attempt at 2 pipelines

.github/ISSUE_TEMPLATE/1-bug_report.yml

@@ -1,87 +0,0 @@
-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

@@ -1,67 +0,0 @@
-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

@@ -1,52 +0,0 @@
-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

@@ -1,82 +0,0 @@
-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

@@ -1,56 +0,0 @@
-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

@@ -1,74 +0,0 @@
-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

@@ -1,70 +0,0 @@
-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

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

.gitignore

@@ -7,7 +7,7 @@ venv
 /.idea
 #*#
 
-# Distribution / Packaging
+# Distribution / packaging
 .Python
 build/
 develop-eggs/
@@ -30,24 +30,24 @@ MANIFEST
 .env
 fly.toml
 
-# Examples
-examples/telnyx-chatbot/templates/streams.xml
-examples/twilio-chatbot/templates/streams.xml
-examples/**/node_modules/
-examples/**/.expo/
-examples/**/dist/
-examples/**/npm-debug.*
-examples/**/*.jks
-examples/**/*.p8
-examples/**/*.p12
-examples/**/*.key
-examples/**/*.mobileprovision
-examples/**/*.orig.*
-examples/**/web-build/
+# Example files
+pipecat/examples/twilio-chatbot/templates/streams.xml
+pipecat/examples/bot-ready-signalling/client/react-native/node_modules/
+pipecat/examples/bot-ready-signalling/client/react-native/.expo/
+pipecat/examples/bot-ready-signalling/client/react-native/dist/
+pipecat/examples/bot-ready-signalling/client/react-native/npm-debug.*
+pipecat/examples/bot-ready-signalling/client/react-native/*.jks
+pipecat/examples/bot-ready-signalling/client/react-native/*.p8
+pipecat/examples/bot-ready-signalling/client/react-native/*.p12
+pipecat/examples/bot-ready-signalling/client/react-native/*.key
+pipecat/examples/bot-ready-signalling/client/react-native/*.mobileprovision
+pipecat/examples/bot-ready-signalling/client/react-native/*.orig.*
+pipecat/examples/bot-ready-signalling/client/react-native/web-build/
 
 # macOS
 .DS_Store
 
+
 # Documentation
 docs/api/_build/
 docs/api/api

.pre-commit-config.yaml

@@ -1,8 +1,7 @@
 repos:
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.7
+  - repo: local
     hooks:
-      - id: ruff
-        language_version: python3
-        args: [ --select,  I, ]
-      - id: ruff-format
+      - id: ruff-format-hook
+        name: Check ruff formatting
+        entry: sh scripts/pre-commit.sh
+        language: system

CHANGELOG.md

@@ -5,812 +5,10 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## Unreleased
 
