fix: add type annotations to event_handler decorator

Add proper generic type annotations to the event_handler decorator
so that static type checkers (pyright, mypy) understand the decorated
function is returned and used, eliminating false reportUnusedFunction
warnings.

Changes:
- Import TypeVar and Callable from typing
- Define F TypeVar bound to Callable[..., Any]
- Add Callable[[F], F] return type to event_handler method
- Add F type annotations to inner decorator function

.github/workflows/coