioclient = Client(twilio_account_sid, twilio_auth_token)
+
+daily_api_key = os.getenv("DAILY_API_KEY", "")
+
+
+async def main(room_url: str, token: str, callId: str, sipUri: str):
+    # dialin_settings are only needed if Daily's SIP URI is used
+    # If you are handling this via Twilio, Telnyx, set this to None
+    # and handle call-forwarding when on_dialin_ready fires.
+    transport = DailyTransport(
+        room_url,
+        token,
+        "Chatbot",
+        DailyParams(
+            api_key=daily_api_key,
+            dialin_settings=None,  # Not required for Twilio
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=False,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            transcription_enabled=True,
+        )
+    )
+
+    tts = ElevenLabsTTSService(
+        api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
+    )
+
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        model="gpt-4o"
+    )
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are Chatbot, a friendly, helpful robot. 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, but keep your responses brief. Start by saying 'Hello! Who dares dial me at this hour?!'.",
+        },
+    ]
+
+    tma_in = LLMUserResponseAggregator(messages)
+    tma_out = LLMAssistantResponseAggregator(messages)
+
+    pipeline = Pipeline([
+        transport.input(),
+        tma_in,
+        llm,
+        tts,
+        transport.output(),
+        tma_out,
+    ])
+
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+    @transport.event_handler("on_first_participant_joined")
+    async def on_first_participant_joined(transport, participant):
+        transport.capture_participant_transcription(participant["id"])
+        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())
+
+    @transport.event_handler("on_dialin_ready")
+    async def on_dialin_ready(transport, cdata):
+        # For Twilio, Telnyx, etc. You need to update the state of the call
+        # and forward it to the sip_uri..
+        print(f"Forwarding call: {callId} {sipUri}")
+
+        try:
+            # The TwiML is updated using Twilio's client library
+            call = twilioclient.calls(callId).update(
+                twiml=f'<Response><Dial><Sip>{sipUri}</Sip></Dial></Response>'
+            )
+        except Exception as e:
+            raise Exception(f"Failed to forward call: {str(e)}")
+
+    runner = PipelineRunner()
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Pipecat Simple ChatBot")
+    parser.add_argument("-u", type=str, help="Room URL")
+    parser.add_argument("-t", type=str, help="Token")
+    parser.add_argument("-i", type=str, help="Call ID")
+    parser.add_argument("-s", type=str, help="SIP URI")
+    config = parser.parse_args()
+
+    asyncio.run(main(config.u, config.t, config.i, config.s))

examples/dialin-chatbot/env.example

@@ -0,0 +1,8 @@
+DAILY_SAMPLE_ROOM_URL=https://yourdomain.daily.co/yourroom # (optional: for joining the bot to the same room repeatedly for local dev)
+DAILY_API_KEY=.
+DAILY_API_URL=api.daily.co/v1
+OPENAI_API_KEY=
+ELEVENLABS_API_KEY=
+ELEVENLABS_VOICE_ID=
+TWILIO_ACCOUNT_SID=
+TWILIO_AUTH_TOKEN=

examples/dialin-chatbot/fly.example.toml

@@ -0,0 +1,19 @@
+# fly.toml app configuration file generated for pipecat-dialin-demo on 2024-06-03T15:57:57+02:00
+#
+# See https://fly.io/docs/reference/configuration/ for information about how to use this file.
+#
+
+app = 'pipecat-dialin-demo'
+primary_region = 'sjc'
+
+[build]
+
+[http_service]
+  internal_port = 7860
+  force_https = true
+  auto_stop_machines = true
+  auto_start_machines = true
+  min_machines_running = 1
+
+[[vm]]
+  size = 'performance-1x'

examples/dialin-chatbot/requirements.txt

@@ -0,0 +1,5 @@
+pipecat-ai[daily,openai,silero]
+fastapi
+uvicorn
+python-dotenv
+twilio

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

@@ -0,0 +1,56 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import TextFrame
+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
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(Pipeline([tts, transport.output()]))
+
+        # Register an event handler so we can play the audio when the
+        # participant joins.
+        @transport.event_handler("on_participant_joined")
+        async def on_new_participant_joined(transport, participant):
+            participant_name = participant["info"]["userName"] or ''
+            await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,52 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import TextFrame
+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.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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        transport = LocalAudioTransport(TransportParams(audio_out_enabled=True))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        pipeline = Pipeline([tts, transport.output()])
+
+        task = PipelineTask(pipeline)
+
+        async def say_something():
+            await asyncio.sleep(1)
+            await task.queue_frame(TextFrame("Hello there!"))
+
+        runner = PipelineRunner()
+
+        await asyncio.gather(runner.run(task), say_something())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,68 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import LLMMessagesFrame
+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.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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Say One Thing From an LLM",
+            DailyParams(audio_out_enabled=True))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
+            }]
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(Pipeline([llm, tts, transport.output()]))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await task.queue_frame(LLMMessagesFrame(messages))
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/03-still-frame.py

@@ -0,0 +1,69 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Show a still frame image",
+            DailyParams(
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024
+            )
+        )
+
+        imagegen = FalImageGenService(
+            params=FalImageGenService.InputParams(
+                image_size="square_hd"
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(Pipeline([imagegen, transport.output()]))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            # Note that we do not put an EndFrame() item in the pipeline for this demo.
+            # This means that the bot will stay in the channel until it times out.
+            # An EndFrame() in the pipeline would cause the transport to shut
+            # down.
+            await task.queue_frames([TextFrame("a cat in the style of picasso")])
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,68 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+import tkinter as tk
+
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.fal import FalImageGenService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.local.tk import TkLocalTransport
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        tk_root = tk.Tk()
+        tk_root.title("Picasso Cat")
+
+        transport = TkLocalTransport(
+            tk_root,
+            TransportParams(
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024))
+
+        imagegen = FalImageGenService(
+            params=FalImageGenService.InputParams(
+                image_size="square_hd"
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        pipeline = Pipeline([imagegen, transport.output()])
+
+        task = PipelineTask(pipeline)
+        await task.queue_frames([TextFrame("a cat in the style of picasso")])
+
+        runner = PipelineRunner()
+
+        async def run_tk():
+            while not task.has_finished():
+                tk_root.update()
+                tk_root.update_idletasks()
+                await asyncio.sleep(0.1)
+
+        await asyncio.gather(runner.run(task), run_tk())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,87 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+from pipecat.pipeline.merge_pipeline import SequentialMergePipeline
+from pipecat.pipeline.pipeline import Pipeline
+
+from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(room_url, None, "Static And Dynamic Speech")
+
+        meeting = TransportServiceOutput(transport, mic_enabled=True)
+
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+        )
+        azure_tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
+        )
+
+        elevenlabs_tts = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
+        )
+
+        messages = [{"role": "system",
+                     "content": "tell the user a joke about llamas"}]
+
+        # Start a task to run the LLM to create a joke, and convert the LLM
+        # output to audio frames. This task will run in parallel with generating
+        # and speaking the audio for static text, so there's no delay to speak
+        # the LLM response.
+        llm_pipeline = Pipeline([llm, elevenlabs_tts])
+        llm_task = PipelineTask(llm_pipeline)
+        await llm_task.queue_frames([LLMMessagesFrame(messages), EndPipeFrame()])
+
+        simple_tts_pipeline = Pipeline([azure_tts])
+        await simple_tts_pipeline.queue_frames(
+            [
+                TextFrame("My friend the LLM is going to tell a joke about llamas."),
+                EndPipeFrame(),
+            ]
+        )
+
+        merge_pipeline = SequentialMergePipeline(
+            [simple_tts_pipeline, llm_pipeline])
+
+        await asyncio.gather(
+            transport.run(merge_pipeline),
+            simple_tts_pipeline.run_pipeline(),
+            llm_pipeline.run_pipeline(),
+        )
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,163 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from dataclasses import dataclass
+
+from pipecat.frames.frames import (
+    AppFrame,
+    Frame,
+    ImageRawFrame,
+    LLMFullResponseStartFrame,
+    LLMMessagesFrame,
+    TextFrame
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.parallel_task import ParallelTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.aggregators.gated import GatedAggregator
+from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
+from pipecat.processors.aggregators.sentence import SentenceAggregator
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+@dataclass
+class MonthFrame(AppFrame):
+    month: str
+
+    def __str__(self):
+        return f"{self.name}(month: {self.month})"
+
+
+class MonthPrepender(FrameProcessor):
+    def __init__(self):
+        super().__init__()
+        self.most_recent_month = "Placeholder, month frame not yet received"
+        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):
+            await self.push_frame(TextFrame(f"{self.most_recent_month}: {frame.text}"))
+            self.prepend_to_next_text_frame = False
+        elif isinstance(frame, LLMFullResponseStartFrame):
+            self.prepend_to_next_text_frame = True
+            await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Month Narration Bot",
+            DailyParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024
+            )
+        )
+
+        tts = ElevenLabsTTSService(
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+
+        imagegen = FalImageGenService(
+            params=FalImageGenService.InputParams(
+                image_size="square_hd"
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        gated_aggregator = GatedAggregator(
+            gate_open_fn=lambda frame: isinstance(frame, ImageRawFrame),
+            gate_close_fn=lambda frame: isinstance(frame, LLMFullResponseStartFrame),
+            start_open=False
+        )
+
+        sentence_aggregator = SentenceAggregator()
+        month_prepender = MonthPrepender()
+        llm_full_response_aggregator = LLMFullResponseAggregator()
+
+        pipeline = Pipeline([
+            llm,                     # LLM
+            sentence_aggregator,     # Aggregates LLM output into full sentences
+            ParallelTask(            # Run pipelines in parallel aggregating the result
+                [month_prepender, tts],                   # Create "Month: sentence" and output audio
+                [llm_full_response_aggregator, imagegen]  # Aggregate full LLM response
+            ),
+            gated_aggregator,        # Queues everything until an image is available
+            transport.output()       # Transport output
+        ])
+
+        frames = []
+        for month in [
+            "January",
+            "February",
+            "March",
+            "April",
+            "May",
+            "June",
+            "July",
+            "August",
+            "September",
+            "October",
+            "November",
+            "December",
+        ]:
+            messages = [
+                {
+                    "role": "system",
+                    "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
+                }
+            ]
+            frames.append(MonthFrame(month=month))
+            frames.append(LLMMessagesFrame(messages))
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await task.queue_frames(frames)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,170 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+import tkinter as tk
+
+from pipecat.frames.frames import AudioRawFrame, Frame, URLImageRawFrame, LLMMessagesFrame, 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 PipelineTask
+from pipecat.processors.aggregators.llm_response import LLMFullResponseAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        tk_root = tk.Tk()
+        tk_root.title("Calendar")
+
+        runner = PipelineRunner()
+
+        async def get_month_data(month):
+            messages = [{"role": "system", "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.", }]
+
+            class ImageDescription(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    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)
+
+            class AudioGrabber(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    self.audio = bytearray()
+
+                async def process_frame(self, frame: Frame, direction: FrameDirection):
+                    await super().process_frame(frame, direction)
+
+                    if isinstance(frame, AudioRawFrame):
+                        self.audio.extend(frame.audio)
+                        self.frame = AudioRawFrame(
+                            bytes(self.audio), frame.sample_rate, frame.num_channels)
+
+            class ImageGrabber(FrameProcessor):
+                def __init__(self):
+                    super().__init__()
+                    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
+
+            llm = OpenAILLMService(
+                api_key=os.getenv("OPENAI_API_KEY"),
+                model="gpt-4o")
+
+            tts = ElevenLabsTTSService(
+                api_key=os.getenv("ELEVENLABS_API_KEY"),
+                voice_id=os.getenv("ELEVENLABS_VOICE_ID"))
+
+            imagegen = FalImageGenService(
+                params=FalImageGenService.InputParams(
+                    image_size="square_hd"
+                ),
+                aiohttp_session=session,
+                key=os.getenv("FAL_KEY"))
+
+            aggregator = LLMFullResponseAggregator()
+
+            description = ImageDescription()
+
+            audio_grabber = AudioGrabber()
+
+            image_grabber = ImageGrabber()
+
+            pipeline = Pipeline([
+                llm,
+                aggregator,
+                description,
+                ParallelPipeline([tts, audio_grabber],
+                                 [imagegen, image_grabber])
+            ])
+
+            task = PipelineTask(pipeline)
+            await task.queue_frame(LLMMessagesFrame(messages))
+            await task.stop_when_done()
+
+            await runner.run(task)
+
+            return {
+                "month": month,
+                "text": description.text,
+                "image": image_grabber.frame,
+                "audio": audio_grabber.frame,
+            }
+
+        transport = TkLocalTransport(
+            tk_root,
+            TransportParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024))
+
+        pipeline = Pipeline([transport.output()])
+
+        task = PipelineTask(pipeline)
+
+        # We only specify a few months as we create tasks all at once and we
+        # might get rate limited otherwise.
+        months: list[str] = [
+            "January",
+            "February",
+        ]
+
+        # We create one task per month. This will be executed concurrently.
+        month_tasks = [asyncio.create_task(get_month_data(month)) for month in months]
+
+        # Now we wait for each month task in the order they're completed. The
+        # benefit is we'll have as little delay as possible before the first
+        # month, and likely no delay between months, but the months won't
+        # display in order.
+        async def show_images(month_tasks):
+            for month_data_task in asyncio.as_completed(month_tasks):
+                data = await month_data_task
+                await task.queue_frames([data["image"], data["audio"]])
+
+            await runner.stop_when_done()
+
+        async def run_tk():
+            while not task.has_finished():
+                tk_root.update()
+                tk_root.update_idletasks()
+                await asyncio.sleep(0.1)
+
+        await asyncio.gather(runner.run(task), show_images(month_tasks), run_tk())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,113 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import Frame, LLMMessagesFrame, MetricsFrame
+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.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class MetricsLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        if isinstance(frame, MetricsFrame):
+            print(
+                f"!!! MetricsFrame: {frame}, ttfb: {frame.ttfb}, processing: {frame.processing}, tokens: {frame.tokens}, characters: {frame.characters}")
+        await self.push_frame(frame, direction)
+
+
+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 = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o"
+        )
+
+        ml = MetricsLogger()
+
+        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.",
+            },
+        ]
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),
+            tma_in,
+            llm,
+            tts,
+            ml,
+            transport.output(),
+            tma_out,
+        ])
+
+        task = PipelineTask(pipeline)
+        task = PipelineTask(pipeline, PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            report_only_initial_ttfb=False,
+        ))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,129 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from PIL import Image
+
+from pipecat.frames.frames import ImageRawFrame, Frame, SystemFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator,
+)
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.transports.services.daily import DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from pipecat.transports.services.daily import DailyParams
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class ImageSyncAggregator(FrameProcessor):
+    def __init__(self, speaking_path: str, waiting_path: str):
+        super().__init__()
+        self._speaking_image = Image.open(speaking_path)
+        self._speaking_image_format = self._speaking_image.format
+        self._speaking_image_bytes = self._speaking_image.tobytes()
+
+        self._waiting_image = Image.open(waiting_path)
+        self._waiting_image_format = self._waiting_image.format
+        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(ImageRawFrame(image=self._speaking_image_bytes, size=(1024, 1024), format=self._speaking_image_format))
+            await self.push_frame(frame)
+            await self.push_frame(ImageRawFrame(image=self._waiting_image_bytes, size=(1024, 1024), format=self._waiting_image_format))
+        else:
+            await self.push_frame(frame)
+
+
+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,
+                camera_out_enabled=True,
+                camera_out_width=1024,
+                camera_out_height=1024,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            )
+        )
+
+        tts = ElevenLabsTTSService(
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        image_sync_aggregator = ImageSyncAggregator(
+            os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
+            os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
+        )
+
+        pipeline = Pipeline([
+            transport.input(),
+            image_sync_aggregator,
+            tma_in,
+            llm,
+            tts,
+            transport.output(),
+            tma_out
+        ])
+
+        task = PipelineTask(pipeline)
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            participant_name = participant["info"]["userName"] or ''
+            transport.capture_participant_transcription(participant["id"])
+            await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/07-interruptible.py

@@ -0,0 +1,99 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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 = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # 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):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,95 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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 = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY"),
+            model="claude-3-opus-20240229")
+
+        # todo: think more about how to handle system prompts in a more general way. OpenAI,
+        # Google, and Anthropic all have slightly different approaches to providing a system
+        # prompt.
+        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, helpful, and brief way. Say hello.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,125 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.processors.frameworks.langchain import LangchainProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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)
+
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+message_store = {}
+
+
+def get_session_history(session_id: str) -> BaseChatMessageHistory:
+    if session_id not in message_store:
+        message_store[session_id] = ChatMessageHistory()
+    return message_store[session_id]
+
+
+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
+        )
+
+        prompt = ChatPromptTemplate.from_messages(
+            [
+                ("system",
+                 "Be nice and helpful. Answer very briefly and without special characters like `#` or `*`. "
+                 "Your response will be synthesized to voice and those characters will create unnatural sounds.",
+                 ),
+                MessagesPlaceholder("chat_history"),
+                ("human", "{input}"),
+            ])
+        chain = prompt | ChatOpenAI(model="gpt-4o", temperature=0.7)
+        history_chain = RunnableWithMessageHistory(
+            chain,
+            get_session_history,
+            history_messages_key="chat_history",
+            input_messages_key="input")
+        lc = LangchainProcessor(history_chain)
+
+        tma_in = LLMUserResponseAggregator()
+        tma_out = LLMAssistantResponseAggregator()
+
+        pipeline = Pipeline(
+            [
+                transport.input(),      # Transport user input
+                tma_in,                 # User responses
+                lc,                     # Langchain
+                tts,                    # TTS
+                transport.output(),     # Transport bot output
+                tma_out,                # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            lc.set_participant_id(participant["id"])
+            # Kick off the conversation.
+            # the `LLMMessagesFrame` will be picked up by the LangchainProcessor using
+            # only the content of the last message to inject it in the prompt defined
+            # above. So no role is required here.
+            messages = [(
+                {
+                    "content": "Please briefly introduce yourself to the user."
+                }
+            )]
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,98 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+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 runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True
+            )
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = DeepgramTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-helios-en"
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            stt,                 # STT
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,97 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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_sample_rate=44100,
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="a0e99841-438c-4a64-b679-ae501e7d6091",  # Barbershop Man
+            sample_rate=44100,
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            tma_out,             # Goes before the transport because cartesia has word-level timestamps!
+            transport.output(),  # Transport bot output
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,96 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.playht import PlayHTTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                audio_out_sample_rate=16000,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = PlayHTTTSService(
+            user_id=os.getenv("PLAYHT_USER_ID"),
+            api_key=os.getenv("PLAYHT_API_KEY"),
+            voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,103 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.azure import AzureLLMService, AzureSTTService, AzureTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                audio_out_sample_rate=16000,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            )
+        )
+
+        stt = AzureSTTService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
+        )
+
+        tts = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
+        )
+
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            stt,                 # STT
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,95 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.openai import OpenAITTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                audio_out_sample_rate=24000,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = OpenAITTSService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            voice="alloy"
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,102 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator,
+)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openpipe import OpenPipeLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+import time
+
+from dotenv import load_dotenv
+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 = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        timestamp = int(time.time())
+        llm = OpenPipeLLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
+            model="gpt-4o",
+            tags={
+                "conversation_id": f"pipecat-{timestamp}"
+            }
+        )
+
+        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.",
+            },
+        ]
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,97 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.xtts import XTTSService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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 = XTTSService(
+            aiohttp_session=session,
+            voice_id="Claribel Dervla",
+            language="en",
+            base_url="http://localhost:8000"
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,100 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.gladia import GladiaSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            )
+        )
+
+        stt = GladiaSTTService(
+            api_key=os.getenv("GLADIA_API_KEY"),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            stt,                 # STT
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,95 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.lmnt import LmntTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+                audio_out_sample_rate=24000,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = LmntTTSService(
+            api_key=os.getenv("LMNT_API_KEY"),
+            voice_id="morgan"
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/08-bots-arguing.py

@@ -0,0 +1,149 @@
+from typing import Tuple
+import aiohttp
+import asyncio
+import logging
+import os
+from pipecat.pipeline.aggregators import SentenceAggregator
+from pipecat.pipeline.pipeline import Pipeline
+
+from pipecat.transports.daily_transport import DailyTransport
+from pipecat.services.azure_ai_services import AzureLLMService, AzureTTSService
+from pipecat.services.elevenlabs_ai_services import ElevenLabsTTSService
+from pipecat.services.fal_ai_services import FalImageGenService
+from pipecat.pipeline.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
+
+from runner import configure
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logging.basicConfig(format=f"%(levelno)s %(asctime)s %(message)s")
+logger = logging.getLogger("pipecat")
+logger.setLevel(logging.DEBUG)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            duration_minutes=10,
+            mic_enabled=True,
+            mic_sample_rate=16000,
+            camera_enabled=True,
+            camera_width=1024,
+            camera_height=1024,
+        )
+
+        llm = AzureLLMService(
+            api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
+            endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
+            model=os.getenv("AZURE_CHATGPT_MODEL"),
+        )
+        tts1 = AzureTTSService(
+            api_key=os.getenv("AZURE_SPEECH_API_KEY"),
+            region=os.getenv("AZURE_SPEECH_REGION"),
+        )
+        tts2 = ElevenLabsTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="jBpfuIE2acCO8z3wKNLl",
+        )
+        dalle = FalImageGenService(
+            params=FalImageGenService.InputParams(
+                image_size="1024x1024"
+            ),
+            aiohttp_session=session,
+            key=os.getenv("FAL_KEY"),
+        )
+
+        bot1_messages = [
+            {
+                "role": "system",
+                "content": "You are a stern librarian. You strongly believe that a hot dog is a sandwich. Start by stating this fact in a few sentences, then be prepared to debate this with the user. You shouldn't ever compromise on the fundamental truth that a hot dog is a sandwich. Your responses should only be a few sentences long.",
+            },
+        ]
+        bot2_messages = [
+            {
+                "role": "system",
+                "content": "You are a silly cat, and you strongly believe that a hot dog is not a sandwich. Debate this with the user, only responding with a few sentences. Don't ever accept that a hot dog is a sandwich.",
+            },
+        ]
+
+        async def get_text_and_audio(messages) -> Tuple[str, bytearray]:
+            """This function streams text from the LLM and uses the TTS service to convert
+             that text to speech as it's received. """
+            source_queue = asyncio.Queue()
+            sink_queue = asyncio.Queue()
+            sentence_aggregator = SentenceAggregator()
+            pipeline = Pipeline(
+                [llm, sentence_aggregator, tts1], source_queue, sink_queue
+            )
+
+            await source_queue.put(LLMMessagesFrame(messages))
+            await source_queue.put(EndFrame())
+            await pipeline.run_pipeline()
+
+            message = ""
+            all_audio = bytearray()
+            while sink_queue.qsize():
+                frame = sink_queue.get_nowait()
+                if isinstance(frame, TextFrame):
+                    message += frame.text
+                elif isinstance(frame, AudioFrame):
+                    all_audio.extend(frame.audio)
+
+            return (message, all_audio)
+
+        async def get_bot1_statement():
+            message, audio = await get_text_and_audio(bot1_messages)
+
+            bot1_messages.append({"role": "assistant", "content": message})
+            bot2_messages.append({"role": "user", "content": message})
+
+            return audio
+
+        async def get_bot2_statement():
+            message, audio = await get_text_and_audio(bot2_messages)
+
+            bot2_messages.append({"role": "assistant", "content": message})
+            bot1_messages.append({"role": "user", "content": message})
+
+            return audio
+
+        async def argue():
+            for i in range(100):
+                print(f"In iteration {i}")
+
+                bot1_description = "A woman conservatively dressed as a librarian in a library surrounded by books, cartoon, serious, highly detailed"
+
+                (audio1, image_data1) = await asyncio.gather(
+                    get_bot1_statement(), dalle.run_image_gen(bot1_description)
+                )
+                await transport.send_queue.put(
+                    [
+                        ImageFrame(image_data1[1], image_data1[2]),
+                        AudioFrame(audio1),
+                    ]
+                )
+
+                bot2_description = "A cat dressed in a hot dog costume, cartoon, bright colors, funny, highly detailed"
+
+                (audio2, image_data2) = await asyncio.gather(
+                    get_bot2_statement(), dalle.run_image_gen(bot2_description)
+                )
+                await transport.send_queue.put(
+                    [
+                        ImageFrame(image_data2[1], image_data2[2]),
+                        AudioFrame(audio2),
+                    ]
+                )
+
+        await asyncio.gather(transport.run(), argue())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/09-mirror.py

@@ -0,0 +1,57 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import sys
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.transports.services.daily import DailyTransport, DailyParams
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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, "Test",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_is_live=True,
+                camera_out_width=1280,
+                camera_out_height=720
+            )
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_video(participant["id"])
+
+        pipeline = Pipeline([transport.input(), transport.output()])
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,71 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import sys
+
+import tkinter as tk
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        tk_root = tk.Tk()
+        tk_root.title("Local Mirror")
+
+        daily_transport = DailyTransport(
+            room_url, token, "Test", DailyParams(
+                audio_in_enabled=True))
+
+        tk_transport = TkLocalTransport(
+            tk_root,
+            TransportParams(
+                audio_out_enabled=True,
+                camera_out_enabled=True,
+                camera_out_is_live=True,
+                camera_out_width=1280,
+                camera_out_height=720))
+
+        @daily_transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_video(participant["id"])
+
+        pipeline = Pipeline([daily_transport.input(), tk_transport.output()])
+
+        task = PipelineTask(pipeline)
+
+        async def run_tk():
+            while not task.has_finished():
+                tk_root.update()
+                tk_root.update_idletasks()
+                await asyncio.sleep(0.1)
+
+        runner = PipelineRunner()
+
+        await asyncio.gather(runner.run(task), run_tk())
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/10-wake-phrase.py

@@ -0,0 +1,93 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
+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.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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,
+            "Robot",
+            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 = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
+            },
+        ]
+
+        hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            hey_robot_filter,    # Filter out speech not directed at the robot
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            await tts.say("Hi! If you want to talk to me, just say 'Hey Robot'.")
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/11-sound-effects.py

@@ -0,0 +1,152 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+import wave
+
+from pipecat.frames.frames import (
+    Frame,
+    AudioRawFrame,
+    LLMFullResponseEndFrame,
+    LLMMessagesFrame,
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMUserResponseAggregator,
+    LLMAssistantResponseAggregator,
+)
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.processors.logger import FrameLogger
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+sounds = {}
+sound_files = ["ding1.wav", "ding2.wav"]
+
+script_dir = os.path.dirname(__file__)
+
+for file in sound_files:
+    # Build the full path to the image file
+    full_path = os.path.join(script_dir, "assets", file)
+    # Get the filename without the extension to use as the dictionary key
+    filename = os.path.splitext(os.path.basename(full_path))[0]
+    # Open the image and convert it to bytes
+    with wave.open(full_path) as audio_file:
+        sounds[file] = AudioRawFrame(audio_file.readframes(-1),
+                                     audio_file.getframerate(), audio_file.getnchannels())
+
+
+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
+            await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+class InboundSoundEffectWrapper(FrameProcessor):
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, LLMMessagesFrame):
+            await self.push_frame(sounds["ding2.wav"])
+            # In case anything else downstream needs it
+            await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+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()
+            )
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+
+        tts = ElevenLabsTTSService(
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            voice_id="ErXwobaYiN019PkySvjV",
+        )
+
+        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. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+        out_sound = OutboundSoundEffectWrapper()
+        in_sound = InboundSoundEffectWrapper()
+        fl = FrameLogger("LLM Out")
+        fl2 = FrameLogger("Transcription In")
+
+        pipeline = Pipeline([
+            transport.input(),
+            tma_in,
+            in_sound,
+            fl2,
+            llm,
+            fl,
+            tts,
+            out_sound,
+            transport.output(),
+            tma_out
+        ])
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            await tts.say("Hi, I'm listening!")
+            await transport.send_audio(sounds["ding1.wav"])
+
+        runner = PipelineRunner()
+
+        task = PipelineTask(pipeline)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/12-describe-video.py

