Merge pull request #2640 from pipecat-ai/aleix/pipecat-0.0.85

update CHANGELOG for 0.0.85

.github/workflows/coverage.yaml

@@ -25,7 +25,7 @@ jobs:
           version: "latest"
 
       - name: Set up Python
-        run: uv python install 3.10
+        run: uv python install 3.12
 
       - name: Install system packages
         run: |

.github/workflows/sync-quickstart.yaml

@@ -23,17 +23,12 @@ jobs:
           token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
           path: quickstart-repo
 
-      - name: Sync files (excluding READMEs)
+      - name: Sync files (excluding uv.lock and README.md)
         run: |
-          # Copy code files only, skip READMEs
-          cp examples/quickstart/bot.py quickstart-repo/
-          cp examples/quickstart/requirements.txt quickstart-repo/
-          cp examples/quickstart/env.example quickstart-repo/
-
-          # Copy any other files that aren't README.md
+          # Copy all files except uv.lock and README.md
           find examples/quickstart -type f \
             -not -name "README.md" \
-            -not -name "*.md" \
+            -not -name "uv.lock" \
             -exec cp {} quickstart-repo/ \;
 
       - name: Commit and push changes

.github/workflows/tests.yaml

@@ -29,7 +29,7 @@ jobs:
           version: "latest"
 
       - name: Set up Python
-        run: uv python install 3.10
+        run: uv python install 3.12
 
       - name: Install system packages
         run: |

.github/workflows/update-lockfile.yaml

@@ -1,42 +0,0 @@
-name: Update lockfile
-
-on:
-  push:
-    paths:
-      - 'pyproject.toml'
-    branches:
-      - main
-  workflow_dispatch: # Allows manual triggering from GitHub UI
-
-jobs:
-  update-lockfile:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          # This gives the workflow permission to push back to the repo
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Install uv
-        uses: astral-sh/setup-uv@v1
-
-      - name: Update lockfile
-        run: uv lock
-
-      - name: Check for changes
-        id: verify-changed-files
-        run: |
-          if [ -n "$(git status --porcelain)" ]; then
-            echo "changed=true" >> $GITHUB_OUTPUT
-          else
-            echo "changed=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Commit lockfile
-        if: steps.verify-changed-files.outputs.changed == 'true'
-        run: |
-          git config --local user.email "action@github.com"  
-          git config --local user.name "GitHub Action"
-          git add uv.lock
-          git commit -m "chore: update uv.lock after dependency changes"
-          git push

CHANGELOG.md

@@ -5,18 +5,645 @@ 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
+## [0.0.85] - 2025-09-12
+
+### Added
+
+- `AzureSTTService` now pushes interim transcriptions.
+
+- Added `voice_cloning_key` to `GoogleTTSService` to support custom cloned
+  voices.
+
+- Added `speaking_rate` to `GoogleTTSService.InputParams` to control the
+  speaking rate.
+
+- Added a `speed` arg to `OpenAITTSService` to control the speed of the voice
+  response.
+
+- Added `FrameProcessor.push_interruption_task_frame_and_wait()`. Use this
+  method to programatically interrupt the bot from any part of the
+  pipeline. This guarantees that all the processors in the pipeline are
+  interrupted in order (from upstream to downstream). Internally, this works by
+  first pushing an `InterruptionTaskFrame` upstream until it reaches the
+  pipeline task. The pipeline task then generates an `InterruptionFrame`, which
+  flows downstream through all processors. Once the `InterruptionFrame` has
+  reaches the processor waiting for the interruption, the function returns and
+  execution continues after the call. Think of it as sending an upstream request
+  for interruption and waiting until the acknowledgment flows back downstream.
+
+- Added new base `TaskFrame` (which is a system frame). This is the base class
+  for all task frames (`EndTaskFrame`, `CancelTaskFrame`, etc.) that are meant
+  to be pushed upstream to reach the pipeline task.
+
+- Expanded support for universal `LLMContext` to the AWS Bedrock LLM service.
+  Using the universal `LLMContext` and associated `LLMContextAggregatorPair` is
+  a pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
+
+- Added new fields to the development runner's `parse_telephony_websocket`
+  method in support of providing dynamic data to a bot.
+
+  - Twilio: Added a new `body` parameter, which parses the websocket message
+    for `customParameters`. Provide data via the `Parameter` nouns in your
+    TwiML to use this feature.
+  - Telnyx & Exotel: Both providers make the `to` and `from` phone numbers
+    available in the websocket messages. You can now access these numbers as
+    `call_data["to"]` and `call_data["from"]`.
+
+  Note: Each telephony provider offers different features. Refer to the
+  corresponding example in `pipecat-examples` to see how to pass custom data
+  to your bot.
+
+- Added `body` to the `WebsocketRunnerArguments` as an optional parameter.
+  Custom `body` information can be passed from the server into the bot file via
+  the `bot()` method using this new parameter.
+
+- Added video streaming support to `LiveKitTransport`.
+
+- Added `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService` which provide
+  access to OpenAI Realtime.
 
 ### Changed
 
+- `pipeline.tests.utils.run_test()` now allows passing `PipelineParams` instead
+  of individual parameters.
+
+### Removed
+
+- Remove `VisionImageRawFrame` in favor of context frames (`LLMContextFrame` or
+  `OpenAILLMContextFrame`).
+
+### Deprecated
+
+- `BotInterruptionFrame` is now deprecated, use `InterruptionTaskFrame` instead.
+
+- `StartInterruptionFrame` is now deprected, use `InterruptionFrame` instead.
+
+- Deprecate `VisionImageFrameAggregator` because `VisionImageRawFrame` has been
+  removed. See the `12*` examples for the new recommended replacement pattern.
+
+- `NoisereduceFilter` is now deprecated and will be removed in a future
+  version. Use other audio filters like `KrispFilter` or `AICFilter`.
+
+- Deprecated `OpenAIRealtimeBetaLLMService` and `AzureRealtimeBetaLLMService`.
+  Use `OpenAIRealtimeLLMService` and `AzureRealtimeLLMService`, respectively.
+  Each service will be removed in an upcoming version, 1.0.0.
+
+### Fixed
+
+- Fixed a `BaseOutputTransport` issue that caused incorrect detection of when
+  the bot stopped talking while using an audio mixer.
+
+- Fixed a `LiveKitTransport` issue where RTVI messages were not properly
+  encoded.
+
+- Add additional fixups to Mistral context messages to ensure they meet
+  Mistral-specific requirements, avoiding Mistral "invalid request" errors.
+
+- Fixed `DailyTransport` transcription handling to gracefully handle missing
+  `rawResponse` field in transcription messages, preventing KeyError crashes.
+
+## [0.0.84] - 2025-09-05
+
+### Added
+
+- Add the ability to send DTMF to `LiveKitTransport`.
+
+- Expanded support for universal `LLMContext` to the Anthropic LLM service.
+  Using the universal `LLMContext` and associated `LLMContextAggregatorPair` is
+  a pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
+
+### Changed
+
+- Updated `daily-python` to 0.19.9.
+
+- Restored `DailyTransport`'s native DTMF support using Daily's `send_dtmf()`
+  method instead of generated audio tones.
+
+### Fixed
+
+- Fixed a `AWSBedrockLLMService` crash caused by an extra `await`.
+
+- Fixed a `OpenAIImageGenService` issue where it was not creating
+  `URLImageRawFrame` correctly.
+
+## [0.0.83] - 2025-09-03
+
+### Added
+
+- Added multilingual support for AsyncAI in `AsyncAITTSService` and `AsyncAIHttpTTSService`.
+
+  - New `languages`: `es`, `fr`, `de`, `it`.
+
+- Added new frames `InputTransportMessageUrgentFrame` and
+  `DailyInputTransportMessageUrgentFrame` for transport messages received from
+  external sources.
+
+- Added `UserSpeakingFrame`. This will be sent upstream and downstream while VAD
+  detects the user is speaking.
+
+- Expanded support for universal `LLMContext` to more LLM services. Using the
+  universal `LLMContext` and associated `LLMContextAggregatorPair` is a
+  pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
+  Here are the newly-supported services:
+
+  - Azure
+  - Cerebras
+  - Deepseek
+  - Fireworks AI
+  - Google Vertex AI
+  - Grok
+  - Groq
+  - Mistral
+  - NVIDIA NIM
+  - Ollama
+  - OpenPipe
+  - OpenRouter
+  - Perplexity
+  - Qwen
+  - SambaNova
+  - Together.ai
+
+- Added support for WhatsApp User-initiated Calls.
+
+- Added new audio filter `AICFilter`, speech enhancement for improving VAD/STT
+  performance, no ONNX dependency.
+  See https://ai-coustics.com/sdk/
+
+- Added a timeout around cancel input tasks to prevent indefinite hangs when
+  cancellation is swallowed by third-party code.
+
+- Added `pipecat.extensions.ivr` for automated IVR system navigation with
+  configurable goals and conversation handling. Supports DTMF input, verbal
+  responses, and intelligent menu traversal.
+
+  Basic usage:
+
+  ```python
+  from pipecat.extensions.ivr.ivr_navigator import IVRNavigator
+
+  # Create IVR navigator with your goal
+  ivr_navigator = IVRNavigator(
+      llm=llm_service,
+      ivr_prompt="Navigate to billing department to dispute a charge"
+  )
+
+  # Handle different outcomes
+  @ivr_navigator.event_handler("on_conversation_detected")
+  async def on_conversation(processor, conversation_history):
+      # Switch to normal conversation mode
+      pass
+
+  @ivr_navigator.event_handler("on_ivr_status_changed")
+  async def on_ivr_status(processor, status):
+      if status == IVRStatus.COMPLETED:
+          # End pipeline, transfer call, or start bot conversation
+      elif status == IVRStatus.STUCK:
+          # Handle navigation failure
+  ```
+
+- `BaseOutputTransport` now implements `write_dtmf()` by loading DTMF audio and
+  sending it through the transport. This makes sending DTMF generic across all
+  output transports.
+
+- Added new config parameters to `GladiaSTTService`.
+  - PreProcessingConfig > `audio_enhancer` to enhance audio quality.
+  - CustomVocabularyItem > `pronunciations` and `language` to specify special
+    pronunciations and in which language it will be pronounced.
+
+### Changed
+
+- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` are also pushed
+  upstream.
+
+- `ParallelPipeline` now waits for `CancelFrame` to finish in all branches
+  before pushing it downstream.
+
+- Added `sip_codecs` to the `DailyRoomSipParams`.
+
+- Updated the `configure()` function in `pipecat.runner.daily` to include new
+  args to create SIP-enabled rooms. Additionally, added new args to control the
+  room and token expiration durations.
+
+- `pipecat.frames.frames.KeypadEntry` is deprecated and has been moved to
+  `pipecat.audio.dtmf.types.KeypadEntry`.
+
+- Updated `RimeTTSService`'s flush_audio message to conform with Rime's official
+  API.
+
+- Updated the default model for `CerebrasLLMService` to GPT-OSS-120B.
+
+### Removed
+
+- Remove `StopInterruptionFrame`. This was a legacy frame that was not being
+  used really anywhere and it didn't provide any useful meaning. It was only
+  pushed after `UserStoppedSpeakingFrame`, so developers can just use
+  `UserStoppedSpeakingFrame`.
+
+- `DailyTransport.write_dtmf()` has been removed in favor of the generic
+  `BaseOutputTransport.write_dtmf()`.
+
+- Remove deprecated `DailyTransport.send_dtmf()`.
+
+### Deprecated
+
+- Transports have been re-organized.
+
+  ```
+  pipecat.transports.network.small_webrtc        -> pipecat.transports.smallwebrtc.transport
+  pipecat.transports.network.webrtc_connection   -> pipecat.transports.smallwebrtc.connection
+  pipecat.transports.network.websocket_client    -> pipecat.transports.websocket.client
+  pipecat.transports.network.websocket_server    -> pipecat.transports.websocket.server
+  pipecat.transports.network.fastapi_websocket   -> pipecat.transports.websocket.fastapi
+  pipecat.transports.services.daily              -> pipecat.transports.daily.transport
+  pipecat.transports.services.helpers.daily_rest -> pipecat.transports.daily.utils
+  pipecat.transports.services.livekit            -> pipecat.transports.livekit.transport
+  pipecat.transports.services.tavus              -> pipecat.transports.tavus.transport
+  ```
+
+- `pipecat.frames.frames.KeypadEntry` is deprecated use
+  `pipecat.audio.dtmf.types.KeypadEntry` instead.
+
+### Fixed
+
+- Fixed an issue where messages received from the transport were always being resent.
+
+- Fixed `SmallWebRTCTransport` to not use `mid` to decide if the transceiver should
+  be `sendrecv` or not.
+
+- Fixed an issue where Deepgram swallowed `asyncio.CancelledError` during
+  disconnect, preventing tasks from being cancelled.
+
+- Fixed an issue where `PipelineTask` was not cleaning up the observers.
+
+### Performance
+
+- Reduced latency and improved memory performance in `Mem0MemoryService`.
+
+## [0.0.82] - 2025-08-28
+
+### Added
+
+- Added a new `LLMRunFrame` to trigger an LLM response:
+
+  ```python
+  await task.queue_frames([LLMRunFrame()])
+  ```
+
+  This replaces `OpenAILLMContextFrame`, which you’d previously typically use
+  like this:
+
+  ```python
+  await task.queue_frames([context_aggregator.user().get_context_frame()])
+  ```
+
+  Use this way of kicking off your conversation when you’ve already initialized
+  your context and are simply instructing the bot when to go:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+
+  # ...
+
+  @transport.event_handler("on_client_connected")
+  async def on_client_connected(transport, client):
+      # Kick off the conversation.
+      await task.queue_frames([LLMRunFrame()])
+  ```
+
+  Note that if you want to add new messages when kicking off the conversation,
+  you could use `LLMMessagesAppendFrame` with `run_llm=True` instead:
+
+  ```python
+  @transport.event_handler("on_client_connected")
+  async def on_client_connected(transport, client):
+      # Kick off the conversation.
+      await task.queue_frames([LLMMessagesAppendFrame(new_messages, run_llm=True)])
+  ```
+
+  In the rare case you don’t have a context aggregator in your pipeline, then
+  you may continue using a context frame.
+
+- Added support for switching between audio+text to text-only modes within the
+  same pipeline. This is done by pushing
+  `LLMConfigureOutputFrame(skip_tts=True)` to enter text-only mode, and
+  disabling it to return to audio+text. The LLM will still generate tokens and
+  add them to the context, but they will not be sent to TTS.
+
+- Added `skip_tts` field to `TextFrame`. This lets a text frame bypass TTS while
+  still being included in the LLM context. Useful for cases like structured text
+  that isn’t meant to be spoken but should still contribute to context.
+
+- Added a `cancel_timeout_secs` argument to `PipelineTask` which defines how
+  long the pipeline has to complete cancellation. When `PipelineTask.cancel()`
+  is called, a `CancelFrame` is pushed through the pipeline and must reach the
+  end. If it does not reach the end within the specified time, a warning is
+  shown and the wait is aborted.
+
+- Added a new "universal" (LLM-agnostic) `LLMContext` and accompanying
+  `LLMContextAggregatorPair`, which will eventually replace `OpenAILLMContext`
+  (and the other under-the-hood contexts) and the other context aggregators.
+  The new universal `LLMContext` machinery allows a single context to be shared
+  between different LLMs, enabling runtime LLM switching and scenarios like
+  failover.
+
+  From the developer's point of view, switching to using the new universal
+  context machinery will usually be a matter of going from this:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+  ```
+
+  To this:
+
+  ```python
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(context)
+  ```
+
+  To start, the universal `LLMContext` is supported with the following LLM
+  services:
+
+  - `OpenAILLMService`
+  - `GoogleLLMService`
+
+- Added a new `LLMSwitcher` class to enable runtime LLM switching, built atop a
+  new generic `ServiceSwitcher`.
+
