Save

Add CHANGELOG entry for PR 1525

.github/ISSUE_TEMPLATE/1-bug_report.yml

@@ -0,0 +1,87 @@
+name: Bug report
+description: Report a bug or unexpected behavior
+type: Bug
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Bug Report
+
+        Thank you for taking the time to fill out this bug report.
+
+  - type: markdown
+    attributes:
+      value: |
+        ### Environment
+
+  - type: input
+    id: pipecat-version
+    attributes:
+      label: pipecat version
+      description: Which version are you using?
+      placeholder: e.g., 0.0.63
+    validations:
+      required: true
+
+  - type: input
+    id: python-version
+    attributes:
+      label: Python version
+      description: Which Python version are you using?
+      placeholder: e.g., 3.12.8
+    validations:
+      required: true
+
+  - type: input
+    id: os
+    attributes:
+      label: Operating System
+      description: Which OS are you using?
+      placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
+    validations:
+      required: true
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Issue description
+      description: Provide a clear description of the issue.
+    validations:
+      required: true
+
+  - type: textarea
+    id: repro
+    attributes:
+      label: Reproduction steps
+      description: List the steps to reproduce the issue.
+      placeholder: |
+        1. Do this...
+        2. Then do that...
+        3. Observe the error...
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected behavior
+      description: What did you expect to happen?
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual behavior
+      description: What actually happened?
+    validations:
+      required: true
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Logs
+      description: If applicable, include any relevant logs or error messages
+      render: shell
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/2-question.yml

@@ -0,0 +1,67 @@
+name: Question
+description: Ask a question or get help
+type: Question
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Question
+
+        Use this form to ask a question about pipecat.
+
+  - type: markdown
+    attributes:
+      value: |
+        ### Environment (if applicable)
+
+  - type: input
+    id: pipecat-version
+    attributes:
+      label: pipecat version
+      description: Which version are you using? (if applicable)
+      placeholder: e.g., 0.0.63
+    validations:
+      required: false
+
+  - type: input
+    id: python-version
+    attributes:
+      label: Python version
+      description: Which Python version are you using? (if applicable)
+      placeholder: e.g., 3.12.8
+    validations:
+      required: false
+
+  - type: input
+    id: os
+    attributes:
+      label: Operating System
+      description: Which OS are you using? (if applicable)
+      placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
+    validations:
+      required: false
+
+  - type: textarea
+    id: question
+    attributes:
+      label: Question
+      description: Provide your question in detail here.
+    validations:
+      required: true
+
+  - type: textarea
+    id: tried
+    attributes:
+      label: What I've tried
+      description: Describe what you've already tried or research you've done.
+      placeholder: I've looked at the documentation and tried...
+    validations:
+      required: false
+
+  - type: textarea
+    id: context
+    attributes:
+      label: Context
+      description: Any additional context or information that might help others understand your question better.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/3-feature_request.yml

@@ -0,0 +1,52 @@
+name: Feature request
+description: Suggest an enhancement or new feature
+type: Enhancement
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Feature Request
+
+        Thank you for suggesting an enhancement to pipecat.
+
+  - type: textarea
+    id: problem
+    attributes:
+      label: Problem Statement
+      description: A clear description of the problem this feature would solve.
+      placeholder: I'm always frustrated when...
+    validations:
+      required: true
+
+  - type: textarea
+    id: solution
+    attributes:
+      label: Proposed Solution
+      description: A clear and concise description of what you want to happen.
+    validations:
+      required: true
+
+  - type: textarea
+    id: alternatives
+    attributes:
+      label: Alternative Solutions
+      description: Any alternative solutions or features you've considered.
+    validations:
+      required: false
+
+  - type: textarea
+    id: context
+    attributes:
+      label: Additional Context
+      description: Add any other context, mockups, or screenshots about the feature request here.
+      placeholder: You can drag and drop images here to include them.
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: contribution
+    attributes:
+      label: Would you be willing to help implement this feature?
+      options:
+        - label: Yes, I'd like to contribute
+        - label: No, I'm just suggesting

.github/ISSUE_TEMPLATE/4-service-issue.yml

@@ -0,0 +1,82 @@
+name: Service Issue
+description: An issue with a third-party service
+type: Service Issue
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Service Issue
+
+        Use this form to report an issue with a third-party service integration.
+
+  - type: input
+    id: pipecat-version
+    attributes:
+      label: pipecat version
+      description: Which version are you using?
+      placeholder: e.g., 0.0.63
+    validations:
+      required: true
+
+  - type: input
+    id: service-name
+    attributes:
+      label: Service Name
+      description: Which third-party service is having issues?
+      placeholder: e.g., OpenAI, ElevenLabs, Anthropic
+    validations:
+      required: true
+
+  - type: input
+    id: service-version
+    attributes:
+      label: Service or model version
+      description: Which version of the service API or model are you using?
+      placeholder: e.g., v1, gpt-4.1
+    validations:
+      required: false
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Issue Description
+      description: Provide a clear description of the service issue.
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Reproduction Steps
+      description: Provide steps to reproduce the issue.
+      placeholder: |
+        1. Configure service X
+        2. Call method Y
+        3. See error Z
+    validations:
+      required: true
+
+  - type: textarea
+    id: expected
+    attributes:
+      label: Expected Behavior
+      description: What did you expect to happen?
+    validations:
+      required: true
+
+  - type: textarea
+    id: actual
+    attributes:
+      label: Actual Behavior
+      description: What actually happened?
+    validations:
+      required: true
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Error Logs
+      description: If available, include any error messages or logs.
+      render: shell
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/5-new-service.yml

@@ -0,0 +1,56 @@
+name: New Service
+description: Request to support a new third-party service
+type: New Service
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## New Service Request
+
+        Use this form to request support for a new third-party service in pipecat.
+
+  - type: input
+    id: service-name
+    attributes:
+      label: Service Name
+      description: What is the name of the third-party service?
+      placeholder: e.g., NewAPI, SomeService
+    validations:
+      required: true
+
+  - type: input
+    id: service-website
+    attributes:
+      label: Service Website
+      description: Link to the service's website or documentation
+      placeholder: e.g., https://newapi.com
+    validations:
+      required: true
+
+  - type: textarea
+    id: service-description
+    attributes:
+      label: Service Description
+      description: Briefly describe what this service does and how it works.
+    validations:
+      required: true
+
+  - type: textarea
+    id: api-info
+    attributes:
+      label: API Information
+      description: If available, provide details about the service's API.
+      placeholder: |
+        - API documentation link
+        - Authentication method
+        - Key endpoints you'd like supported
+    validations:
+      required: false
+
+  - type: checkboxes
+    id: contribution
+    attributes:
+      label: Would you be willing to help implement this service?
+      options:
+        - label: Yes, I'd like to contribute
+        - label: No, I'm just suggesting

.github/ISSUE_TEMPLATE/6-dependency.yml

@@ -0,0 +1,74 @@
+name: Dependency Issue
+description: An issue with a Pipecat dependency (not a third-party service)
+type: Dependency Issue
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Dependency Issue
+
+        Use this form to report an issue with a Pipecat dependency.
+
+  - type: input
+    id: pipecat-version
+    attributes:
+      label: pipecat version
+      description: Which version are you using?
+      placeholder: e.g., 0.0.63
+    validations:
+      required: true
+
+  - type: input
+    id: dependency-name
+    attributes:
+      label: Dependency Name
+      description: Which Pipecat dependency is causing the issue?
+      placeholder: e.g., openai, anthropic, fastapi
+    validations:
+      required: true
+
+  - type: input
+    id: dependency-version
+    attributes:
+      label: Dependency Version
+      description: Which version of the dependency are you using?
+      placeholder: e.g., 1.2.3
+    validations:
+      required: true
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Issue Description
+      description: Provide a clear description of the dependency issue.
+    validations:
+      required: true
+
+  - type: textarea
+    id: impact
+    attributes:
+      label: Impact
+      description: How is this dependency issue affecting your usage of pipecat?
+    validations:
+      required: true
+
+  - type: textarea
+    id: reproduction
+    attributes:
+      label: Reproduction Steps
+      description: If applicable, provide steps to reproduce the issue.
+      placeholder: |
+        1. Install dependency X
+        2. Run command Y
+        3. See error Z
+    validations:
+      required: false
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Error Logs
+      description: If applicable, include any relevant error messages or logs.
+      render: shell
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/7-troubleshooting.yml

@@ -0,0 +1,70 @@
+name: Troubleshooting
+description: Help with a specific use case
+type: Troubleshooting
+body:
+  - type: markdown
+    attributes:
+      value: |
+        ## Troubleshooting Request
+
+        Use this form to get help with a specific use case or implementation.
+
+  - type: input
+    id: pipecat-version
+    attributes:
+      label: pipecat version
+      description: Which version are you using?
+      placeholder: e.g., 0.0.63
+    validations:
+      required: true
+
+  - type: input
+    id: python-version
+    attributes:
+      label: Python version
+      description: Which version of Python are you using?
+      placeholder: e.g., 3.12.8
+    validations:
+      required: true
+
+  - type: input
+    id: os
+    attributes:
+      label: Operating System
+      description: Which OS are you using?
+      placeholder: e.g., Ubuntu 24.04, Windows 11, macOS 12.5
+    validations:
+      required: true
+
+  - type: textarea
+    id: use-case
+    attributes:
+      label: Use Case Description
+      description: Describe what you're trying to accomplish with pipecat.
+    validations:
+      required: true
+
+  - type: textarea
+    id: current-approach
+    attributes:
+      label: Current Approach
+      description: What have you tried so far? Include code snippets if relevant.
+      render: python
+    validations:
+      required: true
+
+  - type: textarea
+    id: errors
+    attributes:
+      label: Errors or Unexpected Behavior
+      description: Describe any errors or unexpected behavior you're encountering.
+    validations:
+      required: true
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Any other information that might help us understand your situation.
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1 @@
+blank_issues_enabled: false

CHANGELOG.md

@@ -9,6 +9,157 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added support for Application Default Credentials in Google services,
+  `GoogleSTTService`, `GoogleTTSService`, and `GoogleVertexLLMService`.
+
+- Added support for Smart Turn Detection via the `turn_analyzer` transport
+  parameter. You can now choose between `SmartTurnAnalyzer()` for remote
+  inference or `LocalCoreMLSmartTurnAnalyzer()` for on-device inference using
+  Core ML.
+
+- `DeepgramTTSService` accepts `base_url` argument again, allowing you to
+  connect to an on-prem service.
+
+- Added `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` which allow
+  you to control aggregator settings. You can now pass these arguments when
+  creating aggregator pairs with `create_context_aggregator()`.
+
+- Added `previous_text` context support to ElevenLabsHttpTTSService, improving
+  speech consistency across sentences within an LLM response.
+
+- Added word/timestamp pairs to `ElevenLabsHttpTTSService`.
+
+- It is now possible to disable `SoundfileMixer` when created. You can then use
+  `MixerEnableFrame` to dynamically enable it when necessary.
+
+- Added `on_client_connected` and `on_client_disconnected` event handlers to
+  the `DailyTransport` class. These handlers map to the same underlying Daily
+  events as `on_participant_joined` and `on_participant_left`, respectively.
+  This makes it easier to write a single bot pipeline that can also use other
+  transports like `SmallWebRTCTransport` and `FastAPIWebsocketTransport`.
+
+### Changed
+
+- Daily's REST helpers now include an `eject_at_token_exp` param, which ejects
+  the user when their token expires. This new parameter defaults to False.
+  Also, the default value for `enable_prejoin_ui` changed to False and
+  `eject_at_room_exp` changed to False.
+
+- `OpenAILLMService` and `OpenPipeLLMService` now use `gpt-4.1` as their
+  default model.
+
+- `SoundfileMixer` constructor arguments need to be keywords.
+
+### Deprecated
+
+- `DeepgramSTTService` parameter `url` is now deprecated, use `base_url`
+  instead.
+
+### Removed
+
+- Parameters `user_kwargs` and `assistant_kwargs` when creating a context
+  aggregator pair using `create_context_aggregator()` have been removed. Use
+  `user_params` and `assistant_params` instead.
+
+### Fixed
+
+- Fixed an issue that would cause TTS websocket-based services to not cleanup
+  resources properly when disconnecting.
+
+- Fixed a `TavusVideoService` issue that was causing audio choppiness.
+
+- Fixed an issue in `SmallWebRTCTransport` where an error was thrown if the
+  client did not create a video transceiver.
+
+- Fixed an issue where LLM input parameters were not working and applied correctly in `GoogleVertexLLMService`, causing
+  unexpected behavior during inference.
+
+## [0.0.63] - 2025-04-11
+
+### Added
+
+- Added media resolution control to `GeminiMultimodalLiveLLMService` with
+  `GeminiMediaResolution` enum, allowing configuration of token usage for
+  image processing (LOW: 64 tokens, MEDIUM: 256 tokens, HIGH: zoomed reframing
+  with 256 tokens).
+
+- Added Gemini's Voice Activity Detection (VAD) configuration to
+  `GeminiMultimodalLiveLLMService` with `GeminiVADParams`, allowing fine
+  control over speech detection sensitivity and timing, including:
+
+  - Start sensitivity (how quickly speech is detected)
+  - End sensitivity (how quickly turns end after pauses)
+  - Prefix padding (milliseconds of audio to keep before speech is detected)
+  - Silence duration (milliseconds of silence required to end a turn)
+
+- Added comprehensive language support to `GeminiMultimodalLiveLLMService`,
+  supporting over 30 languages via the `language` parameter, with proper
+  mapping between Pipecat's `Language` enum and Gemini's language codes.
+
+- Added support in `SmallWebRTCTransport` to detect when remote tracks are
+  muted.
+
+- Added support for image capture from a video stream to the
+  `SmallWebRTCTransport`.
+
+- Added a new iOS client option to the `SmallWebRTCTransport`
+  **video-transform** example.
+
+- Added new processors `ProducerProcessor` and `ConsumerProcessor`. The
+  producer processor processes frames from the pipeline and decides whether the
+  consumers should consume it or not. If so, the same frame that is received by
+  the producer is sent to the consumer. There can be multiple consumers per
+  producer. These processors can be useful to push frames from one part of a
+  pipeline to a different one (e.g. when using `ParallelPipeline`).
+
+- Improvements for the `SmallWebRTCTransport`:
+  - Wait until the pipeline is ready before triggering the `connected` event.
+  - Queue messages if the data channel is not ready.
+  - Update the aiortc dependency to fix an issue where the 'video/rtx' MIME
+    type was incorrectly handled as a codec retransmission.
+  - Avoid initial video delays.
+
+### Changed
+
+- In `GeminiMultimodalLiveLLMService`, removed the `transcribe_model_audio`
+  parameter in favor of Gemini Live's native output transcription support. Now
+  text transcriptions are produced directly by the model. No configuration is
+  required.
+
+- Updated `GeminiMultimodalLiveLLMService`’s default `model` to
+  `models/gemini-2.0-flash-live-001` and `base_url` to the `v1beta` websocket
+  URL.
+
+### Fixed
+
+- Updated `daily-python` to 0.17.0 to fix an issue that was preventing to run on
+  older platforms.
+
+- Fixed an issue where `CartesiaTTSService`'s spell feature would result in
+  the spelled word in the context appearing as "F,O,O,B,A,R" instead of
+  "FOOBAR".
+
+- Fixed an issue in the Azure TTS services where the language was being set
+  incorrectly.
+
+- Fixed `SmallWebRTCTransport` to support dynamic values for
+  `TransportParams.audio_out_10ms_chunks`. Previously, it only worked with 20ms
+  chunks.
+
+- Fixed an issue with `GeminiMultimodalLiveLLMService` where the assistant
+  context messages had no space between words.
+
+- Fixed an issue where `LLMAssistantContextAggregator` would prevent a
+  `BotStoppedSpeakingFrame` from moving through the pipeline.
+
+## [0.0.62] - 2025-04-01 "An April Fools' release"
+
+### Added
+
+- Added `TransportParams.audio_out_10ms_chunks` parameter to allow controlling
+  the amount of audio being sent by the output transport. It defaults to 4, so
+  40ms audio chunks are sent.
+
 - Added `QwenLLMService` for Qwen integration with an OpenAI-compatible
   interface. Added foundational example `14q-function-calling-qwen.py`.
 
@@ -53,6 +204,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- `FunctionCallResultFrame`a are now system frames. This is to prevent function
+  call results to be discarded during interruptions.
+
 - Pipecat services have been reorganized into packages. Each package can have
   one or more of the following modules (in the future new module names might be
   needed) depending on the services implemented:
@@ -65,15 +219,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - video: for video generation services
   - vision: for video recognition services
 
-- `GladiaSTTService` now uses Gladia's default values.
+- Base classes for AI services have been reorganized into modules. They can now
+  be found in
+  `pipecat.services.[ai_service,image_service,llm_service,stt_service,vision_service]`.
 
-### Fixed
-
-- Fixed an issue that would cause `SegmentedSTTService` based services
-  (e.g. `OpenAISTTService`) to try to transcribe non-spoken audio, causing
-  invalid transcriptions.
-
-- Fixed an issue where `GoogleTTSService` was emitting two `TTSStoppedFrames`.
+- `GladiaSTTService` now uses the `solaria-1` model by default. Other params
+  use Gladia's default values. Added support for more language codes.
 
 ### Deprecated
 
@@ -82,12 +233,41 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `pipecat.services.[service].[image,llm,memory,stt,tts,video,vision]`. For
   example, `from pipecat.services.openai.llm import OpenAILLMService`.
 
+- Import for AI services base classes from `pipecat.services.ai_services` is now
+  deprecated, use one of
+  `pipecat.services.[ai_service,image_service,llm_service,stt_service,vision_service]`.
+
 - Deprecated the `language` parameter in `GladiaSTTService.InputParams` in
   favor of `language_config`, which better aligns with Gladia's API.
 
 - Deprecated using `GladiaSTTService.InputParams` directly. Use the new
   `GladiaInputParams` class instead.
 
+### Fixed
+
+- Fixed a `FastAPIWebsocketTransport` and `WebsocketClientTransport` issue that
+  would cause the transport to be closed prematurely, preventing the internally
+  queued audio to be sent. The same issue could also cause an infinite loop
+  while using an output mixer and when sending an `EndFrame`, preventing the bot
+  to finish.
+
+- Fixed an issue that could cause the `TranscriptionUpdateFrame` being pushed
+  because of an interruption to be discarded.
+
+- Fixed an issue that would cause `SegmentedSTTService` based services
+  (e.g. `OpenAISTTService`) to try to transcribe non-spoken audio, causing
+  invalid transcriptions.
+
+- Fixed an issue where `GoogleTTSService` was emitting two `TTSStoppedFrames`.
+
+### Performance
+
+- Output transports now send 40ms audio chunks instead of 20ms. This should
+  improve performance.
+
+- `BotSpeakingFrame`s are now sent every 200ms. If the output transport audio chunks
+  are higher than 200ms then they will be sent at every audio chunk.
+
 ### Other
 
 - Added foundational example `37-mem0.py` demonstrating how to use the

CONTRIBUTING.md

@@ -26,11 +26,52 @@ git commit -m "Description of your changes"
 git push origin your-branch-name
 ```
 
-9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo. 
-> Important: Describe the changes you've made clearly!
+8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
+   > Important: Describe the changes you've made clearly!
 
 Our maintainers will review your PR, and once everything is good, your contributions will be merged!
 
+## Code Style and Documentation
+
+### Python Code Style
+
+We use Ruff for code linting and formatting. Please ensure your code passes all linting checks before submitting a PR.
+
+### Docstring Conventions
+
+We follow Google-style docstrings with these specific conventions:
+
+- Class docstrings should fully document all parameters used in `__init__`
+- We don't require separate docstrings for `__init__` methods when parameters are documented in the class docstring
+- Property methods should have docstrings explaining their purpose and return value
+
+Example of correctly documented class:
+
+```python
+class MyClass:
+    """Class description.
+
+    Additional details about the class.
+
+    Args:
+        param1: Description of first parameter.
+        param2: Description of second parameter.
+    """
+
+    def __init__(self, param1, param2):
+        # No docstring required here as parameters are documented above
+        self.param1 = param1
+        self.param2 = param2
+
+    @property
+    def some_property(self) -> str:
+        """Get the formatted property value.
+
+        Returns:
+            A string representation of the property.
+        """
+        return f"Property: {self.param1}"
+```
 
 # Contributor Covenant Code of Conduct
 
@@ -51,23 +92,23 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
   and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the overall
+- Focusing on what is best not just for us as individuals, but for the overall
   community
 
 Examples of unacceptable behavior include:
 
-* The use of sexualized language or imagery, and sexual attention or advances of
+- The use of sexualized language or imagery, and sexual attention or advances of
   any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email address,
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email address,
   without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
+- Other conduct which could reasonably be considered inappropriate in a
   professional setting
 
 ## Enforcement Responsibilities
@@ -162,4 +203,4 @@ For answers to common questions about this code of conduct, see the FAQ at
 [v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
 [Mozilla CoC]: https://github.com/mozilla/diversity
 [FAQ]: https://www.contributor-covenant.org/faq
-[translations]: https://www.contributor-covenant.org/translations
+[translations]: https://www.contributor-covenant.org/translations

README.md

@@ -1,43 +1,72 @@
 <h1><div align="center">
- <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
+ <img alt="pipecat" width="300px" height="auto" src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/pipecat.png">
 </div></h1>
 
 [![PyPI](https://img.shields.io/pypi/v/pipecat-ai)](https://pypi.org/project/pipecat-ai) ![Tests](https://github.com/pipecat-ai/pipecat/actions/workflows/tests.yaml/badge.svg) [![codecov](https://codecov.io/gh/pipecat-ai/pipecat/graph/badge.svg?token=LNVUIVO4Y9)](https://codecov.io/gh/pipecat-ai/pipecat) [![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.ai) [![Discord](https://img.shields.io/discord/1239284677165056021)](https://discord.gg/pipecat)
 
-Pipecat is an open source Python framework for building voice and multimodal conversational agents. It handles the complex orchestration of AI services, network transport, audio processing, and multimodal interactions, letting you focus on creating engaging experiences.
+# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
 
-## What you can build
+**Pipecat** is an open-source Python framework for building real-time voice and multimodal conversational agents. Orchestrate audio and video, AI services, different transports, and conversation pipelines effortlessly—so you can focus on what makes your agent unique.
 
-- **Voice Assistants**: [Natural, real-time conversations with AI](https://demo.dailybots.ai/)
-- **Interactive Agents**: Personal coaches and meeting assistants
-- **Multimodal Apps**: Combine voice, video, images, and text
-- **Creative Tools**: [Story-telling experiences](https://storytelling-chatbot.fly.dev/) and social companions
-- **Business Solutions**: [Customer intake flows](https://www.youtube.com/watch?v=lDevgsp9vn0) and support bots
-- **Complex conversational flows**: [Refer to Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) to learn more
+## 🚀 What You Can Build
 
-## See it in action
+- **Voice Assistants** – natural, streaming conversations with AI
+- **AI Companions** – coaches, meeting assistants, characters
+- **Multimodal Interfaces** – voice, video, images, and more
+- **Interactive Storytelling** – creative tools with generative media
+- **Business Agents** – customer intake, support bots, guided flows
+- **Complex Dialog Systems** – design logic with structured conversations
+
+🧭 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
+
+## 🧠 Why Pipecat?
+
+- **Voice-first**: Integrates speech recognition, text-to-speech, and conversation handling
+- **Pluggable**: Supports many AI services and tools
+- **Composable Pipelines**: Build complex behavior from modular components
+- **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
+
+## 🎬 See it in action
 
 <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>
+    <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="400" /></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="400" /></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>
+    <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="400" /></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="400" /></a>
 </p>
 
-## Key features
+## 📱 Client SDKs
 
-- **Voice-first Design**: Built-in speech recognition, TTS, and conversation handling
-- **Flexible Integration**: Works with popular AI services (OpenAI, ElevenLabs, etc.)
-- **Pipeline Architecture**: Build complex apps from simple, reusable components
-- **Real-time Processing**: Frame-based pipeline architecture for fluid interactions
-- **Production Ready**: Enterprise-grade WebRTC and Websocket support
+You can connect to Pipecat from any platform using our official SDKs:
 
-💡 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
+| Platform | SDK Repo                                                                       | Description                      |
+| -------- | ------------------------------------------------------------------------------ | -------------------------------- |
+| Web      | [pipecat-client-web](https://github.com/pipecat-ai/pipecat-client-web)         | JavaScript and React client SDKs |
+| iOS      | [pipecat-client-ios](https://github.com/pipecat-ai/pipecat-client-ios)         | Swift SDK for iOS                |
+| Android  | [pipecat-client-android](https://github.com/pipecat-ai/pipecat-client-android) | Kotlin SDK for Android           |
+| C++      | [pipecat-client-cxx](https://github.com/pipecat-ai/pipecat-client-cxx)         | C++ client SDK                   |
 
-## Getting started
+## 🧩 Available services
 
-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.
+| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                            |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
+| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                       |
+| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+
+📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
+
+## ⚡ Getting started
+
+You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready.
 
 ```shell
 # Install the module
@@ -53,141 +82,51 @@ To keep things lightweight, only the core framework is included by default. If y
 pip install "pipecat-ai[option,...]"
 ```
 
-### Available services
-
-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | Install Command Example                 |
-| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [Parakeet (NVIDIA)](https://docs.pipecat.ai/server/services/stt/parakeet), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                            | `pip install "pipecat-ai[deepgram]"`    |
-| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
-| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [FastPitch (NVIDIA)](https://docs.pipecat.ai/server/services/tts/fastpitch), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                       | `pip install "pipecat-ai[cartesia]"`    |
-| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               | `pip install "pipecat-ai[google]"`      |
-| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | `pip install "pipecat-ai[daily]"`       |
-| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        | `pip install "pipecat-ai[tavus,simli]"` |
-| Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | `pip install "pipecat-ai[mem0]"`        |
-| Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[moondream]"`   |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    | `pip install "pipecat-ai[silero]"`      |
-| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   | `pip install "pipecat-ai[canonical]"`   |
-
-📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
-
-## Code examples
+## 🧪 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
+## 🛠️ Hacking on the framework itself
 
-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.
+1. Set up a virtual environment before following these instructions. From the root of the repo:
 
-```python
-import asyncio
+   ```shell
+   python3 -m venv venv
+   source venv/bin/activate
+   ```
 
-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
+2. Install the development dependencies:
 
-async def main():
-  # Use Daily as a real-time media transport (WebRTC)
-  transport = DailyTransport(
-    room_url=...,
-    token="", # leave empty. Note: token is _not_ your api key
-    bot_name="Bot Name",
-    params=DailyParams(audio_out_enabled=True))
+   ```shell
+   pip install -r dev-requirements.txt
+   ```
 
-  # Use Cartesia for Text-to-Speech
-  tts = CartesiaTTSService(
-    api_key=...,
-    voice_id=...
-  )
+3. Install the git pre-commit hooks (these help ensure your code follows project rules):
 
-  # Simple pipeline that will process text to speech and output the result
-  pipeline = Pipeline([tts, transport.output()])
+   ```shell
+   pre-commit install
+   ```
 
-  # Create Pipecat processor that can run one or more pipelines tasks
-  runner = PipelineRunner()
+4. Install the `pipecat-ai` package locally in editable mode:
 
-  # Assign the task callable to run the pipeline
-  task = PipelineTask(pipeline)
+   ```shell
+   pip install -e .
+   ```
 
-  # Register an event handler to play audio when a
-  # participant joins the transport WebRTC session
-  @transport.event_handler("on_first_participant_joined")
-  async def on_first_participant_joined(transport, participant):
-    participant_name = participant.get("info", {}).get("userName", "")
-    # Queue a TextFrame that will get spoken by the TTS service (Cartesia)
-    await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
+   > The `-e` or `--editable` option allows you to modify the code without reinstalling.
 
-  # Register an event handler to exit the application when the user leaves.
-  @transport.event_handler("on_participant_left")
-  async def on_participant_left(transport, participant, reason):
-    await task.cancel()
+5. Include optional dependencies as needed. For example:
 
-  # Run the pipeline task
-  await runner.run(task)
+   ```shell
+   pip install -e ".[daily,deepgram,cartesia,openai,silero]"
+   ```
 
-if __name__ == "__main__":
-  asyncio.run(main())
-```
+6. (Optional) If you want to use this package from another directory:
 
-Run it with:
-
-```shell
-python app.py
-```
-
-Daily provides a prebuilt WebRTC user interface. While 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.
-
-## Hacking on the framework itself
-
-_Note: You may need to set up a virtual environment before following these instructions. From the root of the repo:_
-
-```shell
-python3 -m venv venv
-source venv/bin/activate
-```
-
-Install the development dependencies:
-
-```shell
-pip install -r dev-requirements.txt
-```
-
-Install the git pre-commit hooks (these help ensure your code follows project rules):
-
-```shell
-pre-commit install
-```
-
-Install the `pipecat-ai` package locally in editable mode:
-
-```shell
-pip install -e .
-```
-
-The `-e` or `--editable` option allows you to modify the code without reinstalling.
-
-To include optional dependencies, add them to the install command. For example:
-
-```shell
-pip install -e ".[daily,deepgram,cartesia,openai,silero]"     # Updated for the services you're using
-```
-
-If you want to use this package from another directory:
-
-```shell
-pip install "path_to_this_repo[option,...]"
-```
+   ```shell
+   pip install "path_to_this_repo[option,...]"
+   ```
 
 ### Running tests
 
@@ -197,11 +136,11 @@ From the root directory, run:
 pytest
 ```
 
-## Setting up your editor
+### Setting up your editor
 
 This project uses strict [PEP 8](https://peps.python.org/pep-0008/) formatting via [Ruff](https://github.com/astral-sh/ruff).
 