 ### Added
 
-- Added `RTVIObserverParams` which allows you to configure what RTVI messages
-  are sent to the clients.
-
-- Added a `context_window_compression` InputParam to
-  `GeminiMultimodalLiveLLMService` which allows you to enable a sliding context
-  window for the session as well as set the token limit of the sliding window.
-
-- Updated `SmallWebRTCConnection` to support `ice_servers` with credentials.
-
-- Added `VADUserStartedSpeakingFrame` and `VADUserStoppedSpeakingFrame`,
-  indicating when the VAD detected the user to start and stop speaking. These
-  events are helpful when using smart turn detection, as the user's stop time
-  can differ from when their turn ends (signified by UserStoppedSpeakingFrame).
-
-- Added `TranslationFrame`, a new frame type that contains a translated
-  transcription.
-
-- Added `TransportParams.audio_in_passthrough`. If set (the default), incoming
-  audio will be pushed downstream.
-
-- Added `MCPClient`; a way to connect to MCP servers and use the MCP servers'
-  tools.
-
-- Added `Mem0 OSS`, along with Mem0 cloud support now the OSS version is also
-  available.
-
-### Changed
-
-- The `STTMuteFilter` now mutes `InterimTranscriptionFrame` and
-  `TranscriptionFrame` which allows the `STTMuteFilter` to be used in
-  conjunction with transports that generate transcripts, e.g. `DailyTransport`.
-
-- Function calls now receive a single parameter `FunctionCallParams` instead of
-  `(function_name, tool_call_id, args, llm, context, result_callback)` which is
-  now deprecated.
-
-- Changed the user aggregator timeout for late transcriptions from 1.0s to 0.5s
-  (`LLMUserAggregatorParams.aggregation_timeout`). Sometimes, the STT services
-  might give us more than one transcription which could come after the user
-  stopped speaking. We still want to include these additional transcriptions
-  with the first one because it's part of the user turn. This is what this
-  timeout is helpful with.
-
-- Short utterances not detected by VAD while the bot is speaking are now
-  ignored. This reduces the amount of bot interruptions significantly providing
-  a more natural conversation experience.
-
-- Updated `GladiaSTTService` to output a `TranslationFrame` when specifying a
-  `translation` and `translation_config`.
-
-- STT services now passthrough audio frames by default. This allows you to add
-  audio recording without worrying about what's wrong in your pipeline when it
-  doesn't work the first time.
-
-- Input transports now always push audio downstream unless disabled with
-  `TransportParams.audio_in_passthrough`. After many Pipecat releases, we
-  realized this is the common use case. There are use cases where the input
-  transport already provides STT and you also don't want recordings, in which
-  case there's no need to push audio to the rest of the pipeline, but this is
-  not a very common case.
-
-### Deprecated
-
-- Function calls with parameters
-  `(function_name, tool_call_id, args, llm, context, result_callback)` are
-  deprectated, use a single `FunctionCallParams` parameter instead.
-
-- `TransportParams.camera_*` parameters are now deprecated, use
-  `TransportParams.video_*` instead.
-
-- `TransportParams.vad_enabled` parameter is now deprecated, use
-  `TransportParams.audio_in_enabled` and `TransportParams.vad_analyzer` instead.
-
-- `TransportParams.vad_audio_passthrough` parameter is now deprecated, use
-  `TransportParams.audio_in_passthrough` instead.
-
-### Fixed
-
-- Fixed an issue with `GeminiMultimodalLiveLLMService` where the context
-  contained tokens instead of words.
-
-- Fixed an issue with HTTP Smart Turn handling, where the service returns a 500
-  error. Previously, this would cause an unhandled exception. Now, a 500 error
-  is treated as an incomplete response.
-
-- Fixed a TTS services issue that could cause assistant output not to be
-  aggregated to the context when also using `TTSSpeakFrame`s.
-
-- Fixed an issue where the `SmartTurnMetricsData` was reporting 0ms for
-  inference and processing time when using the `FalSmartTurnAnalyzer`.
-
-### Other
-
-- Added 04 foundational examples for client/server transports. Also, renamed
-  `29-livekit-audio-chat.py` to `04b-transports-livekit.py`.
-
-- Added foundational example `13c-gladia-translation.py` showing how to use
-  `TranscriptionFrame` and `TranslationFrame`.
-
-## [0.0.65] - 2025-04-23 "Sant Jordi's release" 🌹📕
-
-https://en.wikipedia.org/wiki/Saint_George%27s_Day_in_Catalonia
-
-### Added
-
-- Added automatic hangup logic to the Telnyx serializer. This feature hangs up
-  the Telnyx call when an `EndFrame` or `CancelFrame` is received. It is
-  enabled by default and is configurable via the `auto_hang_up` `InputParam`.
-
-- Added a keepalive task to `GladiaSTTService` to prevent the websocket from
-  disconnecting after 30 seconds of no audio input.
-
-### Changed
-
-- The `InputParams` for `ElevenLabsTTSService` and `ElevenLabsHttpTTSService`
-  no longer require that `stability` and `similarity_boost` be set. You can
-  individually set each param.
-
-- In `TwilioFrameSerializer`, `call_sid` is Optional so as to avoid a breaking
-  changed. `call_sid` is required to automatically hang up.
-
-### Fixed
-
-- Fixed an issue where `TwilioFrameSerializer` would send two hang up commands:
-  one for the `EndFrame` and one for the `CancelFrame`.
-
-## [0.0.64] - 2025-04-22
-
-### Added
-
-- Added automatic hangup logic to the Twilio serializer. This feature hangs up
-  the Twilio call when an `EndFrame` or `CancelFrame` is received. It is
-  enabled by default and is configurable via the `auto_hang_up` `InputParam`.
-
-- Added `SmartTurnMetricsData`, which contains end-of-turn prediction metrics,
-  to the `MetricsFrame`. Using `MetricsFrame`, you can now retrieve prediction
-  confidence scores and processing time metrics from the smart turn analyzers.
-
-- 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 `HttpSmartTurnAnalyzer()` or
-  `FalSmartTurnAnalyzer()` 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
-
-- `GrokLLMService` now uses `grok-3-beta` as its default model.
-
-- 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.
-
-### Other
-
-- Updated the `twilio-chatbot` example to use the auto-hangup feature.
-
-## [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`.
-
-- Added `Mem0MemoryService`. Mem0 is a self-improving memory layer for LLM
-  applications. Learn more at: https://mem0.ai/.
-
-- Added `WhisperSTTServiceMLX` for Whisper transcription on Apple Silicon.
-  See example in `examples/foundational/13e-whisper-mlx.py`. Latency of
-  completed transcription using Whisper large-v3-turbo on an M4 macbook is
-  ~500ms.
-
-- Added `SmallWebRTCTransport`, a new P2P WebRTC transport.
-
-  - Created two examples in `p2p-webrtc`:
-    - **video-transform**: Demonstrates sending and receiving audio/video with
-      `SmallWebRTCTransport` using `TypeScript`. Includes video frame
-      processing with OpenCV.
-    - **voice-agent**: A minimal example of creating a voice agent with
-      `SmallWebRTCTransport`.
-
-- `GladiaSTTService` now have comprehensive support for the latest API config
-  options, including model, language detection, preprocessing, custom
-  vocabulary, custom spelling, translation, and message filtering options.
-
-- Added `SmallWebRTCTransport`, a new P2P WebRTC transport.
-
-  - Created two examples in `p2p-webrtc`:
-    - **video-transform**: Demonstrates sending and receiving audio/video with
-      `SmallWebRTCTransport` using `TypeScript`. Includes video frame
-      processing with OpenCV.
-    - **voice-agent**: A minimal example of creating a voice agent with
-      `SmallWebRTCTransport`.
-
-- Added support to `ProtobufFrameSerializer` to send the messages from
-  `TransportMessageFrame` and `TransportMessageUrgentFrame`.
-
-- Added support for a new TTS service, `PiperTTSService`.
-  (see https://github.com/rhasspy/piper/)
-
-- It is now possible to tell whether `UserStartedSpeakingFrame` or
-  `UserStoppedSpeakingFrame` have been generated because of emulation frames.
-
-### 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:
-
-  - image: for image generation services
-  - llm: for LLM services
-  - memory: for memory services
-  - stt: for Speech-To-Text services
-  - tts: for Text-To-Speech services
-  - video: for video generation services
-  - vision: for video recognition services
-
-- 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]`.
-
-- `GladiaSTTService` now uses the `solaria-1` model by default. Other params
-  use Gladia's default values. Added support for more language codes.
-
-### Deprecated
-
-- All Pipecat services imports have been deprecated and a warning will be shown
-  when using the old import. The new import should be
-  `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
-  `Mem0MemoryService`.
-
-- Added foundational example `13e-whisper-mlx.py` demonstrating how to use the
-  `WhisperSTTServiceMLX`.
-
-## [0.0.61] - 2025-03-26
-
-### Added
-
-- Added a new frame, `LLMSetToolChoiceFrame`, which provides a mechanism
-  for modifying the `tool_choice` in the context.
-
-- Added `GroqTTSService` which provides text-to-speech functionality using
-  Groq's API.
-
-- Added support in `DailyTransport` for updating remote participants'
-  `canReceive` permission via the `update_remote_participants()` method, by
-  bumping the daily-python dependency to >= 0.16.0.
-
-- ElevenLabs TTS services now support a sample rate of 8000.
-
-- Added support for `instructions` in `OpenAITTSService`.
-
-- Added support for `base_url` in `OpenAIImageGenService` and
-  `OpenAITTSService`.
-
-### Fixed
-
-- Fixed an issue in `RTVIObserver` that prevented handling of Google LLM
-  context messages. The observer now processes both OpenAI-style and
-  Google-style contexts.
-
-- Fixed an issue in Daily involving switching virtual devices, by bumping the
-  daily-python dependency to >= 0.16.1.
-
-- Fixed a `GoogleAssistantContextAggregator` issue where function calls
-  placeholders where not being updated when then function call result was
-  different from a string.
-
-- Fixed an issue that would cause `LLMAssistantContextAggregator` to block
-  processing more frames while processing a function call result.
-
-- Fixed an issue where the `RTVIObserver` would report two bot started and
-  stopped speaking events for each bot turn.
-
-- Fixed an issue in `UltravoxSTTService` that caused improper audio processing
-  and incorrect LLM frame output.
-
-### Other
-
-- Added `examples/foundational/07x-interruptible-local.py` to show how a local
-  transport can be used.
-
-## [0.0.60] - 2025-03-20
-
-### Added
-
-- Added `default_headers` parameter to `BaseOpenAILLMService` constructor.
-
-### Changed
-
-- Rollback to `deepgram-sdk` 3.8.0 since 3.10.1 was causing connections issues.
-
-- Changed the default `InputAudioTranscription` model to `gpt-4o-transcribe`
-  for `OpenAIRealtimeBetaLLMService`.
-
-### Other
-
-- Update the `19-openai-realtime-beta.py` and `19a-azure-realtime-beta.py`
-  examples to use the FunctionSchema format.
-
-## [0.0.59] - 2025-03-20
-
-### Added
-
-- When registering a function call it is now possible to indicate if you want
-  the function call to be cancelled if there's a user interruption via
-  `cancel_on_interruption` (defaults to False). This is now possible because
-  function calls are executed concurrently.
-
-- Added support for detecting idle pipelines. By default, if no activity has
-  been detected during 5 minutes, the `PipelineTask` will be automatically
-  cancelled. It is possible to override this behavior by passing
-  `cancel_on_idle_timeout=False`. It is also possible to change the default
-  timeout with `idle_timeout_secs` or the frames that prevent the pipeline from
-  being idle with `idle_timeout_frames`. Finally, an `on_idle_timeout` event
-  handler will be triggered if the idle timeout is reached (whether the pipeline
-  task is cancelled or not).
-
-- Added `FalSTTService`, which provides STT for Fal's Wizper API.
-
-- Added a `reconnect_on_error` parameter to websocket-based TTS services as well
-  as a `on_connection_error` event handler. The `reconnect_on_error` indicates
-  whether the TTS service should reconnect on error. The `on_connection_error`
-  will always get called if there's any error no matter the value of
-  `reconnect_on_error`. This allows, for example, to fallback to a different TTS
-  provider if something goes wrong with the current one.
-
-- Added new `SkipTagsAggregator` that extends `BaseTextAggregator` to aggregate
-  text and skips end of sentence matching if aggregated text is between
-  start/end tags.
-
-- Added new `PatternPairAggregator` that extends `BaseTextAggregator` to
-  identify content between matching pattern pairs in streamed text. This allows
-  for detection and processing of structured content like XML-style tags that
-  may span across multiple text chunks or sentence boundaries.
-
-- Added new `BaseTextAggregator`. Text aggregators are used by the TTS service
-  to aggregate LLM tokens and decide when the aggregated text should be pushed
-  to the TTS service. They also allow for the text to be manipulated while it's
-  being aggregated. A text aggregator can be passed via `text_aggregator` to the
-  TTS service.
-
-- Added new `sample_rate` constructor parameter to `TavusVideoService` to allow
-  changing the output sample rate.
-
-- Added new `NeuphonicTTSService`.
-  (see https://neuphonic.com)
-
-- Added new `UltravoxSTTService`.
-  (see https://github.com/fixie-ai/ultravox)
-
-- Added `on_frame_reached_upstream` and `on_frame_reached_downstream` event
-  handlers to `PipelineTask`. Those events will be called when a frame reaches
-  the beginning or end of the pipeline respectively. Note that by default, the
-  event handlers will not be called unless a filter is set with
-  `PipelineTask.set_reached_upstream_filter()` or
-  `PipelineTask.set_reached_downstream_filter()`.
-
-- Added support for Chirp voices in `GoogleTTSService`.
-
-- Added a `flush_audio()` method to `FishTTSService` and `LmntTTSService`.
-
-- Added a `set_language` convenience method for `GoogleSTTService`, allowing
-  you to set a single language. This is in addition to the `set_languages`
-  method which allows you to set a list of languages.
-
-- Added `on_user_turn_audio_data` and `on_bot_turn_audio_data` to
-  `AudioBufferProcessor`. This gives the ability to grab the audio of only that
-  turn for both the user and the bot.
-
-- Added new base class `BaseObject` which is now the base class of
-  `FrameProcessor`, `PipelineRunner`, `PipelineTask` and `BaseTransport`. The
-  new `BaseObject` adds supports for event handlers.
-
-- Added support for a unified format for specifying function calling across all
-  LLM services.
-
-```python
-  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.",
-          },
-      },
-      required=["location"],
-  )
-  tools = ToolsSchema(standard_tools=[weather_function])
-```
-
-- Added `speech_threshold` parameter to `GladiaSTTService`.
-
-- Allow passing user (`user_kwargs`) and assistant (`assistant_kwargs`) context
-  aggregator parameters when using `create_context_aggregator()`. The values are
-  passed as a mapping that will then be converted to arguments.
-
-- Added `speed` as an `InputParam` for both `ElevenLabsTTSService` and
-  `ElevenLabsHttpTTSService`.
-
-- Added new `LLMFullResponseAggregator` to aggregate full LLM completions. At
-  every completion the `on_completion` event handler is triggered.
-
-- Added a new frame, `RTVIServerMessageFrame`, and RTVI message
-  `RTVIServerMessage` which provides a generic mechanism for sending custom
-  messages from server to client. The `RTVIServerMessageFrame` is processed by
-  the `RTVIObserver` and will be delivered to the client's `onServerMessage`
-  callback or `ServerMessage` event.
-
-- Added `GoogleLLMOpenAIBetaService` for Google LLM integration with an
-  OpenAI-compatible interface. Added foundational example
-  `14o-function-calling-gemini-openai-format.py`.
-
-- Added `AzureRealtimeBetaLLMService` to support Azure's OpeanAI Realtime API. Added
-  foundational example `19a-azure-realtime-beta.py`.
-
-- Introduced `GoogleVertexLLMService`, a new class for integrating with Vertex AI
-  Gemini models. Added foundational example
-  `14p-function-calling-gemini-vertex-ai.py`.
-
-- Added support in `OpenAIRealtimeBetaLLMService` for a slate of new features:
-
-  - The `'gpt-4o-transcribe'` input audio transcription model, along
-    with new `language` and `prompt` options specific to that model.
-  - The `input_audio_noise_reduction` session property.
-
-    ```python
-    session_properties = SessionProperties(
-      # ...
-      input_audio_noise_reduction=InputAudioNoiseReduction(
-        type="near_field" # also supported: "far_field"
-      )
-      # ...
-    )
-    ```
-
-  - The `'semantic_vad'` `turn_detection` session property value, a more
-    sophisticated model for detecting when the user has stopped speaking.
-  - `on_conversation_item_created` and `on_conversation_item_updated`
-    events to `OpenAIRealtimeBetaLLMService`.
-
-    ```python
-    @llm.event_handler("on_conversation_item_created")
-    async def on_conversation_item_created(llm, item_id, item):
-      # ...
-
-    @llm.event_handler("on_conversation_item_updated")
-    async def on_conversation_item_updated(llm, item_id, item):
-      # `item` may not always be available here
-      # ...
-    ```
-
-  - The `retrieve_conversation_item(item_id)` method for introspecting a
-    conversation item on the server.
-
-    ```python
-    item = await llm.retrieve_conversation_item(item_id)
-    ```
-
-### Changed
-
-- Updated `OpenAISTTService` to use `gpt-4o-transcribe` as the default
-  transcription model.
-
-- Updated `OpenAITTSService` to use `gpt-4o-mini-tts` as the default TTS model.
-
-- Function calls are now executed in tasks. This means that the pipeline will
-  not be blocked while the function call is being executed.
-
-- ⚠️ `PipelineTask` will now be automatically cancelled if no bot activity is
-  happening in the pipeline. There are a few settings to configure this
-  behavior, see `PipelineTask` documentation for more details.
-
-- All event handlers are now executed in separate tasks in order to prevent
-  blocking the pipeline. It is possible that event handlers take some time to
-  execute in which case the pipeline would be blocked waiting for the event
-  handler to complete.
-
-- Updated `TranscriptProcessor` to support text output from
-  `OpenAIRealtimeBetaLLMService`.
-
-- `OpenAIRealtimeBetaLLMService` and `GeminiMultimodalLiveLLMService` now push
-  a `TTSTextFrame`.
-
-- Updated the default mode for `CartesiaTTSService` and
-  `CartesiaHttpTTSService` to `sonic-2`.
-
-### Deprecated
-
-- Passing a `start_callback` to `LLMService.register_function()` is now
-  deprecated, simply move the code from the start callback to the function call.
-
-- `TTSService` parameter `text_filter` is now deprecated, use `text_filters`
-  instead which is now a list. This allows passing multiple filters that will be
-  executed in order.
-
-### Removed
-
-- Removed deprecated `audio.resample_audio()`, use `create_default_resampler()`
-  instead.
-
-- Removed deprecated`stt_service` parameter from `STTMuteFilter`.
-
-- Removed deprecated RTVI processors, use an `RTVIObserver` instead.
-
-- Removed deprecated `AWSTTSService`, use `PollyTTSService` instead.
-
-- Removed deprecated field `tier` from `DailyTranscriptionSettings`, use `model`
-  instead.
-
-- Removed deprecated `pipecat.vad` package, use `pipecat.audio.vad` instead.
-
-### Fixed
-
-- Fixed an assistant aggregator issue that could cause assistant text to be
-  split into multiple chunks during function calls.
-
-- Fixed an assistant aggregator issue that was causing assistant text to not be
-  added to the context during function calls. This could lead to duplications.
-
-- Fixed a `SegmentedSTTService` issue that was causing audio to be sent
-  prematurely to the STT service. Instead of analyzing the volume in this
-  service we rely on VAD events which use both VAD and volume.
-
-- Fixed a `GeminiMultimodalLiveLLMService` issue that was causing messages to be
-  duplicated in the context when pushing `LLMMessagesAppendFrame` frames.
-
-- Fixed an issue with `SegmentedSTTService` based services
-  (e.g. `GroqSTTService`) that was not allow audio to pass-through downstream.
-
-- Fixed a `CartesiaTTSService` and `RimeTTSService` issue that would consider
-  text between spelling out tags end of sentence.
-
-- Fixed a `match_endofsentence` issue that would result in floating point
-  numbers to be considered an end of sentence.
-
-- Fixed a `match_endofsentence` issue that would result in emails to be
-  considered an end of sentence.
-
-- Fixed an issue where the RTVI message `disconnect-bot` was pushing an
-  `EndFrame`, resulting in the pipeline not shutting down. It now pushes an
-  `EndTaskFrame` upstream to shutdown the pipeline.
-
-- Fixed an issue with the `GoogleSTTService` where stream timeouts during
-  periods of inactivity were causing connection failures. The service now
-  properly detects timeout errors and handles reconnection gracefully,
-  ensuring continuous operation even after periods of silence or when using an
-  `STTMuteFilter`.
-
-- Fixed an issue in `RimeTTSService` where the last line of text sent didn't
-  result in an audio output being generated.
-
-- Fixed `OpenAIRealtimeBetaLLMService` by adding proper handling for:
-  - The `conversation.item.input_audio_transcription.delta` server message,
-    which was added server-side at some point and not handled client-side.
-  - Errors reported by the `response.done` server message.
-
-### Other
-
-- Add foundational example `07w-interruptible-fal.py`, showing `FalSTTService`.
-
-- Added a new Ultravox example
-  `examples/foundational/07u-interruptible-ultravox.py`.
-
-- Added new Neuphonic examples
-  `examples/foundational/07v-interruptible-neuphonic.py` and
-  `examples/foundational/07v-interruptible-neuphonic-http.py`.
-
-- Added a new example `examples/foundational/36-user-email-gathering.py` to show
-  how to gather user emails. The example uses's Cartesia's `<spell></spell>`
-  tags and Rime `spell()` function to spell out the emails for confirmation.
-
-- Update the `34-audio-recording.py` example to include an STT processor.
-
-- Added foundational example `35-voice-switching.py` showing how to use the new
-  `PatternPairAggregator`. This example shows how to encode information for the
-  LLM to instruct TTS voice changes, but this can be used to encode any
-  information into the LLM response, which you want to parse and use in other
-  parts of your application.
-
-- Added a Pipecat Cloud deployment example to the `examples` directory.
-
-- Removed foundational examples 28b and 28c as the TranscriptProcessor no
-  longer has an LLM depedency. Renamed foundational example 28a to
-  `28-transcript-processor.py`.
-
-## [0.0.58] - 2025-02-26
-
-### Added
-
-- Added track-specific audio event `on_track_audio_data` to
-  `AudioBufferProcessor` for accessing separate input and output audio tracks.
-
-- Pipecat version will now be logged on every application startup. This will
-  help us identify what version we are running in case of any issues.
-
-- Added a new `StopFrame` which can be used to stop a pipeline task while
-  keeping the frame processors running. The frame processors could then be used
-  in a different pipeline. The difference between a `StopFrame` and a
-  `StopTaskFrame` is that, as with `EndFrame` and `EndTaskFrame`, the
-  `StopFrame` is pushed from the task and the `StopTaskFrame` is pushed upstream
-  inside the pipeline by any processor.
-
-- Added a new `PipelineTask` parameter `observers` that replaces the previous
-  `PipelineParams.observers`.
-
-- Added a new `PipelineTask` parameter `check_dangling_tasks` to enable or
-  disable checking for frame processors' dangling tasks when the Pipeline
-  finishes running.
-
-- Added new `on_completion_timeout` event for LLM services (all OpenAI-based
-  services, Anthropic and Google). Note that this event will only get triggered
-  if LLM timeouts are setup and if the timeout was reached. It can be useful to
-  retrigger another completion and see if the timeout was just a blip.
-
-- Added new log observers `LLMLogObserver` and `TranscriptionLogObserver` that
-  can be useful for debugging your pipelines.
-
 - Added `room_url` property to `DailyTransport`.
 
 - Added `addons` argument to `DeepgramSTTService`.
@@ -819,27 +17,6 @@ https://en.wikipedia.org/wiki/Saint_George%27s_Day_in_Catalonia
 
 ### Changed
 
-- ⚠️ `PipelineTask` now requires keyword arguments (except for the first one for
-  the pipeline).
-
-- Updated `PlayHTHttpTTSService` to take a `voice_engine` and `protocol` input
-  in the constructor. The previous method of providing a `voice_engine` input
-  that contains the engine and protocol is deprecated by PlayHT.
-
-- The base `TTSService` class now strips leading newlines before sending text
-  to the TTS provider. This change is to solve issues where some TTS providers,
-  like Azure, would not output text due to newlines.
-
-- `GrokLLMSService` now uses `grok-2` as the default model.
-
-- `AnthropicLLMService` now uses `claude-3-7-sonnet-20250219` as the default
-  model.
-
-- `RimeHttpTTSService` needs an `aiohttp.ClientSession` to be passed to the
-  constructor as all the other HTTP-based services.
-
-- `RimeHttpTTSService` doesn't use a default voice anymore.
-
 - `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
   to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
   (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
@@ -848,49 +25,8 @@ https://en.wikipedia.org/wiki/Saint_George%27s_Day_in_Catalonia
 stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 ```
 
-### Deprecated
-
-- `PipelineParams.observers` is now deprecated, you the new `PipelineTask`
-  parameter `observers`.
-
-### Removed
-
-- Remove `TransportParams.audio_out_is_live` since it was not being used at all.
-
 ### Fixed
 
-- Fixed an issue that would cause undesired interruptions via
-  `EmulateUserStartedSpeakingFrame`.
-
-- Fixed a `GoogleLLMService` that was causing an exception when sending inline
-  audio in some cases.
-
-- Fixed an `AudioContextWordTTSService` issue that would cause an `EndFrame` to
-  disconnect from the TTS service before audio from all the contexts was
-  received. This affected services like Cartesia and Rime.
-
-- Fixed an issue that was not allowing to pass an `OpenAILLMContext` to create
-  `GoogleLLMService`'s context aggregators.
-
-- Fixed a `ElevenLabsTTSService`, `FishAudioTTSService`, `LMNTTTSService` and
-  `PlayHTTTSService` issue that was resulting in audio requested before an
-  interruption being played after an interruption.
-
-- Fixed `match_endofsentence` support for ellipses.
-
-- Fixed an issue where `EndTaskFrame` was not triggering
-  `on_client_disconnected` or closing the WebSocket in FastAPI.
-
-- Fixed an issue in `DeepgramSTTService` where the `sample_rate` passed to the
-  `LiveOptions` was not being used, causing the service to use the default
-  sample rate of pipeline.
-
-- Fixed a context aggregator issue that would not append the LLM text response
-  to the context if a function call happened in the same LLM turn.
-
-- Fixed an issue that was causing HTTP TTS services to push `TTSStoppedFrame`
-  more than once.
-
 - Fixed a `FishAudioTTSService` issue where `TTSStoppedFrame` was not being
   pushed.
 
@@ -907,9 +43,6 @@ stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
 
 - Added Gemini support to `examples/phone-chatbot`.
 
-- Added foundational example `34-audio-recording.py` showing how to use the
-  AudioBufferProcessor callbacks to save merged and track recordings.
-
 ## [0.0.57] - 2025-02-14
 
 ### Added
@@ -2542,7 +1675,7 @@ async def on_connected(processor):
   completed. If a task is never ran `has_finished()` will return False.
 
 - `PipelineRunner` now supports SIGTERM. If received, the runner will be
-  cancelled.
+  canceled.
 
 ### Fixed
 

CONTRIBUTING.md

@@ -26,52 +26,11 @@ git commit -m "Description of your changes"
 git push origin your-branch-name
 ```
 
-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!
+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!
 
 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
 
@@ -92,23 +51,23 @@ 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
@@ -203,4 +162,4 @@ 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

@@ -1,72 +1,43 @@
 <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: Real-Time Voice & Multimodal AI Agents
+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** 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.
+## What you can build
 
-## 🚀 What You Can Build
+- **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
 
-- **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
+## 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="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>
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/simple-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/simple-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/storytelling-chatbot/image.png" width="280" /></a>
     <br/>
-    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="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>
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/translation-chatbot/image.png" width="280" /></a>&nbsp;
+    <a href="https://github.com/pipecat-ai/pipecat/tree/main/examples/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat/main/examples/moondream-chatbot/image.png" width="280" /></a>
 </p>
 
-## 📱 Client SDKs
+## Key features
 
-You can connect to Pipecat from any platform using our official 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
 
-| 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                   |
+💡 Looking to build structured conversations? Check out [Pipecat Flows](https://github.com/pipecat-ai/pipecat-flows) for managing complex conversational states and transitions.
 
-## 🧩 Available services
+## Getting started
 
-| 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.
+You can get started with Pipecat running on your local machine, then move your agent processes to the cloud when you’re ready. You can also add a 📞 telephone number, 🖼️ image output, 📺 video input, use different LLMs, and more.
 
 ```shell
 # Install the module
@@ -82,71 +53,154 @@ To keep things lightweight, only the core framework is included by default. If y
 pip install "pipecat-ai[option,...]"
 ```
 
-## 🧪 Code examples
+### 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), [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), [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), [Together AI](https://docs.pipecat.ai/server/services/llm/together) | `pip install "pipecat-ai[openai]"`      |
+| Text-to-Speech      | [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts)                                                                                                                                                                          | `pip install "pipecat-ai[cartesia]"`    |
+| Speech-to-Speech    | [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | `pip install "pipecat-ai[google]"`      |
+| Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      | `pip install "pipecat-ai[daily]"`       |
+| Video               | [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[tavus,simli]"` |
+| Vision & Image      | [Moondream](https://docs.pipecat.ai/server/services/vision/moondream), [fal](https://docs.pipecat.ai/server/services/image-generation/fal)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              | `pip install "pipecat-ai[moondream]"`   |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          | `pip install "pipecat-ai[silero]"`      |
+| Analytics & Metrics | [Canonical AI](https://docs.pipecat.ai/server/services/analytics/canonical), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | `pip install "pipecat-ai[canonical]"`   |
+
+📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
+
+## 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
 
-## 🛠️ Hacking on the framework itself
+## A simple voice agent running locally
 
-1. Set up a virtual environment before following these instructions. From the root of the repo:
+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.
 
-   ```shell
-   python3 -m venv venv
-   source venv/bin/activate
-   ```
+```python
+import asyncio
 
-2. Install the development dependencies:
+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
 
-   ```shell
-   pip install -r dev-requirements.txt
-   ```
+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))
 
-3. Install the git pre-commit hooks (these help ensure your code follows project rules):
+  # Use Cartesia for Text-to-Speech
+  tts = CartesiaTTSService(
+    api_key=...,
+    voice_id=...
+  )
 
-   ```shell
-   pre-commit install
-   ```
+  # Simple pipeline that will process text to speech and output the result
+  pipeline = Pipeline([tts, transport.output()])
 
-4. Install the `pipecat-ai` package locally in editable mode:
+  # Create Pipecat processor that can run one or more pipelines tasks
+  runner = PipelineRunner()
 
-   ```shell
-   pip install -e .
-   ```
+  # Assign the task callable to run the pipeline
+  task = PipelineTask(pipeline)
 
-   > The `-e` or `--editable` option allows you to modify the code without reinstalling.
+  # 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}!"))
 
-5. Include optional dependencies as needed. For example:
+  # 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()
 
-   ```shell
-   pip install -e ".[daily,deepgram,cartesia,openai,silero]"
-   ```
+  # Run the pipeline task
+  await runner.run(task)
 
-6. (Optional) If you want to use this package from another directory:
+if __name__ == "__main__":
+  asyncio.run(main())
+```
 
-   ```shell
-   pip install "path_to_this_repo[option,...]"
-   ```
-
-### Running tests
-
-Install the test dependencies:
+Run it with:
 
 ```shell
-pip install -r test-requirements.txt
+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,...]"
+```
+
+### Running tests
+
 From the root directory, run:
 
 ```shell
 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:
 
@@ -168,7 +222,7 @@ 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:
@@ -180,7 +234,7 @@ 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:
 
@@ -190,7 +244,7 @@ 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:
 
@@ -203,7 +257,7 @@ 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)
 

dev-requirements.txt

@@ -3,11 +3,10 @@ coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.397
+pyright~=1.1.393
 pytest~=8.3.4
-pytest-asyncio~=0.25.3
-pytest-aiohttp==1.1.0
-ruff~=0.11.1
+pytest-asyncio~=0.25.2
+ruff~=0.9.5
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

docs/ISSUE_TEMPLATE.md

@@ -0,0 +1,22 @@
+# 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/conf.py

@@ -50,13 +50,6 @@ autodoc_mock_imports = [
     "pyht.protos",
     "pyht.protos.api_pb2",
     "pipecat_ai_playht",  # PlayHT wrapper
-    "aiortc",
-    "aiortc.mediastreams",
-    "cv2",
-    "av",
-    "pyneuphonic",
-    "mem0",
-    "mlx_whisper",
     "anthropic",
     "assemblyai",
     "boto3",
@@ -75,6 +68,7 @@ autodoc_mock_imports = [
     "openpipe",
     "simli",
     "soundfile",
+    # Existing mocks
     "pipecat_ai_krisp",
     "pyaudio",
     "_tkinter",
@@ -85,66 +79,6 @@ autodoc_mock_imports = [
     "pydantic.Field",
     "pydantic._internal._model_construction",
     "pydantic._internal._fields",
-    # Moondream dependencies
-    "torch",
-    "transformers",
-    "intel_extension_for_pytorch",
-    # Ultravox dependencies
-    "huggingface_hub",
-    "vllm",
-    "vllm.engine.arg_utils",
-    "transformers.AutoTokenizer",
-    # Langchain dependencies
-    "langchain_core",
-    "langchain_core.messages",
-    "langchain_core.runnables",
-    "langchain_core.messages.AIMessageChunk",
-    "langchain_core.runnables.Runnable",
-    # LiveKit dependencies
-    "livekit",
-    "livekit.rtc",
-    "livekit_api",
-    "livekit_protocol",
-    "tenacity",
-    "tenacity.retry",
-    "tenacity.stop_after_attempt",
-    "tenacity.wait_exponential",
-    "rtc",
-    "rtc.Room",
-    "rtc.RoomOptions",
-    "rtc.AudioSource",
-    "rtc.LocalAudioTrack",
-    "rtc.TrackPublishOptions",
-    "rtc.TrackSource",
-    "rtc.AudioStream",
-    "rtc.AudioFrameEvent",
-    "rtc.AudioFrame",
-    "rtc.Track",
-    "rtc.TrackKind",
-    "rtc.RemoteParticipant",
-    "rtc.RemoteTrackPublication",
-    "rtc.DataPacket",
-    # Riva dependencies
-    "riva",
-    "riva.client",
-    "riva.client.Auth",
-    "riva.client.ASRService",
-    "riva.client.StreamingRecognitionConfig",
-    "riva.client.RecognitionConfig",
-    "riva.client.AudioEncoding",
-    "riva.client.proto.riva_tts_pb2",
-    "riva.client.SpeechSynthesisService",
-    # Local CoreML Smart Turn dependencies
-    "coremltools",
-    "coremltools.models",
-    "coremltools.models.MLModel",
-    "torch",
-    "torch.nn",
-    "torch.nn.functional",
-    "transformers",
-    "transformers.AutoFeatureExtractor",
-    # Also add specific classes that are imported
-    "AutoFeatureExtractor",
 ]
 
 # HTML output settings
@@ -176,25 +110,12 @@ def verify_modules():
         },
     }
 
-    # Skip importing modules that are in autodoc_mock_imports
-    skipped_modules = set(autodoc_mock_imports)
-
     missing = []
     for category, modules in required_modules.items():
         if isinstance(modules, dict):
             # Handle nested structure
             for subcategory, submodules in modules.items():
                 for module in submodules:
-                    # Check if module is in autodoc_mock_imports
-                    if (
-                        f"pipecat.{category}.{subcategory}.{module}" in skipped_modules
-                        or module in skipped_modules
-                    ):
-                        logger.info(
-                            f"Skipping import of mocked module: pipecat.{category}.{subcategory}.{module}"
-                        )
-                        continue
-
                     try:
                         __import__(f"pipecat.{category}.{subcategory}.{module}")
                         logger.info(
@@ -208,11 +129,6 @@ def verify_modules():
         else:
             # Handle flat structure
             for module in modules:
-                # Check if module is in autodoc_mock_imports
-                if f"pipecat.{category}.{module}" in skipped_modules or module in skipped_modules:
-                    logger.info(f"Skipping import of mocked module: pipecat.{category}.{module}")
-                    continue
-
                 try:
                     __import__(f"pipecat.{category}.{module}")
                     logger.info(f"Successfully imported pipecat.{category}.{module}")

docs/api/index.rst

@@ -45,10 +45,8 @@ 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>`
@@ -58,12 +56,10 @@ 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>

docs/api/requirements.txt

@@ -12,43 +12,29 @@ pipecat-ai[aws]
 pipecat-ai[azure]
 pipecat-ai[canonical]
 pipecat-ai[cartesia]
-pipecat-ai[cerebras]
-pipecat-ai[deepseek]
 pipecat-ai[daily]
 pipecat-ai[deepgram]
 pipecat-ai[elevenlabs]
 pipecat-ai[fal]
 pipecat-ai[fireworks]
-pipecat-ai[fish]
 pipecat-ai[gladia]
 pipecat-ai[google]
 pipecat-ai[grok]
 pipecat-ai[groq]
-# pipecat-ai[krisp] # Mocked
-pipecat-ai[koala]
-# pipecat-ai[langchain] # Mocked
-# pipecat-ai[livekit] # Mocked
+# pipecat-ai[krisp] # Mocked instead
+pipecat-ai[langchain]
+pipecat-ai[livekit]
 pipecat-ai[lmnt]
 pipecat-ai[local]
-# pipecat-ai[local-smart-turn] # Mocked
-# pipecat-ai[mem0] # Mocked
-# pipecat-ai[mlx-whisper] # Mocked
-# pipecat-ai[moondream] # Mocked
+pipecat-ai[moondream]
 pipecat-ai[nim]
-# pipecat-ai[neuphonic] # Mocked
 pipecat-ai[noisereduce]
 pipecat-ai[openai]
 # pipecat-ai[openpipe]
 # pipecat-ai[playht] # Mocked due to grpcio conflict with riva
-pipecat-ai[qwen]
-pipecat-ai[remote-smart-turn]
-# pipecat-ai[riva] # Mocked
+pipecat-ai[riva]
 pipecat-ai[silero]
 pipecat-ai[simli]
 pipecat-ai[soundfile]
-pipecat-ai[tavus]
-pipecat-ai[together]
-# pipecat-ai[ultravox] # Mocked
-# pipecat-ai[webrtc] # Mocked
 pipecat-ai[websocket]
 pipecat-ai[whisper]

dot-env.template

@@ -18,9 +18,6 @@ AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
-# Cartesia
-CARTESIA_API_KEY=...
-
 # Daily
 DAILY_API_KEY=...
 DAILY_SAMPLE_ROOM_URL=https://...
@@ -29,9 +26,6 @@ DAILY_SAMPLE_ROOM_URL=https://...
 ELEVENLABS_API_KEY=...
 ELEVENLABS_VOICE_ID=...
 
-# Neuphonic
-NEUPHONIC_API_KEY=...
-
 # Fal
 FAL_KEY=...
 
@@ -90,14 +84,3 @@ ASSEMBLYAI_API_KEY=...
 
 # OpenRouter
 OPENROUTER_API_KEY=...
-
-# Piper
-PIPER_BASE_URL=...
-
-# Smart turn
-LOCAL_SMART_TURN_MODEL_PATH=
-FAL_SMART_TURN_API_KEY=...
-
-# Twilio
-TWILIO_ACCOUNT_SID=
-TWILIO_AUTH_TOKEN=

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

@@ -17,8 +17,8 @@ from runner import configure
 from pipecat.frames.frames import AudioRawFrame, EndFrame, OutputAudioRawFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
-from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -64,7 +64,7 @@ async def main():
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
-            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
         )
 
         runner = PipelineRunner()

examples/canonical-metrics/bot.py

@@ -21,9 +21,9 @@ 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.audio_buffer_processor import AudioBufferProcessor
-from pipecat.services.canonical.metrics import CanonicalMetricsService
-from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.canonical import CanonicalMetricsService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -43,7 +43,9 @@ async def main():
             DailyParams(
                 audio_out_enabled=True,
                 audio_in_enabled=True,
-                video_out_enabled=False,
+                camera_out_enabled=False,
+                vad_enabled=True,
+                vad_audio_passthrough=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 transcription_enabled=True,
                 #
@@ -70,7 +72,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
         messages = [
             {
@@ -111,13 +113,13 @@ async def main():
                 llm,
                 tts,
                 transport.output(),
-                canonical,  # uploads audio buffer to Canonical AI for metrics
                 audio_buffer_processor,  # captures audio into a buffer
+                canonical,  # uploads audio buffer to Canonical AI for metrics
                 context_aggregator.assistant(),
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/chatbot-audio-recording/bot.py

@@ -23,8 +23,8 @@ 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.audio_buffer_processor import AudioBufferProcessor
-from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -32,16 +32,10 @@ load_dotenv(override=True)
 logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
-# Create the recordings directory if it doesn't exist
-os.makedirs("recordings", exist_ok=True)
 
-
-async def save_audio(audio: bytes, sample_rate: int, num_channels: int, name: str):
+async def save_audio(audio: bytes, sample_rate: int, num_channels: int):
     if len(audio) > 0:
-        filename = os.path.join(
-            "recordings",
-            f"{name}_conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav",
-        )
+        filename = f"conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
         with io.BytesIO() as buffer:
             with wave.open(buffer, "wb") as wf:
                 wf.setsampwidth(2)
@@ -66,7 +60,9 @@ async def main():
             DailyParams(
                 audio_out_enabled=True,
                 audio_in_enabled=True,
-                video_out_enabled=False,
+                camera_out_enabled=False,
+                vad_enabled=True,
+                vad_audio_passthrough=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 transcription_enabled=True,
                 #
@@ -93,7 +89,7 @@ async def main():
             # voice_id="gD1IexrzCvsXPHUuT0s3",
         )
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
         messages = [
             {
@@ -114,7 +110,7 @@ async def main():
 
         # NOTE: Watch out! This will save all the conversation in memory. You
         # can pass `buffer_size` to get periodic callbacks.
-        audiobuffer = AudioBufferProcessor(enable_turn_audio=True)
+        audiobuffer = AudioBufferProcessor()
 
         pipeline = Pipeline(
             [
@@ -128,19 +124,11 @@ async def main():
             ]
         )
 
-        task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @audiobuffer.event_handler("on_audio_data")
         async def on_audio_data(buffer, audio, sample_rate, num_channels):
-            await save_audio(audio, sample_rate, num_channels, "full")
-
-        @audiobuffer.event_handler("on_user_turn_audio_data")
-        async def on_user_turn_audio_data(buffer, audio, sample_rate, num_channels):
-            await save_audio(audio, sample_rate, num_channels, "user")
-
-        @audiobuffer.event_handler("on_bot_turn_audio_data")
-        async def on_bot_turn_audio_data(buffer, audio, sample_rate, num_channels):
-            await save_audio(audio, sample_rate, num_channels, "bot")
+            await save_audio(audio, sample_rate, num_channels)
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):

examples/deployment/flyio-example/bot.py

@@ -1,9 +1,3 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
 import argparse
 import asyncio
 import os
@@ -18,8 +12,8 @@ from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
-from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.elevenlabs import ElevenLabsTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -41,7 +35,8 @@ async def main(room_url: str, token: str):
             api_key=daily_api_key,
             audio_in_enabled=True,
             audio_out_enabled=True,
-            video_out_enabled=False,
+            camera_out_enabled=False,
+            vad_enabled=True,
             vad_analyzer=SileroVADAnalyzer(),
             transcription_enabled=True,
         ),
@@ -52,7 +47,7 @@ async def main(room_url: str, token: str):
         voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
     messages = [
         {
@@ -75,7 +70,7 @@ async def main(room_url: str, token: str):
         ]
     )
 
-    task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+    task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):

examples/deployment/modal-example/app.py

@@ -1,9 +1,3 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
 import os
 
 import aiohttp

examples/deployment/modal-example/bot.py

@@ -1,9 +1,3 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
 import asyncio
 import os
 import sys
@@ -16,8 +10,8 @@ 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.openai.llm import OpenAILLMService
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 load_dotenv(override=True)
@@ -32,18 +26,18 @@ async def main(room_url: str, token: str):
         token,
         "bot",
         DailyParams(
-            audio_in_enabled=True,
             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"
+        api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
     )
 
-    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
 
     messages = [
         {
@@ -68,7 +62,7 @@ async def main(room_url: str, token: str):
 
     task = PipelineTask(
         pipeline,
-        params=PipelineParams(
+        PipelineParams(
             allow_interruptions=True,
             enable_metrics=True,
             enable_usage_metrics=True,

examples/deployment/modal-example/requirements.txt

@@ -1,4 +1,5 @@
 python-dotenv==1.0.1
 modal==0.71.3
-pipecat-ai[daily,silero,cartesia,openai]
+pipecat-ai[daily,silero,cartesia,openai]==0.0.52
 fastapi==0.115.6
+aiohttp==3.11.11

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

@@ -1,178 +0,0 @@
-# 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

@@ -1,98 +0,0 @@
-# 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

@@ -1,3 +0,0 @@
-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

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

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

@@ -1,202 +0,0 @@
-#
-# 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

@@ -1,53 +0,0 @@
-# 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

@@ -1,115 +0,0 @@
-# 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

@@ -1,4 +0,0 @@
-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

@@ -1,22 +0,0 @@
-{
-  "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

@@ -1,176 +0,0 @@
-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

@@ -1,6 +0,0 @@
-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

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

examples/deployment/pipecat-cloud-example/.gitignore

@@ -1,94 +0,0 @@
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-.Python
-build/
-dist/
-*.egg-info/
-*.egg
-.installed.cfg
-.eggs/
-downloads/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-MANIFEST
-
-# Virtual Environments
-venv/
-env/
-.env
-.venv/
-ENV/
-env.bak/
-venv.bak/
-
-# IDE
-.idea/
-.vscode/
-.spyderproject
-.spyproject
-.ropeproject
-
-# Testing and Coverage
-.coverage
-.coverage.*
-htmlcov/
-.pytest_cache/
-.tox/
-.nox/
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-cover/
-
-# Logs and Databases
-*.log
-*.db
-db.sqlite3
-db.sqlite3-journal
-pip-log.txt
-
-# System Files
-.DS_Store
-Thumbs.db
-desktop.ini
-*.swp
-*.swo
-*.bak
-*.tmp
-*~
-
-# Build and Documentation
-docs/_build/
-.pybuilder/
-target/
-instance/
-.webassets-cache
-.pdm.toml
-.pdm-python
-.pdm-build/
-__pypackages__/
-
-# Other
-*.mo
-*.pot
-*.sage.py
-.mypy_cache/
-.dmypy.json
-dmypy.json
-.pyre/
-.pytype/
-cython_debug/
-.ipynb_checkpoints
-
-# Pipecat cloud
-.pcc-deploy.toml

examples/deployment/pipecat-cloud-example/Dockerfile

@@ -1,7 +0,0 @@
-FROM dailyco/pipecat-base:latest
-
-COPY ./requirements.txt requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-
-COPY ./bot.py bot.py

examples/deployment/pipecat-cloud-example/README.md

@@ -1,196 +0,0 @@
-# Pipecat Cloud Starter Project
-
-[![Docs](https://img.shields.io/badge/Documentation-blue)](https://docs.pipecat.daily.co) [![Discord](https://img.shields.io/discord/1217145424381743145)](https://discord.gg/dailyco)
-
-A template voice agent for [Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) that demonstrates building and deploying a conversational AI agent.
-
-> **For a detailed step-by-step guide, see our [Quickstart Documentation](https://docs.pipecat.daily.co/quickstart).**
-
-## Prerequisites
-
-- Python 3.10+
-- Linux, MacOS, or Windows Subsystem for Linux (WSL)
-- [Docker](https://www.docker.com) and a Docker repository (e.g., [Docker Hub](https://hub.docker.com))
-- A Docker Hub account (or other container registry account)
-- [Pipecat Cloud](https://pipecat.daily.co) account
-
-> **Note**: If you haven't installed Docker yet, follow the official installation guides for your platform ([Linux](https://docs.docker.com/engine/install/), [Mac](https://docs.docker.com/desktop/setup/install/mac-install/), [Windows](https://docs.docker.com/desktop/setup/install/windows-install/)). For Docker Hub, [create a free account](https://hub.docker.com/signup) and log in via terminal with `docker login`.
-
-## Get Started
-
-### 1. Get the starter project
-
-Clone the starter project from GitHub:
-
-```bash
-git clone https://github.com/daily-co/pipecat-cloud-starter
-cd pipecat-cloud-starter
-```
-
-### 2. Set up your Python environment
-
-We recommend using a virtual environment to manage your Python dependencies.
-
-```bash
-# Create a virtual environment
-python -m venv .venv
-
-# Activate it
-source .venv/bin/activate  # On Windows: .venv\Scripts\activate
-
-# Install the Pipecat Cloud CLI
-pip install pipecatcloud
-```
-
-### 3. Authenticate with Pipecat Cloud
-
-```bash
-pcc auth login
-```
-
-### 4. Acquire required API keys
-
-This starter requires the following API keys:
-
-- **OpenAI API Key**: Get from [platform.openai.com/api-keys](https://platform.openai.com/api-keys)
-- **Cartesia API Key**: Get from [play.cartesia.ai/keys](https://play.cartesia.ai/keys)
-- **Daily API Key**: Automatically provided through your Pipecat Cloud account
-
-### 5. Configure to run locally (optional)
-
-You can test your agent locally before deploying to Pipecat Cloud:
-
-```bash
-# Set environment variables with your API keys
-export CARTESIA_API_KEY="your_cartesia_key"
-export DAILY_API_KEY="your_daily_key"
-export OPENAI_API_KEY="your_openai_key"
-```
-
-> Your `DAILY_API_KEY` can be found at [https://pipecat.daily.co](https://pipecat.daily.co) under the `Settings` in the `Daily (WebRTC)` tab.
-
-First install requirements:
-
-```bash
-pip install -r requirements.txt
-```
-
-Then, launch the bot.py script locally:
-
-```bash
-LOCAL_RUN=1 python bot.py
-```
-
-## Deploy & Run
-
-### 1. Build and push your Docker image
-
-```bash
-# Build the image (targeting ARM architecture for cloud deployment)
-docker build --platform=linux/arm64 -t my-first-agent:latest .
-
-# Tag with your Docker username and version
-docker tag my-first-agent:latest your-username/my-first-agent:0.1
-
-# Push to Docker Hub
-docker push your-username/my-first-agent:0.1
-```
-
-### 2. Create a secret set for your API keys
-
-The starter project requires API keys for OpenAI and Cartesia:
-
-```bash
-# Copy the example env file
-cp env.example .env
-
-# Edit .env to add your API keys:
-# CARTESIA_API_KEY=your_cartesia_key
-# OPENAI_API_KEY=your_openai_key
-
-# Create a secret set from your .env file
-pcc secrets set my-first-agent-secrets --file .env
-```
-
-Alternatively, you can create secrets directly via CLI:
-
-```bash
-pcc secrets set my-first-agent-secrets \
-  CARTESIA_API_KEY=your_cartesia_key \
-  OPENAI_API_KEY=your_openai_key
-```
-
-### 3. Deploy to Pipecat Cloud
-
-```bash
-pcc deploy my-first-agent your-username/my-first-agent:0.1 --secrets my-first-agent-secrets
-```
-
-> **Note (Optional)**: For a more maintainable approach, you can use the included `pcc-deploy.toml` file:
->
-> ```toml
-> agent_name = "my-first-agent"
-> image = "your-username/my-first-agent:0.1"
-> secret_set = "my-first-agent-secrets"
->
-> [scaling]
->     min_instances = 0
-> ```
->
-> Then simply run `pcc deploy` without additional arguments.
-
-> **Note**: If your repository is private, you'll need to add credentials:
->
-> ```bash
-> # Create pull secret (you’ll be prompted for credentials)
-> pcc secrets image-pull-secret pull-secret https://index.docker.io/v1/
->
-> # Deploy with credentials
-> pcc deploy my-first-agent your-username/my-first-agent:0.1 --credentials pull-secret
-> ```
-
-### 4. Check deployment and scaling (optional)
-
-By default, your agent will use "scale-to-zero" configuration, which means it may have a cold start of around 10 seconds when first used. By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
-
-For more responsive testing, you can scale your deployment to keep a minimum of one instance warm:
-
-```bash
-# Ensure at least one warm instance is always available
-pcc deploy my-first-agent your-username/my-first-agent:0.1 --min-instances 1
-
-# Check the status of your deployment
-pcc agent status my-first-agent
-```
-
-By default, idle instances are maintained for 5 minutes before being terminated when using scale-to-zero.
-
-### 5. Create an API key
-
-```bash
-# Create a public API key for accessing your agent
-pcc organizations keys create
-
-# Set it as the default key to use with your agent
-pcc organizations keys use
-```
-
-### 6. Start your agent
-
-```bash
-# Start a session with your agent in a Daily room
-pcc agent start my-first-agent --use-daily
-```
-
-This will return a URL, which you can use to connect to your running agent.
-
-## Documentation
-
-For more details on Pipecat Cloud and its capabilities:
-
-- [Pipecat Cloud Documentation](https://docs.pipecat.daily.co)
-- [Pipecat Project Documentation](https://docs.pipecat.ai)
-
-## Support
-
-Join our [Discord community](https://discord.gg/dailyco) for help and discussions.

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

@@ -1,161 +0,0 @@
-#
-# Copyright (c) 2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from pipecatcloud.agent import DailySessionArguments
-
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMMessagesFrame
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
-
-# Check if we're in local development mode
-LOCAL_RUN = os.getenv("LOCAL_RUN")
-if LOCAL_RUN:
-    import asyncio
-    import webbrowser
-
-    try:
-        from local_runner import configure
-    except ImportError:
-        logger.error("Could not import local_runner module. Local development mode may not work.")
-
-# Load environment variables
-load_dotenv(override=True)
-
-
-async def main(room_url: str, token: str):
-    """Main pipeline setup and execution function.
-
-    Args:
-        room_url: The Daily room URL
-        token: The Daily room token
-    """
-    logger.debug("Starting bot in room: {}", room_url)
-
-    transport = DailyTransport(
-        room_url,
-        token,
-        "bot",
-        DailyParams(
-            audio_in_enabled=True,
-            audio_out_enabled=True,
-            transcription_enabled=True,
-            vad_analyzer=SileroVADAnalyzer(),
-        ),
-    )
-
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"), voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22"
-    )
-
-    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(),
-            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):
-        logger.info("First participant joined: {}", participant["id"])
-        await transport.capture_participant_transcription(participant["id"])
-        # Kick off the conversation.