@@ -0,0 +1,106 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+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.moondream import MoondreamService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class UserImageRequester(FrameProcessor):
+
+    def __init__(self, participant_id: str | None = None):
+        super().__init__()
+        self._participant_id = participant_id
+
+    def set_participant_id(self, participant_id: str):
+        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)
+        await self.push_frame(frame, direction)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Describe participant video",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        user_response = UserResponseAggregator()
+
+        image_requester = UserImageRequester()
+
+        vision_aggregator = VisionImageFrameAggregator()
+
+        # If you run into weird description, try with use_cpu=True
+        moondream = MoondreamService()
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await tts.say("Hi there! Feel free to ask me what I see.")
+            transport.capture_participant_video(participant["id"], framerate=0)
+            transport.capture_participant_transcription(participant["id"])
+            image_requester.set_participant_id(participant["id"])
+
+        pipeline = Pipeline([
+            transport.input(),
+            user_response,
+            image_requester,
+            vision_aggregator,
+            moondream,
+            tts,
+            transport.output()
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,108 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+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.google import GoogleLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class UserImageRequester(FrameProcessor):
+
+    def __init__(self, participant_id: str | None = None):
+        super().__init__()
+        self._participant_id = participant_id
+
+    def set_participant_id(self, participant_id: str):
+        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)
+        await self.push_frame(frame, direction)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Describe participant video",
+            DailyParams(
+                audio_in_enabled=True,  # This is so Silero VAD can get audio data
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        user_response = UserResponseAggregator()
+
+        image_requester = UserImageRequester()
+
+        vision_aggregator = VisionImageFrameAggregator()
+
+        google = GoogleLLMService(
+            model="gemini-1.5-flash-latest",
+            api_key=os.getenv("GOOGLE_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await tts.say("Hi there! Feel free to ask me what I see.")
+            transport.capture_participant_video(participant["id"], framerate=0)
+            transport.capture_participant_transcription(participant["id"])
+            image_requester.set_participant_id(participant["id"])
+
+        pipeline = Pipeline([
+            transport.input(),
+            user_response,
+            image_requester,
+            vision_aggregator,
+            google,
+            tts,
+            transport.output()
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,108 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+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.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class UserImageRequester(FrameProcessor):
+
+    def __init__(self, participant_id: str | None = None):
+        super().__init__()
+        self._participant_id = participant_id
+
+    def set_participant_id(self, participant_id: str):
+        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)
+        await self.push_frame(frame, direction)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Describe participant video",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        user_response = UserResponseAggregator()
+
+        image_requester = UserImageRequester()
+
+        vision_aggregator = VisionImageFrameAggregator()
+
+        openai = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o"
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await tts.say("Hi there! Feel free to ask me what I see.")
+            transport.capture_participant_video(participant["id"], framerate=0)
+            transport.capture_participant_transcription(participant["id"])
+            image_requester.set_participant_id(participant["id"])
+
+        pipeline = Pipeline([
+            transport.input(),
+            user_response,
+            image_requester,
+            vision_aggregator,
+            openai,
+            tts,
+            transport.output()
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,108 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+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.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class UserImageRequester(FrameProcessor):
+
+    def __init__(self, participant_id: str | None = None):
+        super().__init__()
+        self._participant_id = participant_id
+
+    def set_participant_id(self, participant_id: str):
+        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)
+        await self.push_frame(frame, direction)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Describe participant video",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        user_response = UserResponseAggregator()
+
+        image_requester = UserImageRequester()
+
+        vision_aggregator = VisionImageFrameAggregator()
+
+        anthropic = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY")
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+            sample_rate=16000,
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await tts.say("Hi there! Feel free to ask me what I see.")
+            transport.capture_participant_video(participant["id"], framerate=0)
+            transport.capture_participant_transcription(participant["id"])
+            image_requester.set_participant_id(participant["id"])
+
+        pipeline = Pipeline([
+            transport.input(),
+            user_response,
+            image_requester,
+            vision_aggregator,
+            anthropic,
+            tts,
+            transport.output()
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/13-whisper-transcription.py

@@ -0,0 +1,60 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import sys
+
+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.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)
+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}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(room_url, None, "Transcription bot",
+                                   DailyParams(audio_in_enabled=True))
+
+        stt = WhisperSTTService()
+
+        tl = TranscriptionLogger()
+
+        pipeline = Pipeline([transport.input(), stt, tl])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,54 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import sys
+
+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.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)
+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}")
+
+
+async def main():
+    transport = LocalAudioTransport(TransportParams(audio_in_enabled=True))
+
+    stt = WhisperSTTService()
+
+    tl = TranscriptionLogger()
+
+    pipeline = Pipeline([transport.input(), stt, tl])
+
+    task = PipelineTask(pipeline)
+
+    runner = PipelineRunner()
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,61 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+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
+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)
+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}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(room_url, None, "Transcription bot",
+                                   DailyParams(audio_in_enabled=True))
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tl = TranscriptionLogger()
+
+        pipeline = Pipeline([transport.input(), stt, tl])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/14-function-calling.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.logger import FrameLogger
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def start_fetch_weather(function_name, llm, context):
+    await llm.push_frame(TextFrame("Let me check on that."))
+
+
+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 = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+        # 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)
+
+        fl_in = FrameLogger("Inner")
+        fl_out = FrameLogger("Outer")
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "get_current_weather",
+                    "description": "Get the current 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. Infer this from the users location.",
+                            },
+                        },
+                        "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. 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, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            fl_in,
+            transport.input(),
+            context_aggregator.user(),
+            llm,
+            fl_out,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ])
+
+        task = PipelineTask(pipeline)
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await tts.say("Hi! Ask me about the weather in San Francisco.")
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/15-switch-voices.py

@@ -0,0 +1,151 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import aiohttp
+import asyncio
+import os
+import sys
+
+from pipecat.frames.frames import LLMMessagesFrame
+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.processors.filters.function_filter import FunctionFilter
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+current_voice = "News Lady"
+
+
+async def switch_voice(function_name, tool_call_id, args, llm, context, result_callback):
+    global current_voice
+    current_voice = args["voice"]
+    await result_callback({"voice": f"You are now using your {current_voice} voice. Your responses should now be as if you were a {current_voice}."})
+
+
+async def news_lady_filter(frame) -> bool:
+    return current_voice == "News Lady"
+
+
+async def british_lady_filter(frame) -> bool:
+    return current_voice == "British Lady"
+
+
+async def barbershop_man_filter(frame) -> bool:
+    return current_voice == "Barbershop Man"
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Pipecat",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        news_lady = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="bf991597-6c13-47e4-8411-91ec2de5c466",  # Newslady
+        )
+
+        british_lady = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        barbershop_man = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="a0e99841-438c-4a64-b679-ae501e7d6091",  # Barbershop Man
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+        llm.register_function("switch_voice", switch_voice)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "switch_voice",
+                    "description": "Switch your voice only when the user asks you to",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "voice": {
+                                "type": "string",
+                                "description": "The voice the user wants you to use",
+                            },
+                        },
+                        "required": ["voice"],
+                    },
+                })]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            context_aggregator.user(),  # User responses
+            llm,                 # LLM
+            ParallelPipeline(    # TTS (one of the following vocies)
+                [FunctionFilter(news_lady_filter), news_lady],            # News Lady voice
+                [FunctionFilter(british_lady_filter), british_lady],      # British Lady voice
+                [FunctionFilter(barbershop_man_filter), barbershop_man],  # Barbershop Man voice
+            ),
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append(
+                {
+                    "role": "system",
+                    "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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,146 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import LLMMessagesFrame
+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.processors.filters.function_filter import FunctionFilter
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.whisper import Model, WhisperSTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+current_language = "English"
+
+
+async def switch_language(function_name, tool_call_id, args, llm, context, result_callback):
+    global current_language
+    current_language = args["language"]
+    await result_callback({"voice": f"Your answers from now on should be in {current_language}."})
+
+
+async def english_filter(frame) -> bool:
+    return current_language == "English"
+
+
+async def spanish_filter(frame) -> bool:
+    return current_language == "Spanish"
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Pipecat",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True
+            )
+        )
+
+        stt = WhisperSTTService(model=Model.LARGE)
+
+        english_tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        spanish_tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="846d6cb0-2301-48b6-9683-48f5618ea2f6",  # Spanish-speaking Lady
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
+        llm.register_function("switch_language", switch_language)
+
+        tools = [
+            ChatCompletionToolParam(
+                type="function",
+                function={
+                    "name": "switch_language",
+                    "description": "Switch to another language when the user asks you to",
+                    "parameters": {
+                        "type": "object",
+                        "properties": {
+                            "language": {
+                                "type": "string",
+                                "description": "The language the user wants you to speak",
+                            },
+                        },
+                        "required": ["language"],
+                    },
+                })]
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can speak the following languages: 'English' and 'Spanish'.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            stt,                 # STT
+            context_aggregator.user(),  # User responses
+            llm,                 # LLM
+            ParallelPipeline(    # TTS (bot will speak the chosen language)
+                [FunctionFilter(english_filter), english_tts],  # English
+                [FunctionFilter(spanish_filter), spanish_tts],  # Spanish
+            ),
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant()  # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append(
+                {
+                    "role": "system",
+                    "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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,130 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.deepgram import DeepgramTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyTransportMessageFrame
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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 = DeepgramTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-asteria-en",
+            base_url="http://0.0.0.0:8080/v1/speak"
+        )
+
+        llm = OpenAILLMService(
+            # To use OpenAI
+            # api_key=os.getenv("OPENAI_API_KEY"),
+            # model="gpt-4o"
+            # Or, to use a local vLLM (or similar) api server
+            model="meta-llama/Meta-Llama-3-8B-Instruct",
+            base_url="http://0.0.0.0:8000/v1"
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        # When a participant joins, start transcription for that participant so the
+        # bot can "hear" and respond to them.
+        @transport.event_handler("on_participant_joined")
+        async def on_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+
+        # When the first participant joins, the bot should introduce itself.
+        @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)])
+
+        # Handle "latency-ping" messages. The client will send app messages that look like
+        # this:
+        #   { "latency-ping": { ts: <client-side timestamp> }}
+        #
+        # We want to send an immediate pong back to the client from this handler function.
+        # Also, we will push a frame into the top of the pipeline and send it after the
+        #
+        @transport.event_handler("on_app_message")
+        async def on_app_message(transport, message, sender):
+            try:
+                if "latency-ping" in message:
+                    logger.debug(f"Received latency ping app message: {message}")
+                    ts = message["latency-ping"]["ts"]
+                    # Send immediately
+                    transport.output().send_message(DailyTransportMessageFrame(
+                        message={"latency-pong-msg-handler": {"ts": ts}},
+                        participant_id=sender))
+                    # And push to the pipeline for the Daily transport.output to send
+                    await tma_in.push_frame(
+                        DailyTransportMessageFrame(
+                            message={"latency-pong-pipeline-delivery": {"ts": ts}},
+                            participant_id=sender))
+            except Exception as e:
+                logger.debug(f"message handling error: {e} - {message}")
+
+        runner = PipelineRunner()
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,107 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.processors.user_idle_processor import UserIdleProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+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 = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        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.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        async def user_idle_callback(user_idle: UserIdleProcessor):
+            messages.append(
+                {"role": "system", "content": "Ask the user if they are still there and try to prompt for some input, but be short."})
+            await user_idle.queue_frame(LLMMessagesFrame(messages))
+
+        user_idle = UserIdleProcessor(callback=user_idle_callback, timeout=5.0)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            user_idle,           # Idle user check-in
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            report_only_initial_ttfb=True,
+        ))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/18-gstreamer-filesrc.py

@@ -0,0 +1,78 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import argparse
+import sys
+
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        parser = argparse.ArgumentParser(description="Daily AI SDK Bot Sample")
+        parser.add_argument(
+            "-i",
+            "--input",
+            type=str,
+            required=True,
+            help="Input video file")
+
+        (room_url, _, args) = await configure_with_args(session, parser)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "GStreamer",
+            DailyParams(
+                audio_out_enabled=True,
+                audio_out_is_live=True,
+                camera_out_enabled=True,
+                camera_out_width=1280,
+                camera_out_height=720,
+                camera_out_is_live=True,
+            )
+        )
+
+        gst = GStreamerPipelineSource(
+            pipeline=f"filesrc location={args.input}",
+            out_params=GStreamerPipelineSource.OutputParams(
+                video_width=1280,
+                video_height=720,
+                audio_sample_rate=16000,
+                audio_channels=1,
+            )
+        )
+
+        pipeline = Pipeline([
+            gst,                 # GStreamer file source
+            transport.output(),  # Transport bot output
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

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

@@ -0,0 +1,64 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import sys
+
+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)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "GStreamer",
+            DailyParams(
+                camera_out_enabled=True,
+                camera_out_width=1280,
+                camera_out_height=720,
+                camera_out_is_live=True,
+            )
+        )
+
+        gst = GStreamerPipelineSource(
+            pipeline="videotestsrc ! capsfilter caps=\"video/x-raw,width=1280,height=720,framerate=30/1\"",
+            out_params=GStreamerPipelineSource.OutputParams(
+                video_width=1280,
+                video_height=720,
+                clock_sync=False))
+
+        pipeline = Pipeline([
+            gst,                 # GStreamer file source
+            transport.output(),  # Transport bot output
+        ])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/19a-tools-anthropic.py