-### Emacs
+#### Emacs
 
 You can use [use-package](https://github.com/jwiegley/use-package) to install [emacs-lazy-ruff](https://github.com/christophermadsen/emacs-lazy-ruff) package and configure `ruff` arguments:
 
@@ -223,7 +162,7 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :hook ((python-mode . pyvenv-auto-run)))
 ```
 
-### Visual Studio Code
+#### Visual Studio Code
 
 Install the
 [Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, and enable formatting on save:
@@ -235,7 +174,7 @@ Install the
 }
 ```
 
-### PyCharm
+#### PyCharm
 
 `ruff` was installed in the `venv` environment described before, now to enable autoformatting on save, go to `File` -> `Settings` -> `Tools` -> `File Watchers` and add a new watcher with the following settings:
 
@@ -245,7 +184,7 @@ Install the
 4. **Arguments**: `format $FilePath$`
 5. **Program**: `$PyInterpreterDirectory$/ruff`
 
-## Contributing
+## 🤝 Contributing
 
 We welcome contributions from the community! Whether you're fixing bugs, improving documentation, or adding new features, here's how you can help:
 
@@ -258,7 +197,7 @@ Before submitting a pull request, please check existing issues and PRs to avoid
 
 We aim to review all contributions promptly and provide constructive feedback to help get your changes merged.
 
-## Getting help
+## 🛟 Getting help
 
 ➡️ [Join our Discord](https://discord.gg/pipecat)
 

docs/ISSUE_TEMPLATE.md

@@ -1,22 +0,0 @@
-# Description
-Is this reporting a bug or feature request?
-
-
-If reporting a bug, please fill out the following:
-
-### Environment
-- pipecat-ai version:
-- python version:
-- OS:
-
-### Issue description
-Provide a clear description of the issue.
-
-### Repro steps
-List the steps to reproduce the issue.
-
-### Expected behavior
-
-### Actual behavior
-
-### Logs

docs/api/index.rst

@@ -45,8 +45,10 @@ Transport & Serialization
 Utilities
 ~~~~~~~~~
 
+* :mod:`Adapters <pipecat.adapters>`
 * :mod:`Clocks <pipecat.clocks>`
 * :mod:`Metrics <pipecat.metrics>`
+* :mod:`Observers <pipecat.observers>`
 * :mod:`Sync <pipecat.sync>`
 * :mod:`Transcriptions <pipecat.transcriptions>`
 * :mod:`Utils <pipecat.utils>`
@@ -56,10 +58,12 @@ Utilities
    :caption: API Reference
    :hidden:
 
+   Adapters <api/pipecat.adapters>
    Audio <api/pipecat.audio>
    Clocks <api/pipecat.clocks>
    Frames <api/pipecat.frames>
    Metrics <api/pipecat.metrics>
+   Observers <api/pipecat.observers>
    Pipeline <api/pipecat.pipeline>
    Processors <api/pipecat.processors>
    Serializers <api/pipecat.serializers>

dot-env.template

@@ -92,4 +92,8 @@ ASSEMBLYAI_API_KEY=...
 OPENROUTER_API_KEY=...
 
 # Piper
-PIPER_BASE_URL=...
+PIPER_BASE_URL=...
+
+# Smart turn
+LOCAL_SMART_TURN_MODEL_PATH=
+REMOTE_SMART_TURN_URL=

examples/canonical-metrics/bot.py

@@ -72,7 +72,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/chatbot-audio-recording/bot.py

@@ -95,7 +95,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {

examples/deployment/flyio-example/bot.py

@@ -53,7 +53,7 @@ async def main(room_url: str, token: str):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/deployment/modal-example/bot.py

@@ -43,7 +43,7 @@ async def main(room_url: str, token: str):
         api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/deployment/pipecat-cloud-daily-pstn-server/README.md

@@ -0,0 +1,178 @@
+# Handling PSTN/SIP Dial-in on Pipecat Cloud
+
+This repository contains two server implementations for handling
+the pinless dial-in workflow in Pipecat Cloud. This is the companion to the
+Pipecat Cloud [pstn_sip starter image](https://github.com/daily-co/pipecat-cloud-images/tree/main/pipecat-starters/pstn_sip).
+In addition you can use `/api/dial` to trigger dial-out, and
+eventually, call-transfers.
+
+1. [FastAPI Server](fastapi-webhook-server/README.md) -
+   A FastAPI implementation that handles PSTN (Public Switched Telephone
+   Network) and SIP (Session Initiation Protocol) calls using the Daily API.
+
+2. [Next.js Serverless](nextjs-webhook-server/README.md) -
+   A Next.js API implementation designed for deployment on Vercel's
+   serverless platform.
+
+Both implementations provide:
+
+- HMAC signature validation for pinless webhook
+- Structured logging
+- Support for dial-in and dial-out settings
+- Voicemail detection and call transfer functionality (coming soon)
+- Test request handling
+
+## Choosing an Implementation
+
+- Use the **FastAPI Server** if you:
+
+  - Need a standalone server
+  - Prefer Python and FastAPI
+  - Want to deploy to traditional hosting platforms
+
+- Use the **Next.js Serverless** implementation if you:
+  - Want serverless deployment
+  - Prefer JavaScript/TypeScript
+  - Already use Next.js and Vercel for other projects
+  - Need quick scaling and zero maintenance
+
+## Prerequisites
+
+### Environment Variables
+
+Both implementations require similar environment variables:
+
+- `PIPECAT_CLOUD_API_KEY`: Pipecat Cloud API Key, begins with pk\_\*
+- `AGENT_NAME`: Your Daily agent name
+- `PINLESS_HMAC_SECRET`: Your HMAC secret for request verification
+- `LOG_LEVEL`: (Optional) Logging level (defaults to 'info')
+
+See the individual README files in each implementation directory for
+specific setup instructions.
+
+### Phone number setup
+
+You can buy a phone number through the Pipecat Cloud Dashboard:
+
+1. Go to `Settings` > `Telephony`
+2. Follow the UI to purchase a phone number
+3. Configure the webhook URL to receive incoming calls (e.g. `https://my-webhook-url.com/api/dial`)
+
+Or purchase the number using Daily's
+[PhoneNumbers API](https://docs.daily.co/reference/rest-api/phone-numbers).
+
+```bash
+curl --request POST \
+--url https://api.daily.co/v1/domain-dialin-config \
+--header 'Authorization: Bearer $TOKEN' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+	"type": "pinless_dialin",
+	"name_prefix": "Customer1",
+    "phone_number": "+1PURCHASED_NUM",
+	"room_creation_api": "https://example.com/api/dial",
+    "hold_music_url": "https://example.com/static/ringtone.mp3",
+	"timeout_config": {
+		"message": "No agent is available right now"
+	}
+}'
+```
+
+The API will return a static SIP URI (`sip_uri`) that can be called
+from other SIP services.
+
+### `room_creation_api`
+
+To make and receive calls currently you have to host a server that
+handles incoming calls. In the coming weeks, incoming calls will be
+directly handled within Daily and we will expose an endpoint similar
+to `{service}/start` that will manage this for you.
+
+In the meantime, the server described below serves as the webhook
+handler for the `room_creation_api`. Configure your pinless phone
+number or SIP interconnect to the `ngrok` tunnel or
+the actual server URL, append `/api/dial` to the webhook URL.
+
+## Example curl commands
+
+Note: Replace `http://localhost:3000` with your actual server URL and
+phone numbers with valid values for your use case.
+
+### Dialin Request
+
+The server will receive a request when a call is received from Daily.
+
+### Dialout Request
+
+Dial a number, will use any purchased number
+
+```bash
+curl -X POST http://localhost:3000/api/dial \
+  -H "Content-Type: application/json" \
+  -d '{
+    "dialout_settings": [
+      {
+        "phoneNumber": "+1234567890",
+      }
+    ]
+  }'
+```
+
+Dial a number with callerId, which is the UUID of a purchased number.
+
+```bash
+curl -X POST http://localhost:3000/api/dial \
+  -H "Content-Type: application/json" \
+  -d '{
+    "dialout_settings": [
+      {
+        "phoneNumber": "+1234567890",
+        "callerId": "purchased_phone_uuid"
+      }
+    ]
+  }'
+```
+
+Dial a number
+
+```bash
+curl -X POST http://localhost:3000/api/dial \
+  -H "Content-Type: application/json" \
+  -d '{
+    "dialout_settings": [
+      {
+        "phoneNumber": "+1234567890",
+        "callerId": "purchased_phone_uuid"
+      }
+    ]
+  }'
+```
+
+### Advanced Request with Voicemail Detection
+
+```bash
+curl -X POST http://localhost:3000/api/dial \
+  -H "Content-Type: application/json" \
+  -d '{
+    "To": "+1234567890",
+    "From": "+1987654321",
+    "callId": "call-uuid-123",
+    "callDomain": "domain-uuid-456",
+    "dialout_settings": [
+      {
+        "phoneNumber": "+1234567890",
+        "callerId": "purchased_phone_uuid"
+      }
+    ],
+    "voicemail_detection": {
+      "testInPrebuilt": true
+    },
+    "call_transfer": {
+      "mode": "dialout",
+      "speakSummary": true,
+      "storeSummary": true,
+      "operatorNumber": "+1234567890",
+      "testInPrebuilt": true
+    }
+  }'
+```

examples/deployment/pipecat-cloud-daily-pstn-server/fastapi-webhook-server/README.md

@@ -0,0 +1,98 @@
+# FastAPI server for handling Daily PSTN/SIP Webhook
+
+A FastAPI server that handles PSTN (Public Switched Telephone Network) and SIP (Session Initiation Protocol) calls using the Daily API.
+
+## Setup
+
+1. Clone the repository
+
+2. Navigate to the `fastapi-webhook-server` directory:
+
+   ```bash
+   cd fastapi-webhook-server
+   ```
+
+3. Install dependencies:
+
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+4. Copy `env.example` to `.env`:
+
+   ```bash
+   cp env.example .env
+   ```
+
+5. Update `.env` with your credentials:
+
+   - `AGENT_NAME`: Your Daily agent name
+   - `PIPECAT_CLOUD_API_KEY`: Your Daily API key
+   - `PINLESS_HMAC_SECRET`: Your HMAC secret for request verification
+
+## Running the Server
+
+Start the server:
+
+```bash
+python server.py
+```
+
+The server will run on `http://localhost:7860` and you can expose it via ngrok for testing:
+
+```bash
+`ngrok http 7860`
+```
+
+> Tip: Use a subdomain for a consistent URL (e.g. `ngrok http -subdomain=mydomain http://localhost:7860`)
+
+## API Endpoints
+
+### GET /
+
+Health check endpoint that returns a "Hello, World!" message.
+
+### POST /api/dial
+
+Initiates a PSTN/SIP call with the following request body format:
+
+```json
+{
+  "To": "+14152251493",
+  "From": "+14158483432",
+  "callId": "string-contains-uuid",
+  "callDomain": "string-contains-uuid",
+  "dialout_settings": [
+    {
+      "phoneNumber": "+14158483432",
+      "callerId": "+14152251493"
+    }
+  ],
+  "voicemail_detection": {
+    "testInPrebuilt": true
+  },
+  "call_transfer": {
+    "mode": "dialout",
+    "speakSummary": true,
+    "storeSummary": true,
+    "operatorNumber": "+14152250006",
+    "testInPrebuilt": true
+  }
+}
+```
+
+#### Response
+
+Returns a JSON object containing:
+
+- `status`: Success/failure status
+- `data`: Response from Daily API
+- `room_properties`: Properties of the created Daily room
+
+## Error Handling
+
+- 401: Invalid signature
+- 400: Invalid authorization header (e.g. missing Daily API key in bot.py)
+- 405: Method not allowed (e.g. incorrect route on the webhook URL)
+- 500: Server errors (missing API key, network issues)
+- Other status codes are passed through from the Daily API

examples/deployment/pipecat-cloud-daily-pstn-server/fastapi-webhook-server/env.example

@@ -0,0 +1,3 @@
+AGENT_NAME="your-agent-name"
+PIPECAT_CLOUD_API_KEY="your-daily-api-key"
+PINLESS_HMAC_SECRET="hmac-secret-pinless-dialin"

examples/deployment/pipecat-cloud-daily-pstn-server/fastapi-webhook-server/requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+python-dotenv
+requests
+pydantic
+loguru

examples/deployment/pipecat-cloud-daily-pstn-server/fastapi-webhook-server/server.py

@@ -0,0 +1,202 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+# server.py
+
+
+import base64  # for calculating hmac signature
+import hmac
+import os  # for accessing environment variables
+import time  # for setting expiration time
+from typing import Any, Dict, List, Optional
+
+import requests
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException, Request
+from loguru import logger
+from pydantic import BaseModel, Field
+
+load_dotenv(override=True)
+
+app = FastAPI()
+
+
+class RoomRequest(BaseModel):
+    test: Optional[str] = Field(None, alias="Test", description="Test field")
+    To: Optional[str] = Field(None, alias="to", description="Destination phone number")
+    From: Optional[str] = Field(None, alias="from", description="Source phone number")
+    callId: Optional[str] = Field(None, alias="call_id", description="Unique call identifier")
+    callDomain: Optional[str] = Field(
+        None, alias="call_domain", description="Call domain identifier"
+    )
+    dialout_settings: Optional[List[Dict[str, Any]]] = Field(
+        None, description="An array of phone numbers or SIP URIs to dialout to"
+    )
+    voicemail_detection: Optional[Dict[str, Any]] = Field(
+        None, description="A flag to perform voicemail or answeing-machine detection"
+    )
+    call_transfer: Optional[Dict[str, Any]] = Field(None, description="to initiate a call transfer")
+
+    class Config:
+        populate_by_name = True
+        alias_generator = None
+
+
+"""
+    body can contain any fields, but for handling PSTN/SIP, 
+    we recommend sending the following custom values:
+    dialin, dialout, voicemail detection, and call transfer
+    
+    
+    "To": "+14152251493",
+    "From": "+14158483432",
+    "callId": "string-contains-uuid",
+    "callDomain": "string-contains-uuid"
+    These need to be remapped to dialin_settings
+
+    "dialout_settings": [
+        {"phoneNumber": "+14158483432", "callerId": "+14152251493"}, 
+        {"sipUri": "sip:username@sip.hostname"}
+        ],
+    },
+
+    voicemail_detection:{
+        testInPrebuilt: true
+    },
+
+    "call_transfer": {
+        "mode": "dialout",
+        "speakSummary": true,
+        "storeSummary": true,
+        "operatorNumber": "+14152250006",
+        "testInPrebuilt": true
+    }
+"""
+
+
+@app.get("/")
+async def read_root():
+    return {"message": "Hello, World!"}
+
+
+@app.post("/api/dial")
+async def dial(request: RoomRequest, raw_request: Request):
+    logger.info("Incoming request to /dial:")
+    logger.info(f"Headers: {dict(raw_request.headers)}")
+    raw_body = await raw_request.body()
+    raw_body_str = raw_body.decode()
+    logger.info(f"Raw body: {raw_body_str}")
+    logger.info(f"Parsed body: {request.dict()}")
+
+    # calculate signature and compare/verify
+    hmac_secret = os.getenv("PINLESS_HMAC_SECRET")
+    timestamp = raw_request.headers.get("x-pinless-timestamp")
+    signature = raw_request.headers.get("x-pinless-signature")
+
+    if not hmac_secret:
+        logger.debug("Skipping HMAC validation - PINLESS_HMAC_SECRET not set")
+    elif timestamp and signature:
+        message = timestamp + "." + raw_body_str
+
+        base64_decoded_secret = base64.b64decode(hmac_secret)
+        computed_signature = base64.b64encode(
+            hmac.new(base64_decoded_secret, message.encode(), "sha256").digest()
+        ).decode()
+
+        if computed_signature != signature:
+            logger.error(f"Invalid signature. Expected {signature}, got {computed_signature}")
+            raise HTTPException(status_code=401, detail="Invalid signature")
+    else:
+        logger.debug("Skipping HMAC validation - no signature headers present")
+
+    if request.test == "test":
+        logger.debug("Test request received")
+        return {"status": "success", "message": "Test request received"}
+
+    dialin_settings = None
+    # these fields are camelCase in the request
+    required_fields = ["To", "From", "callId", "callDomain"]
+    if all(
+        field in request.dict() and request.dict()[field] is not None for field in required_fields
+    ):
+        # transform from camelCase to snake_case because daily-python expects snake_case
+        dialin_settings = {
+            "From": request.From,
+            "To": request.To,
+            "call_id": request.callId,
+            "call_domain": request.callDomain,
+            # transform from camelCase to snake_case
+        }
+        logger.debug(f"Populated dialin_settings from request: {dialin_settings}")
+
+    daily_room_properties = {
+        "enable_dialout": request.dialout_settings is not None,
+    }
+
+    if dialin_settings is not None:
+        sip_config = {
+            "display_name": request.From,
+            "sip_mode": "dial-in",
+            "num_endpoints": 2 if request.call_transfer is not None else 1,
+            "codecs": {"audio": ["OPUS"]},
+        }
+        daily_room_properties["sip"] = sip_config
+
+    # Setting default expiry to 5 minutes from now
+    daily_room_properties["exp"] = int(time.time()) + (5 * 60)
+
+    logger.debug(f"Daily room properties: {daily_room_properties}")
+    payload = {
+        "createDailyRoom": True,
+        "dailyRoomProperties": daily_room_properties,
+        "body": {
+            "dialin_settings": dialin_settings,
+            "dialout_settings": request.dialout_settings,
+            "voicemail_detection": request.voicemail_detection,
+            "call_transfer": request.call_transfer,
+        },
+    }
+
+    pcc_api_key = os.getenv("PIPECAT_CLOUD_API_KEY")
+    agent_name = os.getenv("AGENT_NAME", "my-first-agent")
+
+    if not pcc_api_key:
+        raise HTTPException(status_code=500, detail="DAILY_API_KEY environment variable is not set")
+
+    headers = {"Authorization": f"Bearer {pcc_api_key}", "Content-Type": "application/json"}
+
+    url = f"https://api.pipecat.daily.co/v1/public/{agent_name}/start"
+
+    logger.debug(f"Making API call to Daily: {url} {headers} {payload}")
+
+    try:
+        response = requests.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+        response_data = response.json()
+        logger.debug(f"Response: {response_data}")
+        return {
+            "status": "success",
+            "data": response_data,
+            "room_properties": daily_room_properties,
+        }
+    except requests.exceptions.HTTPError as e:
+        # Pass through the status code and error details from the Daily API
+        status_code = e.response.status_code
+        error_detail = e.response.json() if e.response.content else str(e)
+        logger.error(f"HTTP error: {error_detail}")
+        raise HTTPException(status_code=status_code, detail=error_detail)
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Request error: {str(e)}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+if __name__ == "__main__":
+    try:
+        import uvicorn
+
+        uvicorn.run(app, host="0.0.0.0", port=7860)
+    except KeyboardInterrupt:
+        logger.info("Server stopped manually")

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/.gitignore

@@ -0,0 +1,53 @@
+# dependencies
+/node_modules
+/.pnp
+.pnp.js
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# local env files
+.env*.local
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Logs
+logs
+*.log
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/README.md

@@ -0,0 +1,115 @@
+# Next.js server for handling Daily PSTN/SIP Webhook
+
+Next.js API routes for handling Daily PSTN/SIP Pipecat requests.
+
+## Features
+
+- API endpoint for handling Daily PSTN/SIP Pipecat requests
+- HMAC signature validation
+- Structured logging with Pino
+- Support for dial-in and dial-out settings
+- Voicemail detection and call transfer functionality
+- Test request handling
+
+## Setup
+
+1. Clone the repository
+
+2. Navigate to the `nextjs-webhook-server` directory:
+
+   ```bash
+   cd nextjs-webhook-server
+   ```
+
+3. Install dependencies:
+
+   ```bash
+   npm install
+   ```
+
+4. Create `.env.local` file with your credentials:
+
+   ```bash
+   cp env.local.example .env.local
+   ```
+
+5. Update your `.env` with your secrets:
+
+   ```bash
+   PIPECAT_CLOUD_API_KEY=pk_*
+   AGENT_NAME=my-first-agent
+   PINLESS_HMAC_SECRET=your_hmac_secret
+   LOG_LEVEL=info
+   ```
+
+### Running the server
+
+Run the development server:
+
+```bash
+npm run dev
+```
+
+The server will run on `http://localhost:7860` and you can expose it via ngrok for testing:
+
+```bash
+`ngrok http 7860`
+```
+
+> Tip: Use a subdomain for a consistent URL (e.g. `ngrok http -subdomain=mydomain http://localhost:7860`)
+
+## API Endpoints
+
+### GET /api
+
+Returns a simple "Hello, World!" message with a cute cat emoji to verify the server is running.
+
+### POST /api/dial
+
+Handles dial-in and dial-out requests for Pipecat Cloud.
+
+#### Test Requests
+
+The endpoint handles test requests when a webhook is configured. Send a request with `"Test": "test"` to verify your setup:
+
+```json
+{
+  "Test": "test"
+}
+```
+
+#### Production Request Format
+
+```json
+{
+  // for dial-in from webhook
+  "To": "+14152251493",
+  "From": "+14158483432",
+  "callId": "string-contains-uuid",
+  "callDomain": "string-contains-uuid",
+  // for making a dial out to a phone or SIP
+  "dialout_settings": [
+    { "phoneNumber": "+14158483432", "callerId": "purchased_phone_uuid" },
+    { "sipUri": "sip:username@sip.hostname.com" }
+  ]
+}
+```
+
+## Deployment
+
+The application is configured for Vercel deployment:
+
+1. Push your code to a Git repository
+2. Import your project in Vercel dashboard
+3. Configure environment variables:
+   - `PIPECAT_CLOUD_API_KEY`
+   - `AGENT_NAME`
+   - `PINLESS_HMAC_SECRET`
+   - `LOG_LEVEL` (optional, defaults to 'info')
+4. Deploy!
+
+## Security
+
+- HMAC signature validation for request authentication
+- Environment variables for sensitive credentials
+- Method validation (POST only for /dial)

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/env.local.example

@@ -0,0 +1,4 @@
+AGENT_NAME=my-first-agent
+PIPECAT_CLOUD_API_KEY=your_daily_api_key
+PINLESS_HMAC_SECRET=your_hmac_secret
+LOG_LEVEL="info"

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/package.json

@@ -0,0 +1,22 @@
+{
+  "name": "my-daily-app",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "dev": "next dev -p 7860",
+    "build": "next build",
+    "start": "next start -p 7860",
+    "lint": "next lint"
+  },
+  "dependencies": {
+    "axios": "^1.6.0",
+    "next": "^14.0.0",
+    "pino": "^8.15.0",
+    "react": "^18.2.0",
+    "react-dom": "^18.2.0"
+  },
+  "devDependencies": {
+    "eslint": "^8.46.0",
+    "eslint-config-next": "^14.0.0"
+  }
+}

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/pages/api/dial.js

@@ -0,0 +1,176 @@
+import { logger } from '../../lib/utils'; 
+import axios from 'axios';
+import crypto from 'crypto';
+
+const validateSignature = (body, signature, timestamp, secret) => {
+  // Skip if any required fields are missing
+  if (!signature || !timestamp || !secret) {
+    logger.warn('Missing required fields for HMAC validation');
+    return true;
+  }
+
+  try {
+    const decodedSecret = Buffer.from(secret, 'base64');
+    const hmac = crypto.createHmac('sha256', decodedSecret);
+    const signatureData = `${timestamp}.${body}`;
+    const computedSignature = hmac.update(signatureData).digest('base64');
+    
+    logger.debug('Signature validation:', {
+      timestamp,
+      signatureData: signatureData.substring(0, 50) + '...',
+      computedSignature,
+      receivedSignature: signature
+    });
+    
+    return computedSignature === signature;
+  } catch (error) {
+    logger.error('Error validating signature:', error);
+    return true; // Allow request to proceed on error
+  }
+};
+
+export default async function handler(req, res) {
+  // Only allow POST requests
+  if (req.method !== 'POST') {
+    return res.status(405).json({ error: 'Method not allowed' });
+  }
+
+  try {
+    logger.info('Incoming request to /api/dial:');
+    logger.info(`Headers: ${JSON.stringify(req.headers)}`);
+    
+    const rawBody = JSON.stringify(req.body);
+    logger.info(`Raw body: ${rawBody}`);
+
+    const signature = req.headers['x-pinless-signature'];
+    const timestamp = req.headers['x-pinless-timestamp'];
+    
+    if (signature && timestamp) {
+      logger.info('Validating HMAC signature');
+      if (!validateSignature(rawBody, signature, timestamp, process.env.PINLESS_HMAC_SECRET)) {
+        logger.error('Invalid HMAC signature', { signature, timestamp });
+        return res.status(401).json({ 
+          error: 'Invalid signature',
+          message: 'Invalid HMAC signature'
+        });
+      }
+    } else {
+      logger.info('Skipping HMAC validation - no signature headers present');
+    }
+
+    // Extract request data
+    const {
+      Test: test,
+      To,
+      From,
+      callId,
+      callDomain,
+      dialout_settings,
+      voicemail_detection,
+      call_transfer
+    } = req.body;
+
+    // Handle test requests when a webhook is configured
+    if (test === 'test') {
+      logger.debug('Test request received');