-        messages.append(
-            {
-                "role": "system",
-                "content": "Please start with 'Hello World' and introduce yourself to the user.",
-            }
-        )
-        await task.queue_frames([LLMMessagesFrame(messages)])
-
-    @transport.event_handler("on_participant_left")
-    async def on_participant_left(transport, participant, reason):
-        logger.info("Participant left: {}", participant)
-        await task.cancel()
-
-    runner = PipelineRunner()
-
-    await runner.run(task)
-
-
-async def bot(args: DailySessionArguments):
-    """Main bot entry point compatible with the FastAPI route handler.
-
-    Args:
-        room_url: The Daily room URL
-        token: The Daily room token
-        body: The configuration object from the request body
-        session_id: The session ID for logging
-    """
-    logger.info(f"Bot process initialized {args.room_url} {args.token}")
-
-    try:
-        await main(args.room_url, args.token)
-        logger.info("Bot process completed")
-    except Exception as e:
-        logger.exception(f"Error in bot process: {str(e)}")
-        raise
-
-
-# Local development functions
-async def local_main():
-    """Function for local development testing."""
-    try:
-        async with aiohttp.ClientSession() as session:
-            (room_url, token) = await configure(session)
-            logger.warning("_")
-            logger.warning("_")
-            logger.warning(f"Talk to your voice agent here: {room_url}")
-            logger.warning("_")
-            logger.warning("_")
-            webbrowser.open(room_url)
-            await main(room_url, token)
-    except Exception as e:
-        logger.exception(f"Error in local development mode: {e}")
-
-
-# Local development entry point
-if LOCAL_RUN and __name__ == "__main__":
-    try:
-        asyncio.run(local_main())
-    except Exception as e:
-        logger.exception(f"Failed to run in local mode: {e}")

examples/deployment/pipecat-cloud-example/env.example

@@ -1,2 +0,0 @@
-CARTESIA_API_KEY=
-OPENAI_API_KEY=

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

@@ -1,46 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import os
-
-import aiohttp
-
-from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
-
-
-async def configure(aiohttp_session: aiohttp.ClientSession):
-    (url, token) = await configure_with_args(aiohttp_session)
-    return (url, token)
-
-
-async def configure_with_args(aiohttp_session: aiohttp.ClientSession = None):
-    key = os.getenv("DAILY_API_KEY")
-    if not key:
-        raise Exception(
-            "No Daily API key specified. set DAILY_API_KEY in your environment to specify a Daily API key, available from https://dashboard.daily.co/developers."
-        )
-
-    daily_rest_helper = DailyRESTHelper(
-        daily_api_key=key,
-        daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
-        aiohttp_session=aiohttp_session,
-    )
-
-    room = await daily_rest_helper.create_room(
-        DailyRoomParams(properties={"enable_prejoin_ui": False})
-    )
-    if not room.url:
-        raise HTTPException(status_code=500, detail="Failed to create room")
-
-    url = room.url
-
-    # Create a meeting token for the given room with an expiration 1 hour in
-    # the future.
-    expiry_time: float = 60 * 60
-
-    token = await daily_rest_helper.get_token(url, expiry_time)
-
-    return (url, token)

examples/deployment/pipecat-cloud-example/pcc-deploy.toml

@@ -1,6 +0,0 @@
-agent_name = "my-first-agent"
-image = "your-username/my-first-agent:0.1"
-secret_set = "my-first-agent-secrets"
-
-[scaling]
-	min_instances = 0

examples/deployment/pipecat-cloud-example/requirements.txt

@@ -1,3 +0,0 @@
-pipecatcloud
-pipecat-ai[cartesia,daily,openai,silero]>=0.0.58
-python-dotenv~=1.0.1

examples/fal-smart-turn/.gitignore

@@ -1,51 +0,0 @@
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-.Python
-build/
-dist/
-*.egg-info/
-.installed.cfg
-*.egg
-.pytest_cache/
-.coverage
-.coverage.*
-.env
-.venv
-env/
-venv/
-ENV/
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# JavaScript/Node.js
-node_modules/
-dist/
-dist-ssr/
-*.local
-.env.local
-.env.development.local
-.env.test.local
-.env.production.local
-
-# Logs
-logs/
-*.log
-npm-debug.log*
-yarn-debug.log*
-yarn-error.log*
-pnpm-debug.log*
-
-# Editor/IDE
-.vscode/*
-!.vscode/extensions.json
-.idea/
-*.swp
-*.swo
-.DS_Store
-
-# Project specific
-runpod.toml

examples/fal-smart-turn/README.md

@@ -1,152 +0,0 @@
-# Smart Turn Detection Demo
-
-This demo showcases Pipecat's Smart Turn Detection feature - an advanced conversational turn detection system that uses machine learning to identify when a speaker has finished their turn in a conversation. Unlike basic Voice Activity Detection (VAD) which only detects speech vs. silence, Smart Turn detects natural conversational cues like intonation patterns, pacing, and linguistic signals.
-
-This demo uses the [pipecat-ai/smart-turn](https://huggingface.co/pipecat-ai/smart-turn) model - an open-source, community-driven conversational turn detection model designed to provide more natural turn-taking in voice interactions. The model is being hosted on Fal's infrastructure for GPU acceleration, offering inference times between 50-60ms.
-
-In the client UI, you can see the transcription messages along with the smart-turn model's prediction results in real-time.
-
-## Try the demo
-
-Try the hosted version of the demo here: https://pcc-smart-turn.vercel.app/.
-
-## Run the demo locally
-
-### Run the Server
-
-1. Set up and activate your virtual environment:
-
-   ```bash
-   python3 -m venv venv
-   source venv/bin/activate  # On Windows: venv\Scripts\activate
-   ```
-
-2. Install dependencies:
-
-   ```bash
-   pip install -r requirements.txt
-   ```
-
-3. Create your .env file and set your env vars:
-
-   ```bash
-   cp env.example .env
-   ```
-
-   Keys to provide:
-
-   - GOOGLE_API_KEY
-   - CARTESIA_API_KEY
-   - DEEPGRAM_API_KEY
-   - DAILY_API_KEY
-   - FAL_SMART_TURN_API_KEY
-
-4. Run the server:
-
-   ```bash
-   LOCAL=1 python server.py
-   ```
-
-### Run the client
-
-1. Open a new terminal and navigate to the client directory:
-
-   ```bash
-   cd client
-   ```
-
-2. Install dependencies:
-
-   ```bash
-   npm install
-   ```
-
-3. Create your .env.local file:
-
-   ```bash
-   cp env.local.example .env.local
-   ```
-
-   > Note: No keys need to be modified. `NEXT_PUBLIC_API_BASE_URL` is already configured for local use.
-
-4. Start the development server:
-
-   ```bash
-   npm run dev
-   ```
-
-5. Open [http://localhost:3000](http://localhost:3000) in your browser.
-
-## Deploy the app
-
-### Deploy the server to Pipecat Cloud
-
-1. Navigate to server
-
-   ```bash
-   cd server
-   ```
-
-2. You should already have a .env set up from running locally. If not, do that now.
-
-3. Update your build and deploy scripts.
-
-   - In build.sh, set `DOCKER_USERNAME` and `AGENT_NAME`.
-   - In pcc-deploy.toml, set `image`, which specifies where your Docker image is stored.
-
-4. Build your Docker image by running the build script:
-
-   ```bash
-   ./build.sh
-   ```
-
-   > Note: This builds, tags and pushes your docker image and assumes Docker Hub is the container registry.
-
-5. Make sure you have the Pipecat Cloud CLI installed:
-
-   ```bash
-   pip install pipecatcloud
-   ```
-
-6. Login via the Pipecat Cloud CLI:
-
-   ```bash
-   pcc auth login
-   ```
-
-   > Note: If you don't have an account, sign up at https://pipecat.daily.co.
-
-7. Add a secrets set:
-
-   ```bash
-   pcc secrets set pcc-smart-turn-secrets --file .env
-   ```
-
-8. Deploy your agent:
-
-   ```bash
-   pcc deploy
-   ```
-
-   > Note: This uses your pcc-deploy.toml settings. Modify as needed.
-
-### Deploy the client to Vercel
-
-This project uses TypeScript, React, and Next.js, making it a perfect fit for [Vercel](https://vercel.com/).
-
-- In your client directory, install Vercel's CLI tool: `npm install -g vercel`
-- Verify it's installed using `vercel --version`
-- Log in your Vercel account using `vercel login`
-- Deploy your client to Vercel using `vercel`
-
-Follow the vercel prompts to deploy your project.
-
-### Test your deployed app
-
-Now with the client and server deployed, you can join the call using your Vercel URL.
-
-See the debug information for the Smart Turn data. It prints a log line for each smart-turn inference:
-
-```
-Smart Turn: COMPLETE, Probability: 95.3%, Model inference: 65.23ms, Server processing: 82.09ms, End-to-end: 245.43ms
-```

examples/fal-smart-turn/client/.gitignore

@@ -1,41 +0,0 @@
-# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
-
-# dependencies
-/node_modules
-/.pnp
-.pnp.*
-.yarn/*
-!.yarn/patches
-!.yarn/plugins
-!.yarn/releases
-!.yarn/versions
-
-# 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*
-
-# env files (can opt-in for committing if needed)
-.env*
-
-# vercel
-.vercel
-
-# typescript
-*.tsbuildinfo
-next-env.d.ts

examples/fal-smart-turn/client/env.local.example

@@ -1,3 +0,0 @@
-NEXT_PUBLIC_API_BASE_URL=http://localhost:7860
-PIPECAT_CLOUD_API_KEY=
-AGENT_NAME=pcc-smart-turn

examples/fal-smart-turn/client/eslint.config.mjs

@@ -1,16 +0,0 @@
-import { dirname } from "path";
-import { fileURLToPath } from "url";
-import { FlatCompat } from "@eslint/eslintrc";
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-const compat = new FlatCompat({
-  baseDirectory: __dirname,
-});
-
-const eslintConfig = [
-  ...compat.extends("next/core-web-vitals", "next/typescript"),
-];
-
-export default eslintConfig;

examples/fal-smart-turn/client/next.config.ts

@@ -1,7 +0,0 @@
-import type { NextConfig } from "next";
-
-const nextConfig: NextConfig = {
-  /* config options here */
-};
-
-export default nextConfig;

examples/fal-smart-turn/client/package.json

@@ -1,28 +0,0 @@
-{
-  "name": "my-nextjs-app",
-  "version": "0.1.0",
-  "private": true,
-  "scripts": {
-    "dev": "next dev",
-    "build": "next build",
-    "start": "next start",
-    "lint": "next lint"
-  },
-  "dependencies": {
-    "@pipecat-ai/client-js": "^0.3.5",
-    "@pipecat-ai/client-react": "^0.3.5",
-    "@pipecat-ai/daily-transport": "^0.3.10",
-    "next": "15.3.1",
-    "react": "^19.0.0",
-    "react-dom": "^19.0.0"
-  },
-  "devDependencies": {
-    "@eslint/eslintrc": "^3",
-    "@types/node": "^20",
-    "@types/react": "^19",
-    "@types/react-dom": "^19",
-    "eslint": "^9",
-    "eslint-config-next": "15.2.3",
-    "typescript": "^5"
-  }
-}

examples/fal-smart-turn/client/public/favicon.svg

@@ -1,7 +0,0 @@
-<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M3.3088 5.05615C3.64682 4.92779 4.02833 5.02411 4.26653 5.29797L7.36884 8.86461H16.6312L19.7335 5.29797C19.9717 5.02411 20.3532 4.92779 20.6912 5.05615C21.0292 5.18452 21.253 5.51072 21.253 5.87504V13.75H24V15.5H19.5181V8.19909L17.6762 10.3167C17.5115 10.506 17.2738 10.6146 17.0241 10.6146H6.9759C6.72616 10.6146 6.48854 10.506 6.32383 10.3167L4.48193 8.19909V15.5H0V13.75H2.74699V5.87504C2.74699 5.51072 2.97078 5.18452 3.3088 5.05615Z" fill="black"/>
-<path d="M19.5181 17.25H24V19H19.5181V17.25Z" fill="black"/>
-<path d="M0 17.25H4.48193V19H0V17.25Z" fill="black"/>
-<path d="M9.25301 14.3333C9.25301 14.9777 8.73517 15.5 8.09639 15.5C7.4576 15.5 6.93976 14.9777 6.93976 14.3333C6.93976 13.689 7.4576 13.1667 8.09639 13.1667C8.73517 13.1667 9.25301 13.689 9.25301 14.3333Z" fill="black"/>
-<path d="M17.0602 14.3333C17.0602 14.9777 16.5424 15.5 15.9036 15.5C15.2648 15.5 14.747 14.9777 14.747 14.3333C14.747 13.689 15.2648 13.1667 15.9036 13.1667C16.5424 13.1667 17.0602 13.689 17.0602 14.3333Z" fill="black"/>
-</svg>

examples/fal-smart-turn/client/src/app/api/connect/route.ts

@@ -1,44 +0,0 @@
-import { NextResponse, NextRequest } from 'next/server';
-
-export async function POST(request: NextRequest) {
-  const { MY_CUSTOM_DATA } = await request.json();
-
-  try {
-    const response = await fetch(
-      `https://api.pipecat.daily.co/v1/public/${process.env.AGENT_NAME}/start`,