+  Switchers take a switching strategy. The first available strategy is
+  `ServiceSwitcherStrategyManual`.
+
+  To switch LLMs at runtime, the LLMs must be sharing one instance of the new
+  universal `LLMContext` (see above bullet).
+
+  ```python
+  # Instantiate your LLM services
+  llm_openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+  llm_google = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+
+  # Instantiate a switcher
+  # (ServiceSwitcherStrategyManual defaults to OpenAI, as it's first in the list)
+  llm_switcher = LLMSwitcher(
+      llms=[llm_openai, llm_google], strategy_type=ServiceSwitcherStrategyManual
+  )
+
+  # Create your pipeline
+  pipeline = Pipeline(
+    [
+        transport.input(),
+        stt,
+        context_aggregator.user(),
+        llm_switcher,
+        tts,
+        transport.output(),
+        context_aggregator.assistant(),
+    ]
+  )
+  task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+
+  # ...
+  # Whenever is appropriate, switch LLMs!
+  await task.queue_frames([ManuallySwitchServiceFrame(service=llm_google)])
+  ```
+
+- Added an `LLMService.run_inference()` method to LLM services to enable
+  direct, out-of-band (i.e. out-of-pipeline) inference.
+
+### Changed
+
+- Updated `daily-python` to 0.19.8.
+
+- `PipelineTask` now waits for `StartFrame` to reach the end of the pipeline
+  before pushing any other frames.
+
+- Updated `CartesiaTTSService` and `CartesiaHttpTTSService` to align with
+  Cartesia's changes for the `speed` parameter. It now takes only an enum of
+  `slow`, `normal`, or `fast`.
+
+- Added support to `AWSBedrockLLMService` for setting authentication
+  credentials through environment variables.
+
+- Updated `SarvamTTSService` to use WebSocket streaming for real-time audio
+  generation with multiple Indian languages, with HTTP support still available
+  via `SarvamHttpTTSService`.
+
+### Fixed
+
+- Fixed an RTVI issue that was causing frames to be pushed before pipeline was
+  properly initialized.
+
+- Fixed some `get_messages_for_logging()` that were returning a JSON string
+  instead of a list.
+
+- Fixed a `DailyTransport` issue that prevented DTMF tones from being sent.
+
+- Fixed a missing import in `SentryMetrics`.
+
+- Fixed `AWSPollyTTSService` to support AWS credential provider chain (IAM
+  roles, IRSA, instance profiles) instead of requiring explicit environment
+  variables.
+
+- Fixed a `CartesiaTTSService` issue that was causing the application to hang
+  after Cartesia's 5 minutes timed out.
+
+- Fixed an issue preventing `SpeechmaticsSTTService` from transcribing audio.
+
+## [0.0.81] - 2025-08-25
+
+### Added
+
+- Added `pipecat.extensions.voicemail`, a module for detecting voicemail vs.
+  live conversation, primarily intended for use in outbound calling scenarios.
+  The voicemail module is optimized for text LLMs only.
+
+- Added new frames to the `idle_timeout_frames` arg: `TranscriptionFrame`,
+  `InterimTranscriptionFrame`, `UserStartedSpeakingFrame`, and
+  `UserStoppedSpeakingFrame`. These additions serve as indicators of user
+  activity in the pipeline idle detection logic.
+
+- Allow passing custom pipeline sink and source processors to a
+  `Pipeline`. Pipeline source and sink processors are used to know and control
+  what's coming in and out of a `Pipeline` processor.
+
+- Added `FrameProcessor.pause_processing_system_frames()` and
+  `FrameProcessor.resume_processing_system_frames()`. These allow to pause and
+  resume the processing of system frame.
+
+- Added new `on_process_frame()` observer method which makes it possible to know
+  when a frame is being processed.
+
+- Added new `FrameProcessor.entry_processor()` method. This allows you to access
+  the first non-compound processor in a pipeline.
+
+- Added `FrameProcessor` properties `processors`, `next` and `previous`.
+
+- `ElevenLabsTTSService` now supports additional runtime changes to the `model`,
+  `language`, and `voice_settings` parameters.
+
+- Added `apply_text_normalization` support to `ElevenLabsTTSService` and
+  `ElevenLabsHttpTTSService`.
+
+- Added `MistralLLMService`, using Mistral's chat completion API.
+
+- Added the ability to retry executing a chat completion after a timeout period
+  for `OpenAILLMService` and its subclasses, `AnthropicLLMService`, and
+  `AWSBedrockLLMService`. The LLM services accept new args:
+  `retry_timeout_secs` and `retry_on_timeout`. This feature is disabled by
+  default.
+
+### Changed
+
+- Updated `daily-python` to 0.19.7.
+
+### Deprecated
+
+- `FrameProcessor.wait_for_task()` is deprecated. Use `await task` or
+  `await asyncio.wait_for(task, timeout)` instead.
+
+### Removed
+
+- Watchdog timers have been removed. They were introduced in 0.0.72 to help
+  diagnose pipeline freezes. Unfortunately, they proved ineffective since they
+  required developers to use Pipecat-specific queues, iterators, and events to
+  correctly reset the timer, which limited their usefulness and added friction.
+
+- Removed unused `FrameProcessor.set_parent()` and
+  `FrameProcessor.get_parent()`.
+
+### Fixed
+
+- Fixed an issue that would cause `PipelineRunner` and `PipelineTask` to not
+  handle external asyncio task cancellation properly.
+
+- Added `SpeechmaticsSTTService` exception handling on connection and sending.
+
+- Replaced `asyncio.wait_for()` for `wait_for2.wait_for()` for Python <
+  3.12. because of issues regarding task cancellation (i.e. cancellation is
+  never propagated).
+  See https://bugs.python.org/issue42130
+
+- Fixed an `AudioBufferProcessor` issues that would cause audio overlap when
+  setting a max buffer size.
+
+- Fixed an issue where `AsyncAITTSService` had very high latency in responding
+  by adding `force=true` when sending the flush command.
+
+### Performance
+
+- Improve `PipelineTask` performance by using direct mode processors and by
+  removing unnecessary tasks.
+
+- Improve `ParallelPipeline` performance by using direct mode, by not
+  creating a task for each frame and every sub-pipeline and also by removing
+  other unnecessary tasks.
+
+- `Pipeline` performance improvements by using direct mode.
+
+### Other
+
+- Added `14w-function-calling-mistal.py` using `MistralLLMService`.
+
+- Added `13j-azure-transcription.py` using `AzureSTTService`.
+
+## [0.0.80] - 2025-08-13
+
+### Added
+
+- Added `GeminiTTSService` which uses Google Gemini to generate TTS output. The
+  Gemini model can be prompted to insert styled speech to control the TTS
+  output.
+
+- Added Exotel support to Pipecat's development runner. You can now connect
+  using the runner with `uv run bot.py -t exotel` and an ngrok connection to
+  HTTP port 7860.
+
+- Added `enable_direct_mode` argument to `FrameProcessor`. The direct mode is
+  for processors which require very little I/O or compute resources, that is
+  processors that can perform their task almost immediately. These type of
+  processors don't need any of the internal tasks and queues usually created by
+  frame processors which means overall application performance might be slightly
+  increased. Use with care.
+
+- Added TTFB metrics for `HeyGenVideoService` and `TavusVideoService`.
+
+- Added `endpoint_id` parameter to `AzureSTTService`. ([Custom EndpointId](https://docs.azure.cn/en-us/ai-services/speech-service/how-to-recognize-speech?pivots=programming-language-python#use-a-custom-endpoint))
+
+### Changed
+
+- `WatchdogPriorityQueue` now requires the items to be inserted to always be
+  tuples and the size of the tuple needs to be specified in the constructor when
+  creating the queue with the `tuple_size` argument.
+
+- Updated Moondream to revision `2025-01-09`.
+
+- Updated `PlayHTHttpTTSService` to no longer use the `pyht` client to remove
+  compatibility issues with other packages. Now you can use the PlayHT HTTP
+  service with other services, like GoogleLLMService.
+
 - Updated `pyproject.toml` to once again pin `numba` to `>=0.61.2` in order to
   resolve package versioning issues.
 
+- Updated the `STTMuteFilter` to include `VADUserStartedSpeakingFrame` and
+  `VADUserStoppedSpeakingFrame` in the list of frames to filter when the
+  filtering is on.
+
+### Performance
+
+- Improving the latency of the `HeyGenVideoService`.
+
+- Improved some frame processors performance by using the new frame processor
+  direct mode. In direct mode a frame processor will process frames right away
+  avoiding the need for internal queues and tasks. This is useful for some
+  simple processors. For example, in processors that wrap other processors
+  (e.g. `Pipeline`, `ParallelPipeline`), we add one processor before and one
+  after the wrapped processors (internally, you will see them as sources and
+  sinks). These sources and sinks don't do any special processing and they
+  basically forward frames. So, for these simple processors we now enable the
+  new direct mode which avoids creating any internal tasks (and queues) and
+  therefore improves performance.
+
+### Fixed
+
+- Fixed an issue with the `BaseWhisperSTTService` where the language was
+  specified as an enum and not a string.
+
+- Fixed an issue where `SmallWebRTCTransport` ended before TTS finished.
+
+- Fixed an issue in `OpenAIRealtimeBetaLLMService` where specifying a `text`
+  `modalities` didn't result in text being outputted from the model.
+
+- Added SSML reserved character escaping to `AzureBaseTTSService` to properly
+  handle special characters in text sent to Azure TTS. This fixes an issue
+  where characters like `&`, `<`, `>`, `"`, and `'` in LLM-generated text would
+  cause TTS failures.
+
+- Fixed a `WatchdogPriorityQueue` issue that could cause an exception when
+  compating watchdog cancel sentinel items with other items in the queue.
+
+- Fixed an issue that would cause system frames to not be processed with higher
+  priority than other frames. This could cause slower interruption times.
+
+- Fixed an issue where retrying a websocket connection error would result in an
+  error.
+
 ### Other
 
-- Updated `15-switch-voices.py` and `15a-switch-languages.py` examples to show
-  how to enclose complex logic (e.g. `ParallelPipeline`) into a single processor
-  so the main pipeline becomes simpler.
+- Add foundation example `19b-openai-realtime-beta-text.py`, showing how to use
+  `OpenAIRealtimeBetaLLMService` to output text to a TTS service.
+
+- Add vision support to release evals so we can run the foundational examples 12
+  series.
+
+- Added foundational example `15a-switch-languages.py` to release evals. It is
+  able to detect if we switched the language properly.
+
+- Updated foundational examples to show how to enclose complex logic
+  (e.g. `ParallelPipeline`) into a single processor so the main pipeline becomes
+  simpler.
+
+- Added `07n-interruptible-gemini.py`, demonstrating how to use
+  `GeminiTTSService`.
 
 ## [0.0.79] - 2025-08-07
 

CONTRIBUTING.md

@@ -31,6 +31,23 @@ git push origin your-branch-name
 
 Our maintainers will review your PR, and once everything is good, your contributions will be merged!
 
+## Dependency Management
+
+This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.
+
+### Adding or Updating Dependencies
+
+1. Edit `pyproject.toml` to add/update dependencies
+2. Run `uv lock` to update the lockfile with new dependency resolution
+3. Run `uv sync` to install the updated dependencies locally
+4. Always commit both files together:
+   ```bash
+   git add pyproject.toml uv.lock
+   git commit -m "feat: add new dependency for feature X"
+   ```
+
+**Important:** Never manually edit `uv.lock`. It's auto-generated by `uv lock`.
+
 ## Code Style and Documentation
 
 ### Python Code Style

README.md

@@ -28,6 +28,41 @@
 - **Composable Pipelines**: Build complex behavior from modular components
 - **Real-Time**: Ultra-low latency interaction with different transports (e.g. WebSockets or WebRTC)
 
+## 📱 Client SDKs
+
+You can connect to Pipecat from any platform using our official SDKs:
+
+<table>
+  <tr>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/javascript/javascript-original.svg" width="40" height="40" alt="JavaScript"/>
+      <a href="https://docs.pipecat.ai/client/js/introduction">JavaScript</a>
+    </td>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React"/>
+      <a href="https://docs.pipecat.ai/client/react/introduction">React</a>
+    </td>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/react/react-original.svg" width="40" height="40" alt="React Native"/>
+      <a href="https://docs.pipecat.ai/client/react-native/introduction">React Native</a>
+    </td>
+  </tr>
+  <tr>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/swift/swift-original.svg" width="40" height="40" alt="Swift"/>
+      <a href="https://docs.pipecat.ai/client/ios/introduction">Swift</a>
+    </td>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/kotlin/kotlin-original.svg" width="40" height="40" alt="Kotlin"/>
+      <a href="https://docs.pipecat.ai/client/android/introduction">Kotlin</a>
+    </td>
+    <td>
+      <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/cplusplus/cplusplus-original.svg" width="40" height="40" alt="JavaScript"/>
+      <a href="https://docs.pipecat.ai/client/c++/introduction">C++</a>
+    </td>
+  </tr>
+</table>
+
 ## 🎬 See it in action
 
 <p float="left">
@@ -38,23 +73,12 @@
     <a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/moondream-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/moondream-chatbot/image.png" width="400" /></a>
 </p>
 
-## 📱 Client SDKs
-
-You can connect to Pipecat from any platform using our official SDKs:
-
-| 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                   |
-
 ## 🧩 Available services
 
 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [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), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [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), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [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), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                          |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [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), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [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), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
 | Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [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), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [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), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
 | Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [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                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
@@ -62,7 +86,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 | Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| 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), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
@@ -114,7 +138,8 @@ You can get started with Pipecat running on your local machine, then move your a
 
 ### Prerequisites
 
-**Python Version:** 3.10+
+**Minimum Python Version:** 3.10
+**Recommended Python Version:** 3.12
 
 ### Setup Steps
 
@@ -128,7 +153,11 @@ You can get started with Pipecat running on your local machine, then move your a
 2. Install development and testing dependencies:
 
    ```bash
-   uv sync --group dev --all-extras --no-extra gstreamer --no-extra krisp --no-extra local
+   uv sync --group dev --all-extras \
+     --no-extra gstreamer \
+     --no-extra krisp \
+     --no-extra local \
+     --no-extra ultravox # (ultravox not fully supported on macOS)
    ```
 
 3. Install the git pre-commit hooks:
@@ -137,23 +166,6 @@ You can get started with Pipecat running on your local machine, then move your a
    uv run pre-commit install
    ```
 
-### Python 3.13+ Compatibility
-
-Some features require PyTorch, which doesn't yet support Python 3.13+. Install using:
-
-```bash
-uv sync --group dev --all-extras \
-  --no-extra gstreamer \
-  --no-extra krisp \
-  --no-extra local \
-  --no-extra local-smart-turn \
-  --no-extra mlx-whisper \
-  --no-extra moondream \
-  --no-extra ultravox
-```
-
-> **Tip:** For full compatibility, use Python 3.12: `uv python pin 3.12`
-
 > **Note**: Some extras (local, gstreamer) require system dependencies. See documentation if you encounter build errors.
 
 ### Running tests

docs/README.md

@@ -1,10 +0,0 @@
-# Pipecat Docs
-
-## [Architecture Overview](architecture.md)
-
-Learn about the thinking behind the framework's design.
-
-## [A Frame's Progress](frame-progress.md)
-
-See how a Frame is processed through a Transport, a Pipeline, and a series of Frame Processors.
-

docs/api/index.rst

@@ -21,6 +21,7 @@ Quick Links
    Adapters <api/pipecat.adapters>
    Audio <api/pipecat.audio>
    Clocks <api/pipecat.clocks>
+   Extensions <api/pipecat.extensions>
    Frames <api/pipecat.frames>
    Metrics <api/pipecat.metrics>
    Observers <api/pipecat.observers>

docs/architecture.md

@@ -1,17 +0,0 @@
-# Pipecat architecture guide
-
-## Frames
-
-Frames can represent discrete chunks of data, for instance a chunk of text, a chunk of audio, or an image. They can also be used to as control flow, for instance a frame that indicates that there is no more data available, or that a user started or stopped talking. They can also represent more complex data structures, such as a message array used for an LLM completion.
-
-## FrameProcessors
-
-Frame processors operate on frames. Every frame processor implements a `process_frame` method that consumes one frame and produces zero or more frames. Frame processors can do simple transforms, such as concatenating text fragments into sentences, or they can treat frames as input for an AI Service, and emit chat completions based on message arrays or transform text into audio or images.
-
-## Pipelines
-
-Pipelines are lists of frame processors linked together. Frame processors can push frames upstream or downstream to their peers. A very simple pipeline might chain an LLM frame processor to a text-to-speech frame processor, with a transport as an output.
-
-## Transports
-
-Transports provide input and output frame processors to receive or send frames respectively. For example, the `DailyTransport` does this with a WebRTC session joined to a Daily.co room.

docs/frame-progress.md

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

docs/frame.md

@@ -1,110 +0,0 @@
-# Understanding Different Frame Types in the Pipecat System
-
-In the Pipecat system, frames are used to represent different types of data and control signals that flow through the pipeline. Understanding these frame types is crucial for working with the system effectively. This tutorial will cover the main categories of frames and their specific uses.
-
-## 1. Base Frame Classes
-
-### Frame
-The `Frame` class is the base class for all frames. It includes:
-- `id`: A unique identifier
-- `name`: A descriptive name
-- `pts`: Presentation timestamp (optional)
-
-### DataFrame
-`DataFrame` is a subclass of `Frame` and serves as a base for most data-carrying frames.
-
-## 2. Audio Frames
-
-### AudioRawFrame
-Represents a chunk of audio with properties:
-- `audio`: Raw audio data
-- `sample_rate`: Audio sample rate
-- `num_channels`: Number of audio channels
-
-Subclasses include:
-- `InputAudioRawFrame`: For audio from input sources
-- `OutputAudioRawFrame`: For audio to be played by output devices
-- `TTSAudioRawFrame`: For audio generated by Text-to-Speech services
-
-## 3. Image Frames
-
-### ImageRawFrame
-Represents an image with properties:
-- `image`: Raw image data
-- `size`: Image dimensions
-- `format`: Image format (e.g., JPEG, PNG)
-
-Subclasses include:
-- `InputImageRawFrame`: For images from input sources
-- `OutputImageRawFrame`: For images to be displayed
-- `UserImageRawFrame`: For images associated with a specific user
-- `VisionImageRawFrame`: For images with associated text for description
-- `URLImageRawFrame`: For images with an associated URL
-
-### SpriteFrame
-Represents an animated sprite, containing a list of `ImageRawFrame` objects.
-
-## 4. Text and Transcription Frames
-
-### TextFrame
-Represents a chunk of text, used for various purposes in the pipeline.
-
-### TranscriptionFrame
-A specialized `TextFrame` for speech transcriptions, including:
-- `user_id`: ID of the speaking user
-- `timestamp`: When the transcription was generated
-- `language`: Detected language of the speech
-
-### InterimTranscriptionFrame
-Similar to `TranscriptionFrame`, but for interim (not final) transcriptions.
-
-## 5. LLM (Language Model) Frames
-
-### LLMMessagesFrame
-Contains a list of messages for an LLM service to process.
-
-### LLMMessagesAppendFrame and LLMMessagesUpdateFrame
-Used to modify the current context of LLM messages.
-
-### LLMSetToolsFrame
-Specifies tools (functions) available for the LLM to use.
-
-### LLMEnablePromptCachingFrame
-Controls prompt caching in certain LLMs.
-
-## 6. System and Control Frames
-
-### SystemFrame
-Base class for system-level frames.
-
-Important system frames include:
-- `StartFrame`: Initiates a pipeline
-- `CancelFrame`: Stops a pipeline immediately
-- `ErrorFrame`: Notifies of errors (with `FatalErrorFrame` for unrecoverable errors)
-- `EndTaskFrame` and `CancelTaskFrame`: Control pipeline tasks
-- `StartInterruptionFrame` and `StopInterruptionFrame`: Indicate user speech for interruptions
-
-### ControlFrame
-Base class for control-flow frames.
-
-Notable control frames:
-- `EndFrame`: Signals the end of a pipeline
-- `LLMFullResponseStartFrame` and `LLMFullResponseEndFrame`: Bracket LLM responses
-- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame`: Indicate user speech activity
-- `BotStartedSpeakingFrame` and `BotStoppedSpeakingFrame`: Indicate bot speech activity
-- `TTSStartedFrame` and `TTSStoppedFrame`: Bracket Text-to-Speech responses
-
-## 7. Special Purpose Frames
-
-### MetricsFrame
-Contains performance metrics data.
-
-### FunctionCallInProgressFrame and FunctionCallResultFrame
-Used for handling LLM function (tool) calls.
-
-### ServiceUpdateSettingsFrame
-Base class for updating service settings, with specific subclasses for LLM, TTS, and STT services.
-
-## Conclusion
-
-Understanding these frame types is essential for working with the Pipecat system. Each frame type serves a specific purpose in the pipeline, whether it's carrying data (like audio or images), controlling the flow of the pipeline, or managing system-level operations. By using the appropriate frame types, you can effectively process and transmit various kinds of information through your pipeline.

env.example

@@ -1,3 +1,6 @@
+# AI-COUSTICS
+AICOUSTICS_LICENSE_KEY=...
+
 # Anthropic
 ANTHROPIC_API_KEY=...
 
@@ -59,6 +62,9 @@ GOOGLE_VERTEX_TEST_CREDENTIALS=...
 LMNT_API_KEY=...
 LMNT_VOICE_ID=...
 
+# Perplexity
+PERPLEXITY_API_KEY=...
+
 # PlayHT
 PLAY_HT_USER_ID=...
 PLAY_HT_API_KEY=...
@@ -140,3 +146,12 @@ SENTRY_DSN=...
 
 # Heygen
 HEYGEN_API_KEY=...
+
+# Mistral
+MISTRAL_API_KEY=...
+
+# NVIDIA
+NVIDIA_API_KEY=...
+
+# Qwen
+QWEN_API_KEY=...

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

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.piper.tts import PiperTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.rime.tts import RimeHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -17,8 +17,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -17,7 +17,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.runner.livekit import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
+from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
 
 load_dotenv(override=True)
 

examples/foundational/01c-fastpitch.py

@@ -17,8 +17,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.riva.tts import FastPitchTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -22,8 +22,8 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

examples/foundational/03-still-frame.py

@@ -18,7 +18,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.fal.image import FalImageGenService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 

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

@@ -17,7 +17,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.google.image import GoogleImageGenService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 

examples/foundational/04-transports-small-webrtc.py

@@ -18,6 +18,7 @@ from loguru import logger
 from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -26,8 +27,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import TransportParams
-from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
-from pipecat.transports.network.webrtc_connection import IceServer, SmallWebRTCConnection
+from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
+from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
 
 load_dotenv(override=True)
 
@@ -103,7 +104,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/04a-transports-daily.py

@@ -13,6 +13,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -20,7 +21,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.runner.daily import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.daily import DailyLogLevel, DailyParams, DailyTransport
+from pipecat.transports.daily.transport import DailyLogLevel, DailyParams, DailyTransport
 
 load_dotenv(override=True)
 
@@ -86,7 +87,7 @@ async def main():
             await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):

examples/foundational/04b-transports-livekit.py

@@ -14,7 +14,7 @@ from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
-    BotInterruptionFrame,
+    InterruptionFrame,
     TextFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
@@ -28,7 +28,7 @@ from pipecat.runner.livekit import configure
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
+from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
 
 load_dotenv(override=True)
 
@@ -115,7 +115,7 @@ async def main():
 
         await task.queue_frames(
             [
-                BotInterruptionFrame(),
+                InterruptionFrame(),
                 UserStartedSpeakingFrame(),
                 TranscriptionFrame(
                     user_id=participant_id,

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

@@ -33,7 +33,7 @@ from pipecat.services.cartesia.tts import CartesiaHttpTTSService
 from pipecat.services.fal.image import FalImageGenService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 

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

@@ -10,7 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, MetricsFrame
+from pipecat.frames.frames import Frame, LLMRunFrame, MetricsFrame
 from pipecat.metrics.metrics import (
     LLMUsageMetricsData,
     ProcessingMetricsData,
@@ -28,8 +28,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -127,7 +127,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -15,6 +15,7 @@ from pipecat.frames.frames import (
     BotStartedSpeakingFrame,
     BotStoppedSpeakingFrame,
     Frame,
+    LLMRunFrame,
     OutputImageRawFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
@@ -28,7 +29,7 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
@@ -65,7 +66,7 @@ class ImageSyncAggregator(FrameProcessor):
                 )
             )
 
-        await self.push_frame(frame)
+        await self.push_frame(frame, direction)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -144,7 +145,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -10,6 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -20,8 +21,8 @@ from pipecat.services.cartesia.tts import CartesiaHttpTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -96,7 +97,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07-interruptible.py

@@ -10,6 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -20,8 +21,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -95,7 +96,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -9,6 +9,7 @@ import os
 from dotenv import load_dotenv
 from loguru import logger
 
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -24,8 +25,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -154,7 +155,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Say a short hello to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -10,6 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -25,8 +26,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -137,7 +138,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Say a short hello to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07aa-interruptible-soniox.py

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.soniox.stt import SonioxSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -94,7 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07ab-interruptible-inworld-http.py

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.inworld.tts import InworldTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -109,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

examples/foundational/07ac-interruptible-asyncai-http.py

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -101,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

examples/foundational/07ac-interruptible-asyncai.py

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.asyncai.tts import AsyncAITTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/07ad-interruptible-aicoustics.py

@@ -0,0 +1,162 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import datetime
+import os
+import wave
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.filters.aic_filter import AICFilter
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# Create audio buffer processor so we can hear the audio fitler results.
+audiobuffer = AudioBufferProcessor(
+    num_channels=2,  # 1 for mono, 2 for stereo (user left, bot right)
+    enable_turn_audio=False,  # Enable per-turn audio recording
+)
+
+
+def _create_aic_filter() -> AICFilter:
+    license_key = os.getenv("AICOUSTICS_LICENSE_KEY", "")
+
+    return AICFilter(
+        license_key=license_key,
+        enhancement_level=1.0,
+    )
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+        audio_in_filter=_create_aic_filter(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+        audio_in_filter=_create_aic_filter(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+        audio_in_filter=_create_aic_filter(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            audiobuffer,  # write audio data to a file
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        await audiobuffer.start_recording()
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
+
+    @audiobuffer.event_handler("on_audio_data")
+    async def on_audio_data(buffer, audio, sample_rate, num_channels):
+        # Save or process the composite audio
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        filename = f"./conversation_{timestamp}.wav"
+
+        # Create the WAV file
+        with wave.open(filename, "wb") as wf:
+            wf.setnchannels(num_channels)
+            wf.setsampwidth(2)  # 16-bit audio
+            wf.setframerate(sample_rate)
+            wf.writeframes(audio)
+
+        logger.info(f"Saved recording to {filename}")
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -33,8 +33,8 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -12,8 +12,8 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.frames.frames import (
-    BotInterruptionFrame,
-    StopInterruptionFrame,
+    InterruptionFrame,
+    LLMRunFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
@@ -27,8 +27,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,18 +97,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     @stt.event_handler("on_speech_started")
     async def on_speech_started(stt, *args, **kwargs):
-        await task.queue_frames([BotInterruptionFrame(), UserStartedSpeakingFrame()])
+        await task.queue_frames([InterruptionFrame(), UserStartedSpeakingFrame()])
 
     @stt.event_handler("on_utterance_end")
     async def on_utterance_end(stt, *args, **kwargs):
-        await task.queue_frames([StopInterruptionFrame(), UserStoppedSpeakingFrame()])
+        await task.queue_frames([UserStoppedSpeakingFrame()])
 
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -94,7 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -101,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.playht.tts import PlayHTHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.playht.tts import PlayHTTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -99,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.azure.llm import AzureLLMService
 from pipecat.services.azure.stt import AzureSTTService
 from pipecat.services.azure.tts import AzureTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -103,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.openai.stt import OpenAISTTService
 from pipecat.services.openai.tts import OpenAITTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -98,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openpipe.llm import OpenPipeLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -102,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.xtts.tts import XTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -100,7 +101,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -23,8 +24,8 @@ from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -106,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.lmnt.tts import LmntTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -93,7 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.groq.llm import GroqLLMService
 from pipecat.services.groq.stt import GroqSTTService
 from pipecat.services.groq.tts import GroqTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -98,7 +99,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -9,6 +9,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -19,8 +20,8 @@ from pipecat.services.aws.llm import AWSBedrockLLMService
 from pipecat.services.aws.stt import AWSTranscribeSTTService
 from pipecat.services.aws.tts import AWSPollyTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -99,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "user", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -0,0 +1,164 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""
+A conversational AI bot using Gemini for both LLM and TTS.
+
+This example demonstrates how to use Gemini's TTS capabilities with the new
+GeminiTTSService, which uses Gemini's TTS-specific models instead of Google Cloud TTS.
+
+Features showcased:
+- Gemini LLM for conversation
+- Gemini TTS with natural voice control
+- Support for different voice personalities
+- Style and tone control through natural language prompts
+
+Run with:
+    python examples/foundational/gemini-tts.py
+
+Make sure to set your environment variables:
+    export GOOGLE_API_KEY=your_api_key_here
+"""
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+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.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.google.llm import GoogleLLMService
+from pipecat.services.google.stt import GoogleSTTService
+from pipecat.services.google.tts import GeminiTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot with Gemini TTS")
+
+    stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
+        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
+    )
+
+    tts = GeminiTTSService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash-preview-tts",  # TTS-specific model
+        voice_id="Charon",
+        params=GeminiTTSService.InputParams(language=Language.EN_US),
+    )
+
+    llm = GoogleLLMService(
+        api_key=os.getenv("GOOGLE_API_KEY"),
+        model="gemini-2.5-flash",
+    )
+
+    # System message that instructs the AI on how to speak
+    messages = [
+        {
+            "role": "system",
+            "content": """You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
+
+            IMPORTANT: Since you're using Gemini TTS which supports natural voice control, you can include speaking instructions in your responses. For example:
+            - "Say cheerfully: Welcome to our conversation!"
+            - "Read this in a calm, professional tone: Here are the details you requested."
+            - "Speak in an excited whisper: I have some great news to share!"
+            - "Say slowly and clearly: Let me explain this step by step."
+
+            Feel free to use natural language instructions to control your voice style, tone, pace, and emotion. The TTS system will interpret these instructions and adjust the speech accordingly.
+
+            Your output will be converted to audio, so avoid special characters in your answers. Respond to what the user said in a creative and helpful way.""",
+        },
+    ]
+
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # Gemini TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation with a styled introduction
+        messages.append(
+            {
+                "role": "system",
+                "content": "Say cheerfully and warmly: Hello! I'm your AI assistant powered by Gemini's new TTS technology. I can speak with different voices, tones, and styles. How can I help you today?",
+            }
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.google.stt import GoogleSTTService
 from pipecat.services.google.tts import GoogleTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -106,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.assemblyai.stt import AssemblyAISTTService
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -99,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from loguru import logger
 
 from pipecat.audio.filters.krisp_filter import KrispFilter
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.deepgram.tts import DeepgramTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.rime.tts import RimeHttpTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -102,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.rime.tts import RimeTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -96,7 +97,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.nim.llm import NimLLMService
 from pipecat.services.riva.stt import RivaSTTService
 from pipecat.services.riva.tts import RivaTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -93,7 +94,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -16,9 +16,10 @@ from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
+    InterruptionFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
-    StartInterruptionFrame,
+    LLMRunFrame,
     TextFrame,
     TranscriptionFrame,
     UserStartedSpeakingFrame,
@@ -35,8 +36,8 @@ from pipecat.services.google.llm import GoogleLLMService
 from pipecat.services.google.tts import GoogleTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -92,9 +93,8 @@ class UserAudioCollector(FrameProcessor):
         elif isinstance(frame, UserStoppedSpeakingFrame):
             self._user_speaking = False
             self._context.add_audio_frames_message(audio_frames=self._audio_frames)
-            await self._user_context_aggregator.push_frame(
-                self._user_context_aggregator.get_context_frame()
-            )
+            await self._user_context_aggregator.push_frame(LLMRunFrame())
+
         elif isinstance(frame, InputAudioRawFrame):
             if self._user_speaking:
                 self._audio_frames.append(frame)
@@ -150,7 +150,7 @@ class TranscriptExtractor(FrameProcessor):
         await self.push_frame(frame, direction)
 
 
-class TanscriptionContextFixup(FrameProcessor):
+class TranscriptionContextFixup(FrameProcessor):
     def __init__(self, context):
         super().__init__()
         self._context = context
@@ -181,9 +181,7 @@ class TanscriptionContextFixup(FrameProcessor):
 
         if isinstance(frame, MagicDemoTranscriptionFrame):
             self._transcript = frame.text
-        elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(
-            frame, StartInterruptionFrame
-        ):
+        elif isinstance(frame, LLMFullResponseEndFrame) or isinstance(frame, InterruptionFrame):
             self.swap_user_audio()
             self.add_transcript_back_to_inference_output()
             self._transcript = ""
@@ -244,7 +242,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     context_aggregator = llm.create_context_aggregator(context)
     audio_collector = UserAudioCollector(context, context_aggregator.user())
     pull_transcript_out_of_llm_output = TranscriptExtractor(context)
-    fixup_context_messages = TanscriptionContextFixup(context)
+    fixup_context_messages = TranscriptionContextFixup(context)
 
     pipeline = Pipeline(
         [
@@ -274,7 +272,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.fish.tts import FishAudioTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -97,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -19,8 +19,8 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.ultravox.stt import UltravoxSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,8 +23,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -101,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.neuphonic.tts import NeuphonicTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -96,7 +97,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,6 +11,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,8 +22,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.fal.stt import FalSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -99,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         # Kick off the conversation.
         messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-        await task.queue_frames([context_aggregator.user().get_context_frame()])
+        await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -78,7 +79,7 @@ async def main():
     )
 
     messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-    await task.queue_frames([context_aggregator.user().get_context_frame()])
+    await task.queue_frames([LLMRunFrame()])
 
     runner = PipelineRunner()
 

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

@@ -12,6 +12,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -23,8 +24,8 @@ from pipecat.services.minimax.tts import MiniMaxHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -103,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info(f"Client connected")
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+            await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")
         async def on_client_disconnected(transport, client):

examples/foundational/07z-interruptible-sarvam-http.py

@@ -0,0 +1,126 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.tts import SarvamHttpTTSService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Create an HTTP session
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = SarvamHttpTTSService(
+            api_key=os.getenv("SARVAM_API_KEY"),
+            aiohttp_session=session,
+            params=SarvamHttpTTSService.InputParams(language=Language.EN),
+        )
+