+      return res.status(200).json({ status: 'success', message: 'Test request received' });
+    }
+
+    // Process dialin settings
+    let dialin_settings = null;
+    const requiredFields = ['To', 'From', 'callId', 'callDomain'];
+    
+    if (requiredFields.every(field => req.body[field] !== undefined && req.body[field] !== null)) {
+      dialin_settings = {
+        // snake_case because pipecat expects this format
+        From,
+        To,
+        call_id: callId, 
+        call_domain: callDomain,
+      };
+      logger.debug(`Populated dialin_settings from request: ${JSON.stringify(dialin_settings)}`);
+    }
+
+    // Set up Daily room properties
+    const daily_room_properties = {
+      enable_dialout: dialout_settings !== undefined && dialout_settings !== null,
+      exp: Math.floor(Date.now() / 1000) + (5 * 60), // 5 minutes from now
+    };
+
+    // Configure SIP if dialin settings are provided
+    if (dialin_settings !== null) {
+      const sip_config = {
+        display_name: From,
+        sip_mode: 'dial-in',
+        num_endpoints: call_transfer !== null ? 2 : 1,
+        codecs: {"audio": ["OPUS"]},
+      };
+      daily_room_properties.sip = sip_config;
+    }
+
+    // Prepare payload for {service}/start API call
+    const payload = {
+      createDailyRoom: true,
+      dailyRoomProperties: daily_room_properties,
+      body: {
+        dialin_settings,
+        dialout_settings,
+        voicemail_detection,
+        call_transfer,
+      },
+    };
+
+    logger.debug(`Daily room properties: ${JSON.stringify(daily_room_properties)}`);
+
+    // Get Daily API key and agent name from environment variables
+    const pccApiKey = process.env.PIPECAT_CLOUD_API_KEY;
+    const agentName = process.env.AGENT_NAME || 'my-first-agent';
+
+    if (!pccApiKey) {
+      throw new Error('PIPECAT_CLOUD_API_KEY environment variable is not set');
+    }
+
+    // Set up headers for Daily API call
+    const headers = {
+      'Authorization': `Bearer ${pccApiKey}`,
+      'Content-Type': 'application/json',
+    };
+
+    const url = `https://api.pipecat.daily.co/v1/public/${agentName}/start`;
+    logger.debug(`Making API call to Daily: ${url} ${JSON.stringify(headers)} ${JSON.stringify(payload)}`);
+    
+    try {
+      const response = await axios.post(url, payload, { headers });
+      logger.debug(`Response: ${JSON.stringify(response.data)}`);
+      
+      return res.status(200).json({
+        status: 'success',
+        data: response.data,
+        room_properties: daily_room_properties,
+      });
+    } catch (error) {
+      if (error.response) {
+        // Pass through status code and error details from the Daily API
+        const statusCode = error.response.status;
+        const errorDetail = error.response.data || error.message;
+        logger.error(`HTTP error: ${JSON.stringify(errorDetail)}`);
+        return res.status(statusCode).json(errorDetail);
+      } else {
+        logger.error(`Request error: ${error.message}`);
+        return res.status(500).json({ error: error.message });
+      }
+    }    
+  } catch (error) {
+    logger.error(`Unexpected error: ${error.message}`);
+    return res.status(500).json({ error: 'Internal server error', message: error.message });
+  }
+}
+
+// Configure body parser to preserve raw body text
+export const config = {
+  api: {
+    bodyParser: {
+      sizeLimit: '1mb',
+    },
+  },
+};

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/pages/api/index.js

@@ -0,0 +1,6 @@
+import { logger } from '../../lib/utils';
+
+export default function handler(req, res) {
+  logger.info('Received request to /api');
+  res.status(200).json({ message: 'Hello, World! from ᓚᘏᗢ' });
+}

examples/deployment/pipecat-cloud-daily-pstn-server/nextjs-webhook-server/vercel.js

@@ -0,0 +1,6 @@
+module.exports = {
+  version: 2,
+  buildCommand: "next build",
+  outputDirectory: ".next",
+  cleanUrls: true
+};

examples/deployment/pipecat-cloud-example/bot.py

@@ -61,7 +61,7 @@ async def main(room_url: str, token: str):
         api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

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

@@ -4,54 +4,54 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.piper.tts import PiperTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+        ),
+    )
+
+    # Create an HTTP session
     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 = PiperTTSService(
             base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
         )
 
-        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_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await task.queue_frames(
-                [TTSSpeakFrame(f"Hello there, how are you today ?"), EndFrame()]
-            )
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
+
+        runner = PipelineRunner(handle_sigint=False)
 
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -0,0 +1,59 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.frames.frames import EndFrame, TTSSpeakFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.services.rime.tts import RimeHttpTTSService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
+
+load_dotenv(override=True)
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
+
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+        ),
+    )
+
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        tts = RimeHttpTTSService(
+            api_key=os.getenv("RIME_API_KEY", ""),
+            voice_id="rex",
+            aiohttp_session=session,
+        )
+
+        task = PipelineTask(Pipeline([tts, transport.output()]))
+
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
+
+        runner = PipelineRunner(handle_sigint=False)
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()

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

@@ -4,56 +4,52 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    task = PipelineTask(Pipeline([tts, transport.output()]))
 
-        runner = PipelineRunner()
+    # Register an event handler so we can play the audio when the client joins
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
 
-        task = PipelineTask(Pipeline([tts, transport.output()]))
+    runner = PipelineRunner(handle_sigint=False)
 
-        # Register an event handler so we can play the audio when the
-        # participant joins.
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            participant_name = participant.get("info", {}).get("userName", "")
-            await task.queue_frames(
-                [TTSSpeakFrame(f"Hello there, {participant_name}!"), EndFrame()]
-            )
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/01c-fastpitch.py

@@ -4,51 +4,49 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import EndFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.riva.tts import FastPitchTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url, None, "Say One Thing", DailyParams(audio_out_enabled=True)
-        )
+    tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-        tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    task = PipelineTask(Pipeline([tts, transport.output()]))
 
-        runner = PipelineRunner()
+    # Register an event handler so we can play the audio when the client joins
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
 
-        task = PipelineTask(Pipeline([tts, transport.output()]))
+    runner = PipelineRunner(handle_sigint=False)
 
-        # Register an event handler so we can play the audio when the
-        # participant joins.
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            participant_name = participant.get("info", {}).get("userName", "")
-            await task.queue_frames([TTSSpeakFrame(f"Aloha, {participant_name}!"), EndFrame()])
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -19,46 +15,51 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+        ),
+    )
 
-        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="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        }
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are an LLM in a WebRTC session, and this is a 'hello world' demo. Say hello to the world.",
-            }
-        ]
+    task = PipelineTask(Pipeline([llm, tts, transport.output()]))
 
-        runner = PipelineRunner()
+    # Register an event handler so we can play the audio when the client joins
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
 
-        task = PipelineTask(Pipeline([llm, tts, transport.output()]))
+    runner = PipelineRunner(handle_sigint=False)
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/03-still-frame.py

@@ -4,59 +4,67 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.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.image import FalImageGenService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            camera_out_enabled=True,
+            camera_out_width=1024,
+            camera_out_height=1024,
+        ),
+    )
+
+    # Create an HTTP session
     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):
+        # Register an event handler so we can play the audio when the client joins
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
             await task.queue_frame(TextFrame("a cat in the style of picasso"))
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+
+        @transport.event_handler("on_client_closed")
+        async def on_client_closed(transport, client):
+            logger.info(f"Client closed connection")
             await task.cancel()
 
+        runner = PipelineRunner(handle_sigint=False)
+
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,62 +4,67 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
-from pipecat.frames.frames import EndFrame, TextFrame
+from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.services.google.image import GoogleImageGenService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            camera_out_enabled=True,
+            camera_out_width=1024,
+            camera_out_height=1024,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Show a still frame image",
-            DailyParams(camera_out_enabled=True, camera_out_width=1024, camera_out_height=1024),
-        )
+    imagegen = GoogleImageGenService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+    )
 
-        imagegen = GoogleImageGenService(
-            api_key=os.getenv("GOOGLE_API_KEY"),
-        )
+    task = PipelineTask(
+        Pipeline([imagegen, transport.output()]),
+        params=PipelineParams(enable_metrics=True),
+    )
 
-        runner = PipelineRunner()
+    # Register an event handler so we can play the audio when the client joins
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        await task.queue_frame(TextFrame("a cat in the style of picasso"))
+        await task.queue_frame(TextFrame("a dog in the style of picasso"))
+        await task.queue_frame(TextFrame("a fish in the style of picasso"))
 
-        task = PipelineTask(
-            Pipeline([imagegen, transport.output()]),
-            params=PipelineParams(enable_metrics=True),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await task.queue_frame(TextFrame("a cat in the style of picasso"))
-            await task.queue_frame(TextFrame("a dog in the style of picasso"))
-            await task.queue_frame(TextFrame("a fish in the style of picasso"))
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.queue_frame(EndFrame())
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -13,9 +13,9 @@ import os
 import sys
 
 import aiohttp
+from daily_runner import configure
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import EndPipeFrame, LLMMessagesFrame, TextFrame
 from pipecat.pipeline.merge_pipeline import SequentialMergePipeline

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

@@ -4,15 +4,12 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from dataclasses import dataclass
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import (
     DataFrame,
@@ -30,13 +27,12 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia.tts import CartesiaHttpTTSService
 from pipecat.services.fal.image import FalImageGenService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 @dataclass
 class MonthFrame(DataFrame):
@@ -67,23 +63,29 @@ class MonthPrepender(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-async def main():
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    """Run the Calendar Month Narration bot using WebRTC transport.
+
+    Args:
+        webrtc_connection: The WebRTC connection to use
+        room_name: Optional room name for display purposes
+    """
+    logger.info(f"Starting bot")
+
+    # Create a transport using the WebRTC connection
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_out_enabled=True,
+            camera_out_enabled=True,
+            camera_out_width=1024,
+            camera_out_height=1024,
+        ),
+    )
+
+    # Create an HTTP session for API calls
     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,
-            ),
-        )
-
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         tts = CartesiaHttpTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
@@ -144,14 +146,30 @@ async def main():
             frames.append(MonthFrame(month=month))
             frames.append(LLMMessagesFrame(messages))
 
-        runner = PipelineRunner()
-
         task = PipelineTask(pipeline)
 
-        await task.queue_frames(frames)
+        # Set up transport event handlers
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Start the month narration once connected
+            await task.queue_frames(frames)
 
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+
+        @transport.event_handler("on_client_closed")
+        async def on_client_closed(transport, client):
+            logger.info(f"Client closed connection")
+            await task.cancel()
+
+        # Run the pipeline
+        runner = PipelineRunner(handle_sigint=False)
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -93,7 +93,7 @@ async def main():
                         self.frame = frame
                     await self.push_frame(frame, direction)
 
-            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
             tts = CartesiaHttpTTSService(
                 api_key=os.getenv("CARTESIA_API_KEY"),

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, MetricsFrame
@@ -27,14 +23,14 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -56,76 +52,83 @@ class MetricsLogger(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        ml = MetricsLogger()
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    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.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            ml,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                ml,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    runner = PipelineRunner(handle_sigint=False)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,15 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 from PIL import Image
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
@@ -20,7 +16,6 @@ from pipecat.frames.frames import (
     BotStoppedSpeakingFrame,
     Frame,
     OutputImageRawFrame,
-    TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -28,14 +23,14 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -72,83 +67,90 @@ class ImageSyncAggregator(FrameProcessor):
         await self.push_frame(frame)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        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(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_out_enabled=True,
+            camera_out_width=1024,
+            camera_out_height=1024,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        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.",
-            },
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    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(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            image_sync_aggregator,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        image_sync_aggregator = ImageSyncAggregator(
-            os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
-            os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                image_sync_aggregator,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            participant_name = participant.get("info", {}).get("userName", "")
-            await transport.capture_participant_transcription(participant["id"])
-            await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    runner = PipelineRunner(handle_sigint=False)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07-interruptible-vad.py

@@ -1,104 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.audio.vad.silero import SileroVAD
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_in_enabled=True,
-                audio_out_enabled=True,
-                transcription_enabled=True,
-            ),
-        )
-
-        vad = SileroVAD()
-
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading 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.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                vad,
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/07-interruptible.py

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -19,84 +15,92 @@ 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -1,106 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.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.anthropic.llm import AnthropicLLMService
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading 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.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

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

@@ -0,0 +1,106 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.audio.vad.silero import SileroVAD
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
+
+load_dotenv(override=True)
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
+
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+        ),
+    )
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    vad = SileroVAD()
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            vad,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()

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

@@ -4,11 +4,8 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_community.chat_message_histories import ChatMessageHistory
@@ -16,7 +13,6 @@ from langchain_core.chat_history import BaseChatMessageHistory
 from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_openai import ChatOpenAI
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
@@ -29,14 +25,14 @@ from pipecat.processors.aggregators.llm_response import (
 )
 from pipecat.processors.frameworks.langchain import LangchainProcessor
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 message_store = {}
 
 
@@ -46,90 +42,97 @@ def get_session_history(session_id: str) -> BaseChatMessageHistory:
     return message_store[session_id]
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading 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-4.1", temperature=0.7)
+    history_chain = RunnableWithMessageHistory(
+        chain,
+        get_session_history,
+        history_messages_key="chat_history",
+        input_messages_key="input",
+    )
+    lc = LangchainProcessor(history_chain)
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tma_in = LLMUserResponseAggregator()
+    tma_out = LLMAssistantResponseAggregator()
 
-        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)
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            tma_in,  # User responses
+            lc,  # Langchain
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            tma_out,  # Assistant spoken responses
+        ]
+    )
 
-        tma_in = LLMUserResponseAggregator()
-        tma_out = LLMAssistantResponseAggregator()
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        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
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # 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)])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await 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)])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,15 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from deepgram import LiveOptions
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import (
     BotInterruptionFrame,
@@ -27,91 +23,95 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Respond bot",
-            DailyParams(
-                audio_in_enabled=True,
-                audio_out_enabled=True,
-            ),
-        )
+    stt = DeepgramSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
+    )
 
-        stt = DeepgramSTTService(
-            api_key=os.getenv("DEEPGRAM_API_KEY"),
-            live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
-        )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @stt.event_handler("on_speech_started")
+    async def on_speech_started(stt, *args, **kwargs):
+        await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @stt.event_handler("on_utterance_end")
+    async def on_utterance_end(stt, *args, **kwargs):
+        await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
 
-        @stt.event_handler("on_speech_started")
-        async def on_speech_started(stt, *args, **kwargs):
-            await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        @stt.event_handler("on_utterance_end")
-        async def on_utterance_end(stt, *args, **kwargs):
-            await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,82 +17,87 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "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"))
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,45 +4,44 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    # Create an HTTP session
     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(),
-            ),
-        )
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
         tts = ElevenLabsHttpTTSService(
             api_key=os.getenv("ELEVENLABS_API_KEY", ""),
@@ -50,7 +49,7 @@ async def main():
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {
@@ -65,6 +64,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,
                 context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
@@ -83,21 +83,28 @@ async def main():
             ),
         )
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+