-      {
-        method: 'POST',
-        headers: {
-          Authorization: `Bearer ${process.env.PIPECAT_CLOUD_API_KEY}`,
-          'Content-Type': 'application/json',
-        },
-        body: JSON.stringify({
-          // Create Daily room
-          createDailyRoom: true,
-          // Optionally set Daily room properties
-          dailyRoomProperties: { start_video_off: true },
-          // Optionally pass custom data to the bot
-          body: { MY_CUSTOM_DATA },
-        }),
-      }
-    );
-
-    if (!response.ok) {
-      throw new Error(`API responded with status: ${response.status}`);
-    }
-
-    const data = await response.json();
-
-    // Transform the response to match what RTVI client expects
-    return NextResponse.json({
-      room_url: data.dailyRoom,
-      token: data.dailyToken,
-    });
-  } catch (error) {
-    console.error('API error:', error);
-    return NextResponse.json(
-      { error: 'Failed to start agent' },
-      { status: 500 }
-    );
-  }
-}

examples/fal-smart-turn/client/src/app/globals.css

@@ -1,82 +0,0 @@
-body {
-  margin: 0;
-  padding: 20px;
-  font-family: Arial, sans-serif;
-  background-color: #f0f0f0;
-}
-
-.app {
-  max-width: 1200px;
-  margin: 0 auto;
-}
-
-.status-bar {
-  display: flex;
-  justify-content: space-between;
-  align-items: center;
-  padding: 10px;
-  background-color: #fff;
-  border-radius: 8px;
-  margin-bottom: 20px;
-}
-
-.controls button {
-  padding: 8px 16px;
-  margin-left: 10px;
-  border: none;
-  border-radius: 4px;
-  cursor: pointer;
-}
-
-button:disabled {
-  opacity: 0.5;
-  cursor: not-allowed;
-}
-
-.connect-btn {
-  background-color: #4caf50;
-  color: white;
-}
-
-.disconnect-btn {
-  background-color: #f44336;
-  color: white;
-}
-
-.main-content {
-  background-color: #fff;
-  border-radius: 8px;
-  padding: 20px;
-  margin-bottom: 20px;
-}
-
-.bot-container {
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-}
-
-.video-container {
-  width: 640px;
-  height: 360px;
-  background-color: #ddd;
-  margin-bottom: 20px;
-  border-radius: 8px;
-  overflow: hidden;
-}
-
-.video-container video {
-  width: 100%;
-  height: 100%;
-  object-fit: cover;
-}
-
-.mic-enabled {
-  background-color: #4caf50;
-  color: white;
-}
-
-.mic-disabled {
-  background-color: #f44336;
-  color: white;
-}

examples/fal-smart-turn/client/src/app/layout.tsx

@@ -1,27 +0,0 @@
-import './globals.css';
-import { RTVIProvider } from '@/providers/RTVIProvider';
-
-export const metadata = {
-  title: 'Pipecat React Client',
-  description: 'Pipecat RTVI Client using Next.js',
-  icons: {
-    icon: [{ url: '/favicon.svg', type: 'image/svg+xml' }],
-  },
-};
-
-export default function RootLayout({
-  children,
-}: {
-  children: React.ReactNode;
-}) {
-  return (
-    <html lang="en">
-      <head>
-        <link rel="icon" href="/favicon.svg" type="image/svg+xml" />
-      </head>
-      <body>
-        <RTVIProvider>{children}</RTVIProvider>
-      </body>
-    </html>
-  );
-}

examples/fal-smart-turn/client/src/app/page.tsx

@@ -1,41 +0,0 @@
-'use client';
-
-import {
-  RTVIClientAudio,
-  RTVIClientVideo,
-  useRTVIClientTransportState,
-} from '@pipecat-ai/client-react';
-import { ConnectButton } from '../components/ConnectButton';
-import { StatusDisplay } from '../components/StatusDisplay';
-import { DebugDisplay } from '../components/DebugDisplay';
-
-function BotVideo() {
-  const transportState = useRTVIClientTransportState();
-  const isConnected = transportState !== 'disconnected';
-
-  return (
-    <div className="bot-container">
-      <div className="video-container">
-        {isConnected && <RTVIClientVideo participant="bot" fit="cover" />}
-      </div>
-    </div>
-  );
-}
-
-export default function Home() {
-  return (
-    <div className="app">
-      <div className="status-bar">
-        <StatusDisplay />
-        <ConnectButton />
-      </div>
-
-      <div className="main-content">
-        <BotVideo />
-      </div>
-
-      <DebugDisplay />
-      <RTVIClientAudio />
-    </div>
-  );
-}

examples/fal-smart-turn/client/src/components/ConnectButton.tsx

@@ -1,40 +0,0 @@
-import {
-  useRTVIClient,
-  useRTVIClientTransportState,
-} from '@pipecat-ai/client-react';
-
-export function ConnectButton() {
-  const client = useRTVIClient();
-  const transportState = useRTVIClientTransportState();
-  const isConnected = ['connected', 'ready'].includes(transportState);
-
-  const handleClick = async () => {
-    if (!client) {
-      console.error('RTVI client is not initialized');
-      return;
-    }
-
-    try {
-      if (isConnected) {
-        await client.disconnect();
-      } else {
-        await client.connect();
-      }
-    } catch (error) {
-      console.error('Connection error:', error);
-    }
-  };
-
-  return (
-    <div className="controls">
-      <button
-        className={isConnected ? 'disconnect-btn' : 'connect-btn'}
-        onClick={handleClick}
-        disabled={
-          !client || ['connecting', 'disconnecting'].includes(transportState)
-        }>
-        {isConnected ? 'Disconnect' : 'Connect'}
-      </button>
-    </div>
-  );
-}

examples/fal-smart-turn/client/src/components/DebugDisplay.css

@@ -1,26 +0,0 @@
-.debug-panel {
-  background-color: #fff;
-  border-radius: 8px;
-  padding: 20px;
-}
-
-.debug-panel h3 {
-  margin: 0 0 10px 0;
-  font-size: 16px;
-  font-weight: bold;
-}
-
-.debug-log {
-  height: 200px;
-  overflow-y: auto;
-  background-color: #f8f8f8;
-  padding: 10px;
-  border-radius: 4px;
-  font-family: monospace;
-  font-size: 12px;
-  line-height: 1.4;
-}
-
-.debug-log div {
-  margin-bottom: 4px;
-}

examples/fal-smart-turn/client/src/components/DebugDisplay.tsx

@@ -1,171 +0,0 @@
-import { useRef, useCallback } from 'react';
-import {
-  Participant,
-  RTVIEvent,
-  TransportState,
-  TranscriptData,
-  BotLLMTextData,
-} from '@pipecat-ai/client-js';
-import { useRTVIClient, useRTVIClientEvent } from '@pipecat-ai/client-react';
-import './DebugDisplay.css';
-
-interface SmartTurnResultData {
-  type: 'smart_turn_result';
-  is_complete: boolean;
-  probability: number;
-  inference_time_ms: number; // Pure model inference time
-  server_total_time_ms: number; // Server processing time
-  e2e_processing_time_ms: number; // Complete end-to-end time
-}
-
-export function DebugDisplay() {
-  const debugLogRef = useRef<HTMLDivElement>(null);
-  const client = useRTVIClient();
-
-  const log = useCallback((message: string) => {
-    if (!debugLogRef.current) return;
-
-    const entry = document.createElement('div');
-    entry.textContent = `${new Date().toISOString()} - ${message}`;
-
-    // Add styling based on message type
-    if (message.startsWith('User: ')) {
-      entry.style.color = '#2196F3'; // blue for user
-    } else if (message.startsWith('Bot: ')) {
-      entry.style.color = '#4CAF50'; // green for bot
-    } else if (message.includes('Smart Turn:')) {
-      entry.style.color = '#9C27B0'; // purple for smart turn
-    }
-
-    debugLogRef.current.appendChild(entry);
-    debugLogRef.current.scrollTop = debugLogRef.current.scrollHeight;
-  }, []);
-
-  // Log transport state changes
-  useRTVIClientEvent(
-    RTVIEvent.TransportStateChanged,
-    useCallback(
-      (state: TransportState) => {
-        log(`Transport state changed: ${state}`);
-      },
-      [log]
-    )
-  );
-
-  // Log bot connection events
-  useRTVIClientEvent(
-    RTVIEvent.BotConnected,
-    useCallback(
-      (participant?: Participant) => {
-        log(`Bot connected: ${JSON.stringify(participant)}`);
-      },
-      [log]
-    )
-  );
-
-  useRTVIClientEvent(
-    RTVIEvent.BotDisconnected,
-    useCallback(
-      (participant?: Participant) => {
-        log(`Bot disconnected: ${JSON.stringify(participant)}`);
-      },
-      [log]
-    )
-  );
-
-  // Log track events
-  useRTVIClientEvent(
-    RTVIEvent.TrackStarted,
-    useCallback(
-      (track: MediaStreamTrack, participant?: Participant) => {
-        log(
-          `Track started: ${track.kind} from ${participant?.name || 'unknown'}`
-        );
-      },
-      [log]
-    )
-  );
-
-  useRTVIClientEvent(
-    RTVIEvent.TrackStopped,
-    useCallback(
-      (track: MediaStreamTrack, participant?: Participant) => {
-        log(
-          `Track stopped: ${track.kind} from ${participant?.name || 'unknown'}`
-        );
-      },
-      [log]
-    )
-  );
-
-  // Log bot ready state and check tracks
-  useRTVIClientEvent(
-    RTVIEvent.BotReady,
-    useCallback(() => {
-      log(`Bot ready`);
-
-      if (!client) return;
-
-      const tracks = client.tracks();
-      log(
-        `Available tracks: ${JSON.stringify({
-          local: {
-            audio: !!tracks.local.audio,
-            video: !!tracks.local.video,
-          },
-          bot: {
-            audio: !!tracks.bot?.audio,
-            video: !!tracks.bot?.video,
-          },
-        })}`
-      );
-    }, [client, log])
-  );
-
-  // Log transcripts
-  useRTVIClientEvent(
-    RTVIEvent.UserTranscript,
-    useCallback(
-      (data: TranscriptData) => {
-        // Only log final transcripts
-        if (data.final) {
-          log(`User: ${data.text}`);
-        }
-      },
-      [log]
-    )
-  );
-
-  useRTVIClientEvent(
-    RTVIEvent.BotTranscript,
-    useCallback(
-      (data: BotLLMTextData) => {
-        log(`Bot: ${data.text}`);
-      },
-      [log]
-    )
-  );
-
-  useRTVIClientEvent(
-    RTVIEvent.ServerMessage,
-    useCallback(
-      (data: SmartTurnResultData) => {
-        log(
-          `Smart Turn:
-    ${data.is_complete ? 'COMPLETE' : 'INCOMPLETE'},
-    Probability: ${(data.probability * 100).toFixed(1)}%,
-    Model inference: ${data.inference_time_ms?.toFixed(2) || 'N/A'}ms,
-    Server processing: ${data.server_total_time_ms?.toFixed(2) || 'N/A'}ms,
-    End-to-end: ${data.e2e_processing_time_ms?.toFixed(2) || 'N/A'}ms`
-        );
-      },
-      [log]
-    )
-  );
-  return (
-    <div className="debug-panel">
-      <h3>Debug Info</h3>
-      <div ref={debugLogRef} className="debug-log" />
-    </div>
-  );
-}

examples/fal-smart-turn/client/src/components/StatusDisplay.tsx

@@ -1,11 +0,0 @@
-import { useRTVIClientTransportState } from '@pipecat-ai/client-react';
-
-export function StatusDisplay() {
-  const transportState = useRTVIClientTransportState();
-
-  return (
-    <div className="status">
-      Status: <span>{transportState}</span>
-    </div>
-  );
-}

examples/fal-smart-turn/client/src/providers/RTVIProvider.tsx

@@ -1,43 +0,0 @@
-'use client';
-
-import { RTVIClient } from '@pipecat-ai/client-js';
-import { DailyTransport } from '@pipecat-ai/daily-transport';
-import { RTVIClientProvider } from '@pipecat-ai/client-react';
-import { PropsWithChildren, useEffect, useState } from 'react';
-
-// Get the API base URL from environment variables
-// Default to "/api" if not specified
-// "/api" is the default for Next.js API routes and used
-// for the Pipecat Cloud deployed agent
-const API_BASE_URL = process.env.NEXT_PUBLIC_API_BASE_URL || '/api';
-
-console.log('Using API base URL:', API_BASE_URL);
-
-export function RTVIProvider({ children }: PropsWithChildren) {
-  const [client, setClient] = useState<RTVIClient | null>(null);
-
-  useEffect(() => {
-    const transport = new DailyTransport();
-
-    const rtviClient = new RTVIClient({
-      transport,
-      params: {
-        baseUrl: API_BASE_URL,
-        endpoints: {
-          connect: '/connect',
-        },
-        requestData: { foo: 'bar' },
-      },
-      enableMic: true,
-      enableCam: false,
-    });
-
-    setClient(rtviClient);
-  }, []);
-
-  if (!client) {
-    return null;
-  }
-
-  return <RTVIClientProvider client={client}>{children}</RTVIClientProvider>;
-}

examples/fal-smart-turn/client/tsconfig.json

@@ -1,28 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "ES2017",
-    "lib": ["dom", "dom.iterable", "esnext"],
-    "allowJs": true,
-    "skipLibCheck": true,
-    "strict": true,
-    "noEmit": true,
-    "esModuleInterop": true,
-    "module": "esnext",
-    "moduleResolution": "bundler",
-    "resolveJsonModule": true,
-    "isolatedModules": true,
-    "jsx": "preserve",
-    "incremental": true,
-    "plugins": [
-      {
-        "name": "next"
-      }
-    ],
-    "paths": {
-      "@/components/*": ["./src/components/*"],
-      "@/providers/*": ["./src/providers/*"]
-    }
-  },
-  "include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
-  "exclude": ["node_modules"]
-}

examples/fal-smart-turn/server/Dockerfile

@@ -1,8 +0,0 @@
-FROM dailyco/pipecat-base:latest
-
-COPY ./requirements.txt requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-
-COPY ./assets assets
-COPY ./bot.py bot.py

examples/fal-smart-turn/server/bot.py

@@ -1,299 +0,0 @@
-#
-# Copyright (c) 2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-from PIL import Image
-from pipecatcloud.agent import DailySessionArguments
-
-from pipecat.audio.turn.smart_turn.fal_smart_turn import FalSmartTurnAnalyzer
-from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.audio.vad.vad_analyzer import VADParams
-from pipecat.frames.frames import (
-    BotStartedSpeakingFrame,
-    BotStoppedSpeakingFrame,
-    Frame,
-    MetricsFrame,
-    OutputImageRawFrame,
-    SpriteFrame,
-)
-from pipecat.metrics.metrics import SmartTurnMetricsData
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.processors.frameworks.rtvi import (
-    RTVIConfig,
-    RTVIObserver,
-    RTVIProcessor,
-    RTVIServerMessageFrame,
-)
-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
-
-load_dotenv(override=True)
-
-# Check if we're in local development mode
-LOCAL = os.getenv("LOCAL")
-
-logger.remove()
-logger.add(sys.stderr, level="DEBUG")
-
-sprites = []
-script_dir = os.path.dirname(__file__)
-
-# Load sequential animation frames
-for i in range(1, 26):
-    # Build the full path to the image file
-    full_path = os.path.join(script_dir, f"assets/robot0{i}.png")
-    # Get the filename without the extension to use as the dictionary key
-    # Open the image and convert it to bytes
-    with Image.open(full_path) as img:
-        sprites.append(OutputImageRawFrame(image=img.tobytes(), size=img.size, format=img.format))
-
-# Create a smooth animation by adding reversed frames
-flipped = sprites[::-1]
-sprites.extend(flipped)
-
-# Define static and animated states
-quiet_frame = sprites[0]  # Static frame for when bot is listening
-talking_frame = SpriteFrame(images=sprites)  # Animation sequence for when bot is talking
-
-
-class TalkingAnimation(FrameProcessor):
-    """Manages the bot's visual animation states.
-
-    Switches between static (listening) and animated (talking) states based on
-    the bot's current speaking status.
-    """
-
-    def __init__(self):
-        super().__init__()
-        self._is_talking = False
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process incoming frames and update animation state.
-
-        Args:
-            frame: The incoming frame to process
-            direction: The direction of frame flow in the pipeline
-        """
-        await super().process_frame(frame, direction)
-
-        # Switch to talking animation when bot starts speaking
-        if isinstance(frame, BotStartedSpeakingFrame):
-            if not self._is_talking:
-                await self.push_frame(talking_frame)
-                self._is_talking = True
-        # Return to static frame when bot stops speaking
-        elif isinstance(frame, BotStoppedSpeakingFrame):
-            await self.push_frame(quiet_frame)
-            self._is_talking = False
-
-        await self.push_frame(frame, direction)
-
-
-class SmartTurnMetricsProcessor(FrameProcessor):
-    """Processes the metrics data from Smart Turn Analyzer.
-
-    This processor is responsible for handling smart turn metrics data
-    and forwarding it to the client UI via RTVI.
-    """
-
-    async def process_frame(self, frame: Frame, direction: FrameDirection):
-        """Process incoming frames and handle Smart Turn metrics.
-
-        Args:
-            frame: The incoming frame to process
-            direction: The direction of frame flow in the pipeline
-        """
-        await super().process_frame(frame, direction)
-
-        # Handle Smart Turn metrics
-        if isinstance(frame, MetricsFrame):
-            for metrics in frame.data:
-                if isinstance(metrics, SmartTurnMetricsData):
-                    logger.info(f"Smart Turn metrics: {metrics}")
-
-                    # Create a payload with the smart turn prediction data
-                    smart_turn_data = {
-                        "type": "smart_turn_result",
-                        "is_complete": metrics.is_complete,
-                        "probability": metrics.probability,
-                        "inference_time_ms": metrics.inference_time_ms,
-                        "server_total_time_ms": metrics.server_total_time_ms,
-                        "e2e_processing_time_ms": metrics.e2e_processing_time_ms,
-                    }
-
-                    # Send the data to the client via RTVI
-                    rtvi_frame = RTVIServerMessageFrame(data=smart_turn_data)
-                    await self.push_frame(rtvi_frame)
-
-        await self.push_frame(frame, direction)
-
-
-async def main(transport: DailyTransport):
-    # Configure your STT, LLM, and TTS services here
-    # Swap out different processors or properties to customize your bot
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-    llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
-    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-    )
-
-    # Set up the initial context for the conversation
-    # You can specified initial system and assistant messages here
-    messages = [
-        {
-            "role": "system",
-            "content": "You are Chatbot, a friendly, helpful robot. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way, but keep your responses brief. Start by introducing yourself.",
-        },
-    ]
-
-    # This sets up the LLM context by providing messages and tools
-    context = OpenAILLMContext(messages)
-    context_aggregator = llm.create_context_aggregator(context)
-
-    ta = TalkingAnimation()
-    smart_turn_metrics_processor = SmartTurnMetricsProcessor()
-
-    # RTVI events for Pipecat client UI
-    rtvi = RTVIProcessor(config=RTVIConfig(config=[]))
-
-    # A core voice AI pipeline
-    # Add additional processors to customize the bot's behavior
-    pipeline = Pipeline(
-        [
-            transport.input(),
-            rtvi,
-            smart_turn_metrics_processor,
-            stt,
-            context_aggregator.user(),
-            llm,
-            tts,
-            ta,
-            transport.output(),
-            context_aggregator.assistant(),
-        ]
-    )
-
-    task = PipelineTask(
-        pipeline,
-        params=PipelineParams(
-            allow_interruptions=True,
-            enable_metrics=True,
-            enable_usage_metrics=True,
-        ),
-        observers=[RTVIObserver(rtvi)],
-    )
-
-    @rtvi.event_handler("on_client_ready")
-    async def on_client_ready(rtvi):
-        logger.debug("Client ready event received")
-        await rtvi.set_bot_ready()
-        # Kick off the conversation
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
-
-    @transport.event_handler("on_first_participant_joined")
-    async def on_first_participant_joined(transport, participant):
-        logger.info("First participant joined: {}", participant["id"])
-        # Push a static frame to show the bot is listening
-        await task.queue_frame(quiet_frame)
-
-    @transport.event_handler("on_participant_left")
-    async def on_participant_left(transport, participant, reason):
-        logger.info("Participant left: {}", participant)
-        await task.cancel()
-
-    runner = PipelineRunner(handle_sigint=False, force_gc=True)
-
-    await runner.run(task)
-
-
-async def bot(args: DailySessionArguments):
-    """Main bot entry point compatible with the FastAPI route handler.
-
-    Args:
-        room_url: The Daily room URL
-        token: The Daily room token
-        body: The configuration object from the request body
-        session_id: The session ID for logging
-    """
-    from pipecat.audio.filters.krisp_filter import KrispFilter
-
-    logger.info(f"Bot process initialized {args.room_url} {args.token}")
-    async with aiohttp.ClientSession() as session:
-        transport = DailyTransport(
-            args.room_url,
-            args.token,
-            "Smart Turn Bot",
-            params=DailyParams(
-                audio_in_enabled=True,
-                audio_in_filter=KrispFilter(),
-                audio_out_enabled=True,
-                video_out_enabled=True,
-                video_out_width=1024,
-                video_out_height=576,
-                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                turn_analyzer=FalSmartTurnAnalyzer(
-                    api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=session
-                ),
-            ),
-        )
-
-        try:
-            await main(transport)
-            logger.info("Bot process completed")
-        except Exception as e:
-            logger.exception(f"Error in bot process: {str(e)}")
-            raise
-
-
-# Local development
-async def local_daily():
-    """Daily transport for local development."""
-    from runner import configure
-
-    try:
-        async with aiohttp.ClientSession() as session:
-            (room_url, token) = await configure(session)
-            transport = DailyTransport(
-                room_url,
-                token,
-                "Smart Turn Bot",
-                params=DailyParams(
-                    audio_in_enabled=True,
-                    audio_out_enabled=True,
-                    video_out_enabled=True,
-                    video_out_width=1024,
-                    video_out_height=576,
-                    vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-                    turn_analyzer=FalSmartTurnAnalyzer(
-                        api_key=os.getenv("FAL_SMART_TURN_API_KEY"), aiohttp_session=session
-                    ),
-                ),
-            )
-
-            await main(transport)
-    except Exception as e:
-        logger.exception(f"Error in local development mode: {e}")
-
-
-# Local development entry point
-if LOCAL and __name__ == "__main__":
-    try:
-        asyncio.run(local_daily())
-    except Exception as e:
-        logger.exception(f"Failed to run in local mode: {e}")

examples/fal-smart-turn/server/build.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-set -e
-
-VERSION="0.1"
-DOCKER_USERNAME=""
-AGENT_NAME="pcc-smart-turn"
-
-# Build the Docker image with the correct context
-echo "Building Docker image..."
-docker build --platform=linux/arm64 -t "$DOCKER_USERNAME/$AGENT_NAME:$VERSION" -t "$DOCKER_USERNAME/$AGENT_NAME:latest" .
-
-# Push the Docker images
-echo "Pushing Docker image $DOCKER_USERNAME/$AGENT_NAME:$VERSION..."
-docker push "$DOCKER_USERNAME/$AGENT_NAME:$VERSION"
-
-echo "Pushing Docker image $DOCKER_USERNAME/$AGENT_NAME:latest..."
-docker push "$DOCKER_USERNAME/$AGENT_NAME:latest"
-
-echo "Successfully built and pushed $DOCKER_USERNAME/$AGENT_NAME:$VERSION and $DOCKER_USERNAME/$AGENT_NAME:latest"

examples/fal-smart-turn/server/env.example

@@ -1,5 +0,0 @@
-GOOGLE_API_KEY=
-CARTESIA_API_KEY=
-DEEPGRAM_API_KEY=
-DAILY_API_KEY=
-FAL_SMART_TURN_API_KEY=

examples/fal-smart-turn/server/pcc-deploy.toml

@@ -1,7 +0,0 @@
-agent_name = "pcc-smart-turn"
-image = "your-username/pcc-smart-turn:0.1"
-secret_set = "pcc-smart-turn-secrets"
-enable_krisp = true
-
-[scaling]
-	min_instances = 0

examples/fal-smart-turn/server/requirements.txt

@@ -1,3 +0,0 @@
-pipecatcloud
-pipecat-ai[google,daily,deepgram,cartesia,silero]
-python-dotenv