@@ -0,0 +1,116 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
+    location = arguments["location"]
+    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
+
+
+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 = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY"),
+            model="claude-3-5-sonnet-20240620"
+        )
+        llm.register_function("get_weather", get_weather)
+
+        tools = [
+            {
+                "name": "get_weather",
+                "description": "Get the current weather in a given location",
+                "input_schema": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        }
+                    },
+                    "required": ["location"],
+                },
+            }
+        ]
+
+        # todo: test with very short initial user message
+
+        # messages = [{"role": "system",
+        #              "content": "You are a helpful assistant who can report the weather in any location in the universe. Respond concisely. Your response will be turned into speech so use only simple words and punctuation."},
+        #             {"role": "user",
+        #              "content": " Start the conversation by introducing yourself."}]
+
+        messages = [{"role": "user", "content": "Say 'hello' to start the conversation."}]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),               # Transport user input
+            context_aggregator.user(),       # User spoken responses
+            llm,                             # LLM
+            tts,                             # TTS
+            transport.output(),              # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        @ transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            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/19b-tools-video-anthropic.py

@@ -0,0 +1,172 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+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.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+video_participant_id = None
+
+
+async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
+    location = arguments["location"]
+    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
+
+
+async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
+    question = arguments["question"]
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)
+
+
+async def main():
+    global llm
+
+    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 = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY"),
+            model="claude-3-5-sonnet-20240620",
+            enable_prompt_caching_beta=True
+        )
+        llm.register_function("get_weather", get_weather)
+        llm.register_function("get_image", get_image)
+
+        tools = [
+            {
+                "name": "get_weather",
+                "description": "Get the current weather in a given location",
+                "input_schema": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        }
+                    },
+                    "required": ["location"],
+                },
+            },
+            {
+                "name": "get_image",
+                "description": "Get an image from the video stream.",
+                "input_schema": {
+                    "type": "object",
+                    "properties": {
+                        "question": {
+                            "type": "string",
+                            "description": "The question that the user is asking about the image.",
+                        }
+                    },
+                    "required": ["question"],
+                },
+            }
+        ]
+
+        # todo: test with very short initial user message
+
+        system_prompt = """\
+You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
+
+Your response will be turned into speech so use only simple words and punctuation.
+
+You have access to two tools: get_weather and get_image.
+
+You can respond to questions about the weather using the get_weather tool.
+
+You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
+indicate you should use the get_image tool are:
+  - What do you see?
+  - What's in the video?
+  - Can you describe the video?
+  - Tell me about what you see.
+  - Tell me something interesting about what you see.
+  - What's happening in the video?
+
+If you need to use a tool, simply use the tool. Do not tell the user the tool you are using. Be brief and concise.
+        """
+
+        messages = [
+            {
+                "role": "system",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": system_prompt,
+                    }
+                ]
+            },
+            {
+                "role": "user",
+                "content": "Start the conversation by introducing yourself."
+            }]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),               # Transport user input
+            context_aggregator.user(),       # User speech to text
+            llm,                             # LLM
+            tts,                             # TTS
+            transport.output(),              # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        @ transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            global video_participant_id
+            video_participant_id = participant["id"]
+            transport.capture_participant_transcription(video_participant_id)
+            transport.capture_participant_video(video_participant_id, framerate=0)
+            # 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/19c-tools-togetherai.py

@@ -0,0 +1,165 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+import json
+
+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
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.together import TogetherLLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.vad.silero import SileroVADAnalyzer
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def get_current_weather(
+        function_name,
+        tool_call_id,
+        arguments,
+        llm,
+        context,
+        result_callback):
+    logger.debug("IN get_current_weather")
+    location = arguments["location"]
+    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
+
+
+async def save_checkpoint(
+        function_name,
+        tool_call_id,
+        arguments,
+        llm,
+        context,
+        result_callback):
+    logger.debug("IN save_checkpoint")
+    await result_callback({"status": "success"})
+
+
+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 = TogetherLLMService(
+            api_key=os.getenv("TOGETHER_API_KEY"),
+            model=os.getenv("TOGETHER_MODEL"),
+        )
+        llm.register_function("get_current_weather", get_current_weather)
+        llm.register_function("save_checkpoint", save_checkpoint)
+
+        # standard function call that's in all the LLM docs!
+        weatherTool = {
+            "name": "get_current_weather",
+            "description": "Get the current weather in a given location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA",
+                    },
+                },
+                "required": ["location"],
+            },
+        }
+
+        # a function to test function calls with no arguments
+        saveCheckpoint = {
+            "name": "save_checkpoint",
+            "description": "Save the current state of the conversation",
+            "parameters": {
+                "type": "object",
+                "properties": {},
+                "required": [],
+            },
+        }
+
+        system_prompt = f"""\
+You have access to the following functions:
+
+Use the function '{weatherTool["name"]}' to '{weatherTool["description"]}':
+{json.dumps(weatherTool)}
+
+Use the function '{saveCheckpoint["name"]}' to '{saveCheckpoint["description"]}':
+{json.dumps(saveCheckpoint)}
+
+If you choose to call a function ONLY reply in the following format with no prefix or suffix:
+
+<function=example_function_name>{{\"example_name\": \"example_value\"}}</function>
+
+Reminder:
+- Function calls MUST follow the specified format, start with <function= and end with </function>
+- Required parameters MUST be specified
+- Only call one function at a time
+- Put the entire function call reply on one line
+- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls
+
+"""
+
+        messages = [{"role": "system",
+                     "content": system_prompt},
+                    {"role": "user",
+                     "content": "Wait for the user to say something."}]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline([
+            transport.input(),               # Transport user input
+            context_aggregator.user(),       # User speech to text
+            llm,                             # LLM
+            tts,                             # TTS
+            transport.output(),              # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses and tool context
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        @ transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())