+        @transport.event_handler("on_client_closed")
+        async def on_client_closed(transport, client):
+            logger.info(f"Client closed connection")
             await task.cancel()
 
-        runner = PipelineRunner()
+        runner = PipelineRunner(handle_sigint=False)
 
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,99 +4,103 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = ElevenLabsTTSService(
-            api_key=os.getenv("ELEVENLABS_API_KEY", ""),
-            voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
-        )
+    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")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,100 +4,104 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.playht.tts import PlayHTHttpTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = PlayHTHttpTTSService(
-            user_id=os.getenv("PLAYHT_USER_ID"),
-            api_key=os.getenv("PLAYHT_API_KEY"),
-            voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
-        )
+    tts = PlayHTHttpTTSService(
+        user_id=os.getenv("PLAYHT_USER_ID"),
+        api_key=os.getenv("PLAYHT_API_KEY"),
+        voice_url="s3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json",
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,102 +4,106 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.playht.tts import PlayHTTTSService
 from pipecat.transcriptions.language import Language
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = PlayHTTTSService(
-            user_id=os.getenv("PLAYHT_USER_ID"),
-            api_key=os.getenv("PLAYHT_API_KEY"),
-            voice_url="s3://voice-cloning-zero-shot/e46b4027-b38d-4d24-b292-38fbca2be0ef/original/manifest.json",
-            params=PlayHTTTSService.InputParams(language=Language.EN),
-        )
+    tts = PlayHTTTSService(
+        user_id=os.getenv("PLAYHT_USER_ID"),
+        api_key=os.getenv("PLAYHT_API_KEY"),
+        voice_url="s3://voice-cloning-zero-shot/e46b4027-b38d-4d24-b292-38fbca2be0ef/original/manifest.json",
+        params=PlayHTTTSService.InputParams(language=Language.EN),
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,93 +17,97 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.azure.llm import AzureLLMService
 from pipecat.services.azure.stt import AzureSTTService
 from pipecat.services.azure.tts import AzureTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                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"),
+    )
 
-        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"),
+    )
 
-        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"),
+    )
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,95 +17,92 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.openai.stt import OpenAISTTService
 from pipecat.services.openai.tts import OpenAITTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                audio_out_sample_rate=24000,
-                transcription_enabled=False,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    stt = OpenAISTTService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        model="gpt-4o-transcribe",
+        prompt="Expect words related to dogs, such as breed names.",
+    )
 
-        # You can use the OpenAI compatible API like Groq.
-        # stt = OpenAISTTService(
-        #     base_url="https://api.groq.com/openai/v1",
-        #     api_key="gsk_***",
-        #     model="whisper-large-v3",
-        # )
-        stt = OpenAISTTService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            model="gpt-4o-transcribe-latest",
-            prompt="Expect words related to dogs, such as breed names.",
-        )
+    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
-        tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o-mini-tts-latest")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    messages = [
+        {
+            "role": "system",
+            "content": "You are very knowledgable about dogs. 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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are very knowledgable about dogs. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            audio_out_sample_rate=24000,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,15 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 import time
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -20,90 +16,97 @@ 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openpipe.llm import OpenPipeLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading 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}"},
-        )
+    timestamp = int(time.time())
+    llm = OpenPipeLLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
+        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,45 +4,44 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.xtts.tts import XTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    # Create an HTTP session
     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(),
-            ),
-        )
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
         tts = XTTSService(
             aiohttp_session=session,
@@ -50,7 +49,7 @@ async def main():
             base_url="http://localhost:8000",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {
@@ -65,6 +64,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,
                 context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
@@ -83,21 +83,28 @@ async def main():
             ),
         )
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+
+        @transport.event_handler("on_client_closed")
+        async def on_client_closed(transport, client):
+            logger.info(f"Client closed connection")
             await task.cancel()
 
-        runner = PipelineRunner()
+        runner = PipelineRunner(handle_sigint=False)
 
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -23,94 +19,96 @@ from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
 from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        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", ""),
+        params=GladiaInputParams(
+            language_config=LanguageConfig(
+                languages=[Language.EN],
+            )
+        ),
+    )
 
-        stt = GladiaSTTService(
-            api_key=os.getenv("GLADIA_API_KEY"),
-            params=GladiaInputParams(
-                language_config=LanguageConfig(
-                    languages=[Language.EN],
-                )
-            ),
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY", ""),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    messages = [
+        {
+            "role": "system",
+            "content": f"You are a helpful LLM. 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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        # Register an event handler to exit the application when the user leaves.
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    runner = PipelineRunner(handle_sigint=False)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,96 +4,100 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.lmnt.tts import LmntTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
+    tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User respones
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User respones
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -0,0 +1,102 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.groq.llm import GroqLLMService
+from pipecat.services.groq.stt import GroqSTTService
+from pipecat.services.groq.tts import GroqTTSService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
+
+load_dotenv(override=True)
+
+
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
+
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
+
+    llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
+
+    tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
+
+
+if __name__ == "__main__":
+    from run import main
+
+    main()

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

@@ -1,115 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.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.tts import CartesiaTTSService
-from pipecat.services.together.llm import TogetherLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
-
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
-
-        llm = TogetherLLMService(
-            api_key=os.getenv("TOGETHER_API_KEY"),
-            model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
-            params=TogetherLLMService.InputParams(
-                temperature=1.0,
-                top_p=0.9,
-                top_k=40,
-                extra={
-                    "frequency_penalty": 2.0,
-                    "presence_penalty": 0.0,
-                },
-            ),
-        )
-
-        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 in plain language. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-        user_aggregator = context_aggregator.user()
-        assistant_aggregator = context_aggregator.assistant()
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                user_aggregator,  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                assistant_aggregator,  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,89 +17,93 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.aws.tts import PollyTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "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"))
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    tts = PollyTTSService(
+        api_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
+        aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
+        region=os.getenv("AWS_REGION"),
+        voice_id="Amy",
+        params=PollyTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
+    )
 
-        tts = PollyTTSService(
-            api_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
-            aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID"),
-            region=os.getenv("AWS_REGION"),
-            voice_id="Amy",
-            params=PollyTTSService.InputParams(engine="neural", language="en-GB", rate="1.05"),
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -22,88 +18,94 @@ from pipecat.services.google.llm import GoogleLLMService
 from pipecat.services.google.stt import GoogleSTTService
 from pipecat.services.google.tts import GoogleTTSService
 from pipecat.transcriptions.language import Language
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
 
-        stt = GoogleSTTService(
-            params=GoogleSTTService.InputParams(languages=Language.EN_US),
-        )
+    tts = GoogleTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
 
-        tts = GoogleTTSService(
-            voice_id="en-US-Journey-F",
-            params=GoogleTTSService.InputParams(language=Language.EN_US),
-        )
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
 
-        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+    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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User respones
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User respones
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,88 +17,92 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    stt = AssemblyAISTTService(
+        api_key=os.getenv("ASSEMBLYAI_API_KEY"),
+    )
 
-        stt = AssemblyAISTTService(
-            api_key=os.getenv("ASSEMBLYAI_API_KEY"),
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.filters.krisp_filter import KrispFilter
 from pipecat.audio.vad.silero import SileroVADAnalyzer
@@ -22,83 +18,88 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+            audio_in_filter=KrispFilter(),
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-                audio_in_filter=KrispFilter(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
-        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,45 +4,44 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.rime.tts import RimeHttpTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    # Create an HTTP session
     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(),
-            ),
-        )
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
         tts = RimeHttpTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
@@ -50,7 +49,7 @@ async def main():
             aiohttp_session=session,
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
         messages = [
             {
@@ -65,6 +64,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
+                stt,
                 context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
@@ -83,21 +83,28 @@ async def main():
             ),
         )
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+
+        @transport.event_handler("on_client_closed")
+        async def on_client_closed(transport, client):
+            logger.info(f"Client closed connection")
             await task.cancel()
 
-        runner = PipelineRunner()
+        runner = PipelineRunner(handle_sigint=False)
 
         await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,99 +4,103 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.rime.tts import RimeTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = RimeTTSService(
-            api_key=os.getenv("RIME_API_KEY", ""),
-            voice_id="rex",
-        )
+    tts = RimeTTSService(
+        api_key=os.getenv("RIME_API_KEY", ""),
+        voice_id="rex",
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,76 +17,87 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.nim.llm import NimLLMService
 from pipecat.services.riva.stt import ParakeetSTTService
 from pipecat.services.riva.tts import FastPitchTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    stt = ParakeetSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-        stt = ParakeetSTTService(api_key=os.getenv("NVIDIA_API_KEY"))
+    llm = NimLLMService(api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct")
 
-        llm = NimLLMService(
-            api_key=os.getenv("NVIDIA_API_KEY"), model="meta/llama-3.1-405b-instruct"
-        )
+    tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
 
-        tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
+    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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,16 +4,12 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from dataclasses import dataclass
 
-import aiohttp
 import google.ai.generativelanguage as glm
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
@@ -32,14 +28,15 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameProcessor
-from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.google.llm import GoogleLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.services.google.tts import GoogleTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
 marker = "|----|"
 system_message = f"""
@@ -193,85 +190,92 @@ class TanscriptionContextFixup(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                # No transcription at all. just audio input to Gemini!
-                # transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            # No transcription at all. just audio input to Gemini!
+            # transcription_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
 
-        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    tts = GoogleTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
 
-        messages = [
-            {
-                "role": "system",
-                "content": system_message,
-            },
-            {
-                "role": "user",
-                "content": "Start by saying hello.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": system_message,
+        },
+        {
+            "role": "user",
+            "content": "Start by saying hello.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+    audio_collector = UserAudioCollector(context, context_aggregator.user())
+    pull_transcript_out_of_llm_output = TranscriptExtractor(context)
+    fixup_context_messages = TanscriptionContextFixup(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            audio_collector,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            pull_transcript_out_of_llm_output,
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+            fixup_context_messages,
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-        audio_collector = UserAudioCollector(context, context_aggregator.user())
-        pull_transcript_out_of_llm_output = TranscriptExtractor(context)
-        fixup_context_messages = TanscriptionContextFixup(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                audio_collector,
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                pull_transcript_out_of_llm_output,
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-                fixup_context_messages,
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,99 +4,103 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.fish.tts import FishAudioTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = FishAudioTTSService(
-            api_key=os.getenv("FISH_API_KEY"),
-            model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
-        )
+    tts = FishAudioTTSService(
+        api_key=os.getenv("FISH_API_KEY"),
+        model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07u-interruptible-ultravox.py

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -20,7 +16,9 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.ultravox.stt import UltravoxSTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
@@ -28,64 +26,70 @@ load_dotenv(override=True)
 # The Ultravox model is compute-intensive and performs best with GPU acceleration.
 # This can be deployed on cloud GPU providers like Cerebrium.ai for optimal performance.
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
 # Want to initialize the ultravox processor since it takes time to load the model and dont
 # want to load it every time the pipeline is run
 ultravox_processor = UltravoxSTTService(
-    model_size="fixie-ai/ultravox-v0_4_1-llama-3_1-8b",
+    model_name="fixie-ai/ultravox-v0_5-llama-3_1-8b",
     hf_token=os.getenv("HF_TOKEN"),
 )
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=False,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                vad_audio_passthrough=True,
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.environ.get("CARTESIA_API_KEY"),
-            voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
-        )
+    tts = CartesiaTTSService(
+        api_key=os.environ.get("CARTESIA_API_KEY"),
+        voice_id="97f4b8fb-f2fe-444b-bb9a-c109783a857a",
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                ultravox_processor,
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-            ]
-        )
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            ultravox_processor,
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+        ]
+    )
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+        ),
+    )
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07v-interruptible-neuphonic-http.py

@@ -4,99 +4,103 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = NeuphonicHttpTTSService(
-            api_key=os.getenv("NEUPHONIC_API_KEY"),
-            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-        )
+    tts = NeuphonicHttpTTSService(
+        api_key=os.getenv("NEUPHONIC_API_KEY"),
+        voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07v-interruptible-neuphonic.py

@@ -4,99 +4,103 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.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.deepgram.stt import DeepgramSTTService
 from pipecat.services.neuphonic.tts import NeuphonicTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = NeuphonicTTSService(
-            api_key=os.getenv("NEUPHONIC_API_KEY"),
-            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-        )
+    tts = NeuphonicTTSService(
+        api_key=os.getenv("NEUPHONIC_API_KEY"),
+        voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07w-interruptible-fal.py

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
@@ -21,89 +17,92 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.fal.stt import FalSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    stt = FalSTTService(
+        api_key=os.getenv("FAL_KEY"),
+    )
 
-        stt = FalSTTService(
-            api_key=os.getenv("FAL_KEY"),
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,  # STT
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        # Register an event handler to exit the application when the user leaves.
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/07x-interruptible-local.py

@@ -45,7 +45,7 @@ async def main():
         voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
     messages = [
         {

examples/foundational/07y-interruptible-groq.py

@@ -1,103 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from runner import configure
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.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.groq.llm import GroqLLMService
-from pipecat.services.groq.stt import GroqSTTService
-from pipecat.services.groq.tts import GroqTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
-
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                # transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
-
-        stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"))
-
-        llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
-
-        tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
-
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
-        ]
-
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
-
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
-
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-        @transport.event_handler("on_participant_left")
-        async def on_participant_left(transport, participant, reason):
-            await task.cancel()
-
-        runner = PipelineRunner()
-
-        await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/foundational/08-bots-arguing.py

@@ -4,8 +4,8 @@ import os
 from typing import Tuple
 
 import aiohttp
+from daily_runner import configure
 from dotenv import load_dotenv
-from runner import configure
 
 from pipecat.frames.frames import AudioFrame, EndFrame, ImageFrame, LLMMessagesFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -72,7 +72,8 @@ async def main():
 
         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."""
+            that text to speech as it's received.
+            """
             source_queue = asyncio.Queue()
             sink_queue = asyncio.Queue()
             sentence_aggregator = SentenceAggregator()

examples/foundational/09-mirror.py

@@ -4,13 +4,9 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import (
     Frame,
@@ -23,13 +19,12 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class MirrorProcessor(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
@@ -44,6 +39,7 @@ class MirrorProcessor(FrameProcessor):
                 )
             )
         elif isinstance(frame, InputImageRawFrame):
+            print(f"Received image frame: {frame.size} {frame.format}")
             await self.push_frame(
                 OutputImageRawFrame(image=frame.image, size=frame.size, format=frame.format)
             )
@@ -51,42 +47,48 @@ class MirrorProcessor(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        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 = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_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):
-            await transport.capture_participant_video(participant["id"])
+    pipeline = Pipeline([transport.input(), MirrorProcessor(), transport.output()])
 
-        pipeline = Pipeline([transport.input(), MirrorProcessor(), transport.output()])
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(),
+    )
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                audio_in_sample_rate=24000,
-                audio_out_sample_rate=24000,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -5,13 +5,10 @@
 #
 
 import asyncio
-import sys
 import tkinter as tk
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import (
     Frame,
@@ -24,14 +21,13 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.transports.base_transport import TransportParams
 from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class MirrorProcessor(FrameProcessor):
     async def process_frame(self, frame: Frame, direction: FrameDirection):
@@ -53,52 +49,59 @@ class MirrorProcessor(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        tk_root = tk.Tk()
-        tk_root.title("Local Mirror")
+    p2p_transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,
+            camera_out_enabled=True,
+            camera_out_is_live=True,
+            camera_out_width=1280,
+            camera_out_height=720,
+        ),
+    )
 
-        daily_transport = DailyTransport(
-            room_url, token, "Test", DailyParams(audio_in_enabled=True)
-        )
+    tk_root = tk.Tk()
+    tk_root.title("Local Mirror")
 
-        tk_transport = TkLocalTransport(
-            tk_root,
-            TkTransportParams(
-                audio_out_enabled=True,
-                camera_out_enabled=True,
-                camera_out_is_live=True,
-                camera_out_width=1280,
-                camera_out_height=720,
-            ),
-        )
+    tk_transport = TkLocalTransport(
+        tk_root,
+        TkTransportParams(
+            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):
-            await transport.capture_participant_video(participant["id"])
+    @p2p_transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
 
-        pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
+    pipeline = Pipeline([p2p_transport.input(), MirrorProcessor(), tk_transport.output()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                audio_in_sample_rate=24000,
-                audio_out_sample_rate=24000,
-            ),
-        )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(),
+    )
 
-        async def run_tk():
-            while not task.has_finished():
-                tk_root.update()
-                tk_root.update_idletasks()
-                await asyncio.sleep(0.1)
+    async def run_tk():
+        while not task.has_finished():
+            tk_root.update()
+            tk_root.update_idletasks()
+            await asyncio.sleep(0.1)
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await asyncio.gather(runner.run(task), run_tk())
+    await asyncio.gather(runner.run(task), run_tk())
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/10-wake-phrase.py

@@ -4,89 +4,99 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Robot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    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"])
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            hey_robot_filter,  # Filter out speech not directed at the robot
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
+    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frame(TTSSpeakFrame("Hi! If you want to talk to me, just say 'Hey Robot'"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                hey_robot_filter,  # Filter out speech not directed at the robot
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            await tts.say("Hi! If you want to talk to me, just say 'Hey Robot'.")
+    runner = PipelineRunner(handle_sigint=False)
 
-        runner = PipelineRunner()
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/11-sound-effects.py

@@ -4,21 +4,18 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 import wave
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
     LLMFullResponseEndFrame,
     OutputAudioRawFrame,
+    TTSSpeakFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -30,14 +27,14 @@ from pipecat.processors.aggregators.openai_llm_context import (
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.logger import FrameLogger
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 sounds = {}
 sound_files = ["ding1.wav", "ding2.wav"]
@@ -80,70 +77,83 @@ class InboundSoundEffectWrapper(FrameProcessor):
             await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        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.",
-            },
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    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.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+    out_sound = OutboundSoundEffectWrapper()
+    in_sound = InboundSoundEffectWrapper()
+    fl = FrameLogger("LLM Out")
+    fl2 = FrameLogger("Transcription In")
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            in_sound,
+            fl2,
+            llm,
+            fl,
+            tts,
+            out_sound,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
-        out_sound = OutboundSoundEffectWrapper()
-        in_sound = InboundSoundEffectWrapper()
-        fl = FrameLogger("LLM Out")
-        fl2 = FrameLogger("Transcription In")
+    task = PipelineTask(pipeline)
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                in_sound,
-                fl2,
-                llm,
-                fl,
-                tts,
-                out_sound,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frame(TTSSpeakFrame("Hi, I'm listening!"))
+        await transport.send_audio(sounds["ding1.wav"])
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            await tts.say("Hi, I'm listening!")
-            await transport.send_audio(sounds["ding1.wav"])
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        task = PipelineTask(pipeline)
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/12-describe-video.py

@@ -4,15 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from typing import Optional
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
@@ -23,14 +19,14 @@ 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.moondream.vision import MoondreamService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class UserImageRequester(FrameProcessor):
     def __init__(self, participant_id: Optional[str] = None):
@@ -50,61 +46,81 @@ class UserImageRequester(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    # Get WebRTC peer connection ID
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Describe participant video",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        user_response = UserResponseAggregator()
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        image_requester = UserImageRequester()
+    user_response = UserResponseAggregator()
 
-        vision_aggregator = VisionImageFrameAggregator()
+    # Initialize the image requester without setting the participant ID yet
+    image_requester = UserImageRequester()
 
-        # If you run into weird description, try with use_cpu=True
-        moondream = MoondreamService()
+    vision_aggregator = VisionImageFrameAggregator()
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    # If you run into weird description, try with use_cpu=True
+    moondream = MoondreamService()
 
-        @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.")
-            await transport.capture_participant_video(participant["id"], framerate=0)
-            await transport.capture_participant_transcription(participant["id"])
-            image_requester.set_participant_id(participant["id"])
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                user_response,
-                image_requester,
-                vision_aggregator,
-                moondream,
-                tts,
-                transport.output(),
-            ]
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        task = PipelineTask(pipeline)
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_response,
+            image_requester,
+            vision_aggregator,
+            moondream,
+            tts,
+            transport.output(),
+        ]
+    )
 
-        runner = PipelineRunner()
+    task = PipelineTask(pipeline)
 
-        await runner.run(task)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        # Welcome message
+        await tts.say("Hi there! Feel free to ask me what I see.")
+
+        # Set the participant ID in the image requester
+        image_requester.set_participant_id(webrtc_peer_id)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,33 +4,29 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from typing import Optional
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.google.llm import GoogleLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class UserImageRequester(FrameProcessor):
     def __init__(self, participant_id: Optional[str] = None):
@@ -50,61 +46,84 @@ class UserImageRequester(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    # Get WebRTC peer connection ID
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        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(),
-            ),
-        )
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        user_response = UserResponseAggregator()
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        image_requester = UserImageRequester()
+    user_response = UserResponseAggregator()
 
-        vision_aggregator = VisionImageFrameAggregator()
+    # Initialize the image requester without setting the participant ID yet
+    image_requester = UserImageRequester()
 
-        google = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
+    vision_aggregator = VisionImageFrameAggregator()
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        @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.")
-            await transport.capture_participant_video(participant["id"], framerate=0)
-            await transport.capture_participant_transcription(participant["id"])
-            image_requester.set_participant_id(participant["id"])
+    # Google Gemini model for vision analysis
+    google = GoogleLLMService(model="gemini-2.0-flash-001", api_key=os.getenv("GOOGLE_API_KEY"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                user_response,
-                image_requester,
-                vision_aggregator,
-                google,
-                tts,
-                transport.output(),
-            ]
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        task = PipelineTask(pipeline)
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_response,
+            image_requester,
+            vision_aggregator,
+            google,
+            tts,
+            transport.output(),
+        ]
+    )
 
-        runner = PipelineRunner()
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(allow_interruptions=True),
+    )
 
-        await runner.run(task)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        # Welcome message
+        await tts.say("Hi there! Feel free to ask me what I see.")
+
+        # Set the participant ID in the image requester
+        image_requester.set_participant_id(webrtc_peer_id)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,33 +4,29 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from typing import Optional
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class UserImageRequester(FrameProcessor):
     def __init__(self, participant_id: Optional[str] = None):
@@ -50,60 +46,84 @@ class UserImageRequester(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    # Get WebRTC peer connection ID
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Describe participant video",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        user_response = UserResponseAggregator()
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        image_requester = UserImageRequester()
+    user_response = UserResponseAggregator()
 
-        vision_aggregator = VisionImageFrameAggregator()
+    # Initialize the image requester without setting the participant ID yet
+    image_requester = UserImageRequester()
 
-        openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    vision_aggregator = VisionImageFrameAggregator()
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        @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.")
-            await transport.capture_participant_video(participant["id"], framerate=0)
-            await transport.capture_participant_transcription(participant["id"])
-            image_requester.set_participant_id(participant["id"])
+    # OpenAI GPT-4o for vision analysis
+    openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                user_response,
-                image_requester,
-                vision_aggregator,
-                openai,
-                tts,
-                transport.output(),
-            ]
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        task = PipelineTask(pipeline)
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_response,
+            image_requester,
+            vision_aggregator,
+            openai,
+            tts,
+            transport.output(),
+        ]
+    )
 
-        runner = PipelineRunner()
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(allow_interruptions=True),
+    )
 
-        await runner.run(task)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        # Welcome message
+        await tts.say("Hi there! Feel free to ask me what I see.")
+
+        # Set the participant ID in the image requester
+        image_requester.set_participant_id(webrtc_peer_id)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,33 +4,29 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 from typing import Optional
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, 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.anthropic.llm import AnthropicLLMService
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 class UserImageRequester(FrameProcessor):
     def __init__(self, participant_id: Optional[str] = None):
@@ -50,60 +46,84 @@ class UserImageRequester(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    # Get WebRTC peer connection ID
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Describe participant video",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        user_response = UserResponseAggregator()
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        image_requester = UserImageRequester()
+    user_response = UserResponseAggregator()
 
-        vision_aggregator = VisionImageFrameAggregator()
+    # Initialize the image requester without setting the participant ID yet
+    image_requester = UserImageRequester()
 
-        anthropic = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
+    vision_aggregator = VisionImageFrameAggregator()
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        @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.")
-            await transport.capture_participant_video(participant["id"], framerate=0)
-            await transport.capture_participant_transcription(participant["id"])
-            image_requester.set_participant_id(participant["id"])
+    # Anthropic for vision analysis
+    anthropic = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                user_response,
-                image_requester,
-                vision_aggregator,
-                anthropic,
-                tts,
-                transport.output(),
-            ]
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        task = PipelineTask(pipeline)
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_response,
+            image_requester,
+            vision_aggregator,
+            anthropic,
+            tts,
+            transport.output(),
+        ]
+    )
 
-        runner = PipelineRunner()
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(allow_interruptions=True),
+    )
 
-        await runner.run(task)
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        # Welcome message
+        await tts.say("Hi there! Feel free to ask me what I see.")
+
+        # Set the participant ID in the image requester
+        image_requester.set_participant_id(webrtc_peer_id)
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/13-whisper-transcription.py

@@ -4,13 +4,9 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TranscriptionFrame
@@ -19,13 +15,12 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper.stt import WhisperSTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -35,34 +30,42 @@ class TranscriptionLogger(FrameProcessor):
             print(f"Transcription: {frame.text}")
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Transcription bot",
-            DailyParams(
-                audio_in_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        stt = WhisperSTTService()
+    stt = WhisperSTTService()
 
-        tl = TranscriptionLogger()
+    tl = TranscriptionLogger()
 
-        pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
-import os
-import sys
 
-import aiohttp
+import os
+
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -19,13 +16,12 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.deepgram.stt import DeepgramSTTService, Language, LiveOptions
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -35,29 +31,40 @@ class TranscriptionLogger(FrameProcessor):
             print(f"Transcription: {frame.text}")
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(audio_in_enabled=True),
+    )
 
-        stt = DeepgramSTTService(
-            api_key=os.getenv("DEEPGRAM_API_KEY"),
-            #            live_options=LiveOptions(language=Language.FR),
-        )
+    stt = DeepgramSTTService(
+        api_key=os.getenv("DEEPGRAM_API_KEY"),
+        live_options=LiveOptions(language=Language.EN),
+    )
 
-        tl = TranscriptionLogger()
+    tl = TranscriptionLogger()
 
-        pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -19,13 +15,12 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.gladia import GladiaSTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -35,29 +30,40 @@ class TranscriptionLogger(FrameProcessor):
             print(f"Transcription: {frame.text}")
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(audio_in_enabled=True),
+    )
 
-        stt = GladiaSTTService(
-            api_key=os.getenv("GLADIA_API_KEY"),
-            # live_options=LiveOptions(language=Language.FR),
-        )
+    stt = GladiaSTTService(
+        api_key=os.getenv("GLADIA_API_KEY"),
+        # live_options=LiveOptions(language=Language.FR),
+    )
 
-        tl = TranscriptionLogger()
+    tl = TranscriptionLogger()
 
-        pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.frames.frames import Frame, TranscriptionFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -19,13 +15,12 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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):
@@ -35,28 +30,39 @@ class TranscriptionLogger(FrameProcessor):
             print(f"Transcription: {frame.text}")
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(audio_in_enabled=True),
+    )
 
-        stt = AssemblyAISTTService(
-            api_key=os.getenv("ASSEMBLYAI_API_KEY"),
-        )
+    stt = AssemblyAISTTService(
+        api_key=os.getenv("ASSEMBLYAI_API_KEY"),
+    )
 
-        tl = TranscriptionLogger()
+    tl = TranscriptionLogger()
 
-        pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-        task = PipelineTask(pipeline)
+    task = PipelineTask(pipeline)
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,11 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
-import sys
+
 import time
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -21,13 +18,12 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.whisper.stt import MLXModel, WhisperSTTServiceMLX
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 STOP_SECS = 2.0
 
@@ -56,40 +52,48 @@ class TranscriptionLogger(FrameProcessor):
             self._last_transcription_time = time.time()
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, _) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            None,
-            "Transcription bot",
-            DailyParams(
-                audio_in_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
-                vad_audio_passthrough=True,
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=STOP_SECS)),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        stt = WhisperSTTServiceMLX(model=MLXModel.LARGE_V3_TURBO)
+    stt = WhisperSTTServiceMLX(model=MLXModel.LARGE_V3_TURBO)
 
-        tl = TranscriptionLogger()
+    tl = TranscriptionLogger()
 
-        pipeline = Pipeline([transport.input(), stt, tl])
+    pipeline = Pipeline([transport.input(), stt, tl])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                enable_metrics=True,
-                report_only_initial_ttfb=False,
-            ),
-        )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            report_only_initial_ttfb=False,
+        ),
+    )
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

examples/foundational/14-function-calling.py