+        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(),  # Transport user input
+                stt,
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            params=PipelineParams(
+                enable_metrics=True,
+                enable_usage_metrics=True,
+            ),
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        @transport.event_handler("on_client_connected")
+        async def on_client_connected(transport, client):
+            logger.info(f"Client connected")
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/07z-interruptible-sarvam.py

@@ -5,6 +5,7 @@
 #
 
 
+import asyncio
 import os
 
 import aiohttp
@@ -12,6 +13,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -21,10 +23,9 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.sarvam.tts import SarvamTTSService
-from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -54,64 +55,64 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    # Create an HTTP session
-    async with aiohttp.ClientSession() as session:
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-        tts = SarvamTTSService(
-            api_key=os.getenv("SARVAM_API_KEY"),
-            aiohttp_session=session,
-            params=SarvamTTSService.InputParams(language=Language.EN),
-        )
+    tts = SarvamTTSService(
+        api_key=os.getenv("SARVAM_API_KEY"),
+        model="bulbul:v2",
+        voice_id="manisha",
+    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
 
-        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+    messages = [
+        {
+            "role": "system",
+            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
 
-        messages = [
-            {
-                "role": "system",
-                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
-            },
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
+    )
 
-        context = OpenAILLMContext(messages)
-        context_aggregator = llm.create_context_aggregator(context)
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+    )
 
-        pipeline = Pipeline(
-            [
-                transport.input(),  # Transport user input
-                stt,
-                context_aggregator.user(),  # User responses
-                llm,  # LLM
-                tts,  # TTS
-                transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
-            ]
-        )
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
 
-        task = PipelineTask(
-            pipeline,
-            params=PipelineParams(
-                enable_metrics=True,
-                enable_usage_metrics=True,
-            ),
-            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
-        )
+        # Optionally, you can wait for 30 seconds and then change the voice.
+        # await asyncio.sleep(30)
+        # await task.queue_frame(TTSUpdateSettingsFrame(settings={"voice": "anushka"}))
 
-        @transport.event_handler("on_client_connected")
-        async def on_client_connected(transport, client):
-            logger.info(f"Client connected")
-            # Kick off the conversation.
-            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
-            await task.queue_frames([context_aggregator.user().get_context_frame()])
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
 
-        @transport.event_handler("on_client_disconnected")
-        async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
-            await task.cancel()
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 
-        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
-
-        await runner.run(task)
+    await runner.run(task)
 
 
 async def bot(runner_args: RunnerArguments):

examples/foundational/08-bots-arguing.py

@@ -17,7 +17,7 @@ from pipecat.runner.daily import configure
 from pipecat.services.azure import AzureLLMService, AzureTTSService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.fal import FalImageGenService
-from pipecat.transports.services.daily import DailyTransport
+from pipecat.transports.daily.transport import DailyTransport
 
 load_dotenv(override=True)
 

examples/foundational/09-mirror.py

@@ -22,7 +22,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 

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

@@ -24,8 +24,8 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport, maybe_capture_participant_camera
 from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
-from pipecat.transports.services.daily import DailyParams
 
 load_dotenv(override=True)
 

examples/foundational/10-wake-phrase.py

@@ -22,8 +22,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

examples/foundational/11-sound-effects.py

@@ -32,8 +32,8 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 

examples/foundational/12-describe-video.py

@@ -11,12 +11,19 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, TextFrame, TTSSpeakFrame, UserImageRequestFrame
+from pipecat.frames.frames import (
+    Frame,
+    LLMContextFrame,
+    TextFrame,
+    TTSSpeakFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
-from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
@@ -28,12 +35,14 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.moondream.vision import MoondreamService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
 
 class UserImageRequester(FrameProcessor):
+    """Converts incoming text into requests for user images."""
+
     def __init__(self, participant_id: Optional[str] = None):
         super().__init__()
         self._participant_id = participant_id
@@ -46,9 +55,32 @@ class UserImageRequester(FrameProcessor):
 
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
-                UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM
+                UserImageRequestFrame(self._participant_id, context=frame.text),
+                FrameDirection.UPSTREAM,
             )
-        await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+class UserImageProcessor(FrameProcessor):
+    """Converts incoming user images into context frames."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserImageRawFrame):
+            if frame.request and frame.request.context:
+                context = LLMContext()
+                context.add_image_frame_message(
+                    image=frame.image,
+                    text=frame.request.context,
+                    size=frame.size,
+                    format=frame.format,
+                )
+                frame = LLMContextFrame(context)
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -78,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Initialize the image requester without setting the participant ID yet
     image_requester = UserImageRequester()
 
-    vision_aggregator = VisionImageFrameAggregator()
+    image_processor = UserImageProcessor()
 
     # If you run into weird description, try with use_cpu=True
     moondream = MoondreamService()
@@ -96,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             user_response,
             image_requester,
-            vision_aggregator,
+            image_processor,
             moondream,
             tts,
             transport.output(),
@@ -119,7 +151,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         image_requester.set_participant_id(client_id)
 
         # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me what I see."))
+        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,12 +11,19 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, TextFrame, TTSSpeakFrame, UserImageRequestFrame
+from pipecat.frames.frames import (
+    Frame,
+    LLMContextFrame,
+    TextFrame,
+    TTSSpeakFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
-from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
@@ -28,12 +35,14 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.google.llm import GoogleLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
 
 class UserImageRequester(FrameProcessor):
+    """Converts incoming text into requests for user images."""
+
     def __init__(self, participant_id: Optional[str] = None):
         super().__init__()
         self._participant_id = participant_id
@@ -46,9 +55,32 @@ class UserImageRequester(FrameProcessor):
 
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
-                UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM
+                UserImageRequestFrame(self._participant_id, context=frame.text),
+                FrameDirection.UPSTREAM,
             )
-        await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+class UserImageProcessor(FrameProcessor):
+    """Converts incoming user images into context frames."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserImageRawFrame):
+            if frame.request and frame.request.context:
+                context = LLMContext()
+                context.add_image_frame_message(
+                    image=frame.image,
+                    text=frame.request.context,
+                    size=frame.size,
+                    format=frame.format,
+                )
+                frame = LLMContextFrame(context)
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -78,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Initialize the image requester without setting the participant ID yet
     image_requester = UserImageRequester()
 
-    vision_aggregator = VisionImageFrameAggregator()
+    image_processor = UserImageProcessor()
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
@@ -96,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             user_response,
             image_requester,
-            vision_aggregator,
+            image_processor,
             google,
             tts,
             transport.output(),
@@ -123,7 +155,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         image_requester.set_participant_id(client_id)
 
         # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me what I see."))
+        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,12 +11,19 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, TextFrame, TTSSpeakFrame, UserImageRequestFrame
+from pipecat.frames.frames import (
+    Frame,
+    LLMContextFrame,
+    TextFrame,
+    TTSSpeakFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
-from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
@@ -28,12 +35,14 @@ from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
 
 class UserImageRequester(FrameProcessor):
+    """Converts incoming text into requests for user images."""
+
     def __init__(self, participant_id: Optional[str] = None):
         super().__init__()
         self._participant_id = participant_id
@@ -46,9 +55,32 @@ class UserImageRequester(FrameProcessor):
 
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
-                UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM
+                UserImageRequestFrame(self._participant_id, context=frame.text),
+                FrameDirection.UPSTREAM,
             )
-        await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+class UserImageProcessor(FrameProcessor):
+    """Converts incoming user images into context frames."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserImageRawFrame):
+            if frame.request and frame.request.context:
+                context = LLMContext()
+                context.add_image_frame_message(
+                    image=frame.image,
+                    text=frame.request.context,
+                    size=frame.size,
+                    format=frame.format,
+                )
+                frame = LLMContextFrame(context)
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -78,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Initialize the image requester without setting the participant ID yet
     image_requester = UserImageRequester()
 
-    vision_aggregator = VisionImageFrameAggregator()
+    image_processor = UserImageProcessor()
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
@@ -96,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             user_response,
             image_requester,
-            vision_aggregator,
+            image_processor,
             openai,
             tts,
             transport.output(),
@@ -123,7 +155,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         image_requester.set_participant_id(client_id)
 
         # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me what I see."))
+        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

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

@@ -11,12 +11,19 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import Frame, TextFrame, TTSSpeakFrame, UserImageRequestFrame
+from pipecat.frames.frames import (
+    Frame,
+    LLMContextFrame,
+    TextFrame,
+    TTSSpeakFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.user_response import UserResponseAggregator
-from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import (
@@ -28,12 +35,14 @@ from pipecat.services.anthropic.llm import AnthropicLLMService
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
 
 load_dotenv(override=True)
 
 
 class UserImageRequester(FrameProcessor):
+    """Converts incoming text into requests for user images."""
+
     def __init__(self, participant_id: Optional[str] = None):
         super().__init__()
         self._participant_id = participant_id
@@ -46,9 +55,32 @@ class UserImageRequester(FrameProcessor):
 
         if self._participant_id and isinstance(frame, TextFrame):
             await self.push_frame(
-                UserImageRequestFrame(self._participant_id), FrameDirection.UPSTREAM
+                UserImageRequestFrame(self._participant_id, context=frame.text),
+                FrameDirection.UPSTREAM,
             )
-        await self.push_frame(frame, direction)
+        else:
+            await self.push_frame(frame, direction)
+
+
+class UserImageProcessor(FrameProcessor):
+    """Converts incoming user images into context frames."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserImageRawFrame):
+            if frame.request and frame.request.context:
+                context = LLMContext()
+                context.add_image_frame_message(
+                    image=frame.image,
+                    text=frame.request.context,
+                    size=frame.size,
+                    format=frame.format,
+                )
+                frame = LLMContextFrame(context)
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
 
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
@@ -78,7 +110,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Initialize the image requester without setting the participant ID yet
     image_requester = UserImageRequester()
 
-    vision_aggregator = VisionImageFrameAggregator()
+    image_processor = UserImageProcessor()
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
@@ -96,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             stt,
             user_response,
             image_requester,
-            vision_aggregator,
+            image_processor,
             anthropic,
             tts,
             transport.output(),
@@ -123,7 +155,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         image_requester.set_participant_id(client_id)
 
         # Welcome message
-        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me what I see."))
+        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
 
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):

examples/foundational/12d-describe-video-aws.py

@@ -0,0 +1,187 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+from typing import Optional
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import (
+    Frame,
+    LLMContextFrame,
+    TextFrame,
+    TTSSpeakFrame,
+    UserImageRawFrame,
+    UserImageRequestFrame,
+)
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.user_response import UserResponseAggregator
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import (
+    create_transport,
+    get_transport_client_id,
+    maybe_capture_participant_camera,
+)
+from pipecat.services.aws.llm import AWSBedrockLLMService
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+
+load_dotenv(override=True)
+
+
+class UserImageRequester(FrameProcessor):
+    """Converts incoming text into requests for user images."""
+
+    def __init__(self, participant_id: Optional[str] = None):
+        super().__init__()
+        self._participant_id = participant_id
+
+    def set_participant_id(self, participant_id: str):
+        self._participant_id = participant_id
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if self._participant_id and isinstance(frame, TextFrame):
+            await self.push_frame(
+                UserImageRequestFrame(self._participant_id, context=frame.text),
+                FrameDirection.UPSTREAM,
+            )
+        else:
+            await self.push_frame(frame, direction)
+
+
+class UserImageProcessor(FrameProcessor):
+    """Converts incoming user images into context frames."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, UserImageRawFrame):
+            if frame.request and frame.request.context:
+                # Note: AWS Bedrock does not yet support the universal LLMContext
+                context = LLMContext()
+                context.add_image_frame_message(
+                    image=frame.image,
+                    text=frame.request.context,
+                    size=frame.size,
+                    format=frame.format,
+                )
+                frame = LLMContextFrame(context)
+                await self.push_frame(frame)
+        else:
+            await self.push_frame(frame, direction)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    user_response = UserResponseAggregator()
+
+    # Initialize the image requester without setting the participant ID yet
+    image_requester = UserImageRequester()
+
+    image_processor = UserImageProcessor()
+
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+    # AWS for vision analysis
+    aws = AWSBedrockLLMService(
+        aws_region="us-west-2",
+        model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+        # Note: usually, prefer providing latency="optimized" param.
+        # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
+        # which we need for image input.
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+    )
+
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),
+            stt,
+            user_response,
+            image_requester,
+            image_processor,
+            aws,
+            tts,
+            transport.output(),
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected: {client}")
+
+        await maybe_capture_participant_camera(transport, client)
+
+        # Set the participant ID in the image requester
+        client_id = get_transport_client_id(transport, client)
+        image_requester.set_participant_id(client_id)
+
+        # Welcome message
+        await task.queue_frame(TTSSpeakFrame("Hi there! Feel free to ask me about what I see."))
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

examples/foundational/13-whisper-transcription.py

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.whisper.stt import WhisperSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -31,6 +31,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets

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

@@ -32,6 +32,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 async def main():
     transport = LocalAudioTransport(

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

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService, Language, LiveOptions
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -31,6 +31,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets

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

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.gladia import GladiaSTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -31,6 +31,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets

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

@@ -25,8 +25,8 @@ from pipecat.services.gladia.config import (
 from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -40,6 +40,9 @@ class TranscriptionLogger(FrameProcessor):
         elif isinstance(frame, TranslationFrame):
             print(f"Translation ({frame.language}): {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets

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

@@ -18,8 +18,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -31,6 +31,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             print(f"Transcription: {frame.text}")
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets

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

@@ -20,8 +20,8 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.whisper.stt import MLXModel, WhisperSTTServiceMLX
 from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketParams
-from pipecat.transports.services.daily import DailyParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
 
 load_dotenv(override=True)
 
@@ -52,6 +52,9 @@ class TranscriptionLogger(FrameProcessor):
         if isinstance(frame, TranscriptionFrame):
             self._last_transcription_time = time.time()
 
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
 
 # We store functions so objects (e.g. SileroVADAnalyzer) don't get
 # instantiated. The function will be called when the desired transport gets