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,106 +18,118 @@ 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
     await llm.push_frame(TTSSpeakFrame("Let me check on that."))
     await result_callback({"conditions": "nice", "temperature": "75"})
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        # You can also register a function_name of None to get all functions
-        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        weather_function = FunctionSchema(
-            name="get_current_weather",
-            description="Get the current weather",
-            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 user's location.",
-                },
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location", "format"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function])
-
-        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.",
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
+        },
+        required=["location", "format"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function])
+
+    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(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+            report_only_initial_ttfb=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                report_only_initial_ttfb=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,99 +18,111 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.anthropic.llm import AnthropicLLMService
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 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)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        llm = AnthropicLLMService(
-            api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-7-sonnet-latest"
-        )
-        llm.register_function("get_weather", get_weather)
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        weather_function = FunctionSchema(
-            name="get_weather",
-            description="Get the current weather",
-            properties={
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
-                },
+    llm = AnthropicLLMService(
+        api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-7-sonnet-latest"
+    )
+    llm.register_function("get_weather", get_weather)
+
+    weather_function = FunctionSchema(
+        name="get_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function])
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function])
 
-        # todo: test with very short initial user message
+    # 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": "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."}]
+    messages = [{"role": "user", "content": "Say 'hello' to start the conversation."}]
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    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
-            ]
-        )
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            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,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+        ),
+    )
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        runner = PipelineRunner()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        await runner.run(task)
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -6,12 +6,9 @@
 
 import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,14 +19,16 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.anthropic.llm import AnthropicLLMService
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
-video_participant_id = None
+# Global variable to store the peer connection ID
+webrtc_peer_id = None
 
 
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
@@ -39,72 +38,83 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
     question = arguments["question"]
+    logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
+
+    # Request the image frame
     await llm.request_image_frame(
-        user_id=video_participant_id,
+        user_id=webrtc_peer_id,
         function_name=function_name,
         tool_call_id=tool_call_id,
         text_content=question,
     )
 
+    # Wait a short time for the frame to be processed
+    await asyncio.sleep(0.5)
 
-async def main():
-    global llm
+    # Return a result to complete the function call
+    await result_callback(
+        f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
+    )
 
-    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(),
-            ),
-        )
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    global webrtc_peer_id
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        llm = AnthropicLLMService(
-            api_key=os.getenv("ANTHROPIC_API_KEY"),
-            model="claude-3-7-sonnet-latest",
-            enable_prompt_caching_beta=True,
-        )
-        llm.register_function("get_weather", get_weather)
-        llm.register_function("get_image", get_image)
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,  # Make sure camera input is enabled
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        weather_function = FunctionSchema(
-            name="get_weather",
-            description="Get the current weather",
-            properties={
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
-                },
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = AnthropicLLMService(
+        api_key=os.getenv("ANTHROPIC_API_KEY"),
+        model="claude-3-7-sonnet-latest",
+        enable_prompt_caching_beta=True,
+    )
+    llm.register_function("get_weather", get_weather)
+    llm.register_function("get_image", get_image)
+
+    weather_function = FunctionSchema(
+        name="get_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location"],
-        )
-        get_image_function = FunctionSchema(
-            name="get_image",
-            description="Get an image from the video stream.",
-            properties={
-                "question": {
-                    "type": "string",
-                    "description": "The question that the user is asking about the image.",
-                }
-            },
-            required=["question"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
+        },
+        required=["location"],
+    )
+    get_image_function = FunctionSchema(
+        name="get_image",
+        description="Get an image from the video stream.",
+        properties={
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image.",
+            }
+        },
+        required=["question"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
 
-        # todo: test with very short initial user message
-
-        system_prompt = """\
+    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.
@@ -115,63 +125,73 @@ 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?
+- 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."},
+    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
+            stt,  # STT
+            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
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+        ),
+    )
 
-        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
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            global video_participant_id
-            video_participant_id = participant["id"]
-            await transport.capture_participant_transcription(video_participant_id)
-            await transport.capture_participant_video(video_participant_id, framerate=0)
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
-        await runner.run(task)
+    runner = PipelineRunner(handle_sigint=False)
+
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,99 +18,111 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.together.llm import TogetherLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
     await llm.push_frame(TTSSpeakFrame("Let me check on that."))
     await result_callback({"conditions": "nice", "temperature": "75"})
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                transcription_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        llm = TogetherLLMService(
-            api_key=os.getenv("TOGETHER_API_KEY"),
-            model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
-        )
-        # You can also register a function_name of None to get all functions
-        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        weather_function = FunctionSchema(
-            name="get_current_weather",
-            description="Get the current weather",
-            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 user's location.",
-                },
+    llm = TogetherLLMService(
+        api_key=os.getenv("TOGETHER_API_KEY"),
+        model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
+    )
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
+
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location", "format"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function])
-        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.",
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
+        },
+        required=["location", "format"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function])
+    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(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(pipeline)
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(pipeline)
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -6,12 +6,9 @@
 
 import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -21,15 +18,17 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
-video_participant_id = None
+# Global variable to store the peer connection ID
+webrtc_peer_id = None
 
 
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
@@ -38,71 +37,85 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 
 
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
-    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
     question = arguments["question"]
+    logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
+
+    # Request the image frame
     await llm.request_image_frame(
-        user_id=video_participant_id,
+        user_id=webrtc_peer_id,
         function_name=function_name,
         tool_call_id=tool_call_id,
         text_content=question,
     )
 
+    # Wait a short time for the frame to be processed
+    await asyncio.sleep(0.5)
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    # Return a result to complete the function call
+    await result_callback(
+        f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
+    )
 
-        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="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    global webrtc_peer_id
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
-        llm.register_function("get_weather", get_weather)
-        llm.register_function("get_image", get_image)
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        weather_function = FunctionSchema(
-            name="get_weather",
-            description="Get the current weather",
-            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 user's location.",
-                },
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,  # Make sure camera input is enabled
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm.register_function("get_weather", get_weather)
+    llm.register_function("get_image", get_image)
+
+    weather_function = FunctionSchema(
+        name="get_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location"],
-        )
-        get_image_function = FunctionSchema(
-            name="get_image",
-            description="Get an image from the video stream.",
-            properties={
-                "question": {
-                    "type": "string",
-                    "description": "The question that the user is asking about the image.",
-                }
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
-            required=["question"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
+        },
+        required=["location"],
+    )
+    get_image_function = FunctionSchema(
+        name="get_image",
+        description="Get an image from the video stream.",
+        properties={
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image.",
+            }
+        },
+        required=["question"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
 
-        system_prompt = """\
+    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.
@@ -113,46 +126,55 @@ 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?
+- 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?
 """
-        messages = [
-            {"role": "system", "content": system_prompt},
+    messages = [
+        {"role": "system", "content": system_prompt},
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(pipeline)
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(pipeline)
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            global video_participant_id
-            video_participant_id = participant["id"]
-            await transport.capture_participant_transcription(participant["id"])
-            await transport.capture_participant_video(video_participant_id, framerate=0)
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -6,12 +6,9 @@
 
 import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -22,15 +19,17 @@ 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.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.google.llm import GoogleLLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
 
-video_participant_id = None
+# Global variable to store the peer connection ID
+webrtc_peer_id = None
 
 
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
@@ -40,71 +39,85 @@ async def get_weather(function_name, tool_call_id, arguments, llm, context, resu
 
 
 async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
-    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
     question = arguments["question"]
+    logger.debug(f"Requesting image with user_id={webrtc_peer_id}, question={question}")
+
+    # Request the image frame
     await llm.request_image_frame(
-        user_id=video_participant_id,
+        user_id=webrtc_peer_id,
         function_name=function_name,
         tool_call_id=tool_call_id,
         text_content=question,
     )
 
+    # Wait a short time for the frame to be processed
+    await asyncio.sleep(0.5)
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+    # Return a result to complete the function call
+    await result_callback(
+        f"I've captured an image from your camera and I'm analyzing what you asked about: {question}"
+    )
 
-        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="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    global webrtc_peer_id
+    webrtc_peer_id = webrtc_connection.pc_id
 
-        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather)
-        llm.register_function("get_image", get_image)
+    logger.info(f"Starting bot with peer_id: {webrtc_peer_id}")
 
-        weather_function = FunctionSchema(
-            name="get_weather",
-            description="Get the current weather",
-            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 user's location.",
-                },
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            camera_in_enabled=True,  # Make sure camera input is enabled
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
+    llm.register_function("get_weather", get_weather)
+    llm.register_function("get_image", get_image)
+
+    weather_function = FunctionSchema(
+        name="get_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location", "format"],
-        )
-        get_image_function = FunctionSchema(
-            name="get_image",
-            description="Get an image from the video stream.",
-            properties={
-                "question": {
-                    "type": "string",
-                    "description": "The question that the user is asking about the image.",
-                }
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
-            required=["question"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
+        },
+        required=["location", "format"],
+    )
+    get_image_function = FunctionSchema(
+        name="get_image",
+        description="Get an image from the video stream.",
+        properties={
+            "question": {
+                "type": "string",
+                "description": "The question that the user is asking about the image.",
+            }
+        },
+        required=["question"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function, get_image_function])
 
-        system_prompt = """\
+    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.
@@ -115,54 +128,63 @@ 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?
+- 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?
 """
-        messages = [
-            {"role": "system", "content": system_prompt},
-            {"role": "user", "content": "Say hello."},
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": "Say hello."},
+    ]
+
+    context = OpenAILLMContext(messages, tools)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            global video_participant_id
-            video_participant_id = participant["id"]
-            await transport.capture_participant_transcription(participant["id"])
-            await transport.capture_participant_video(video_participant_id, framerate=0)
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()

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

@@ -4,14 +4,10 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
-import sys
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
-from runner import configure
 
 from pipecat.adapters.schemas.function_schema import FunctionSchema
 from pipecat.adapters.schemas.tools_schema import ToolsSchema
@@ -24,105 +20,113 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.groq.llm import GroqLLMService
 from pipecat.services.groq.stt import GroqSTTService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
 
 async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
     await llm.push_frame(TTSSpeakFrame("Let me check on that."))
     await result_callback({"conditions": "nice", "temperature": "75"})
 
 
-async def main():
-    async with aiohttp.ClientSession() as session:
-        (room_url, token) = await configure(session)
+async def run_bot(webrtc_connection: SmallWebRTCConnection):
+    logger.info(f"Starting bot")
 
-        transport = DailyTransport(
-            room_url,
-            token,
-            "Respond bot",
-            DailyParams(
-                audio_out_enabled=True,
-                vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True,
-            ),
-        )
+    transport = SmallWebRTCTransport(
+        webrtc_connection=webrtc_connection,
+        params=TransportParams(
+            audio_in_enabled=True,
+            audio_out_enabled=True,
+            vad_enabled=True,
+            vad_analyzer=SileroVADAnalyzer(),
+            vad_audio_passthrough=True,
+        ),
+    )
 
-        stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"), model="distil-whisper-large-v3-en")
+    stt = GroqSTTService(api_key=os.getenv("GROQ_API_KEY"), model="distil-whisper-large-v3-en")
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
-        # You can also register a function_name of None to get all functions
-        # sent to the same callback with an additional function_name parameter.
-        llm.register_function("get_current_weather", fetch_weather_from_api)
+    llm = GroqLLMService(api_key=os.getenv("GROQ_API_KEY"), model="llama-3.3-70b-versatile")
+    # You can also register a function_name of None to get all functions
+    # sent to the same callback with an additional function_name parameter.
+    llm.register_function("get_current_weather", fetch_weather_from_api)
 
-        weather_function = FunctionSchema(
-            name="get_current_weather",
-            description="Get the current weather",
-            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 user's location.",
-                },
+    weather_function = FunctionSchema(
+        name="get_current_weather",
+        description="Get the current weather",
+        properties={
+            "location": {
+                "type": "string",
+                "description": "The city and state, e.g. San Francisco, CA",
             },
-            required=["location"],
-        )
-        tools = ToolsSchema(standard_tools=[weather_function])
-        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.",
+            "format": {
+                "type": "string",
+                "enum": ["celsius", "fahrenheit"],
+                "description": "The temperature unit to use. Infer this from the user's location.",
             },
+        },
+        required=["location"],
+    )
+    tools = ToolsSchema(standard_tools=[weather_function])
+    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(
+        [
+            transport.input(),
+            stt,
+            context_aggregator.user(),
+            llm,
+            tts,
+            transport.output(),
+            context_aggregator.assistant(),
         ]
+    )
 
-        context = OpenAILLMContext(messages, tools)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            allow_interruptions=True,
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),
-                stt,
-                context_aggregator.user(),
-                llm,
-                tts,
-                transport.output(),
-                context_aggregator.assistant(),
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        await task.queue_frames([context_aggregator.user().get_context_frame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                allow_interruptions=True,
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-        )
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
 
-        @transport.event_handler("on_first_participant_joined")
-        async def on_first_participant_joined(transport, participant):
-            await transport.capture_participant_transcription(participant["id"])
-            # Kick off the conversation.
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_closed")
+    async def on_client_closed(transport, client):
+        logger.info(f"Client closed connection")
+        await task.cancel()
 
-        runner = PipelineRunner()
+    runner = PipelineRunner(handle_sigint=False)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    from run import main
+
+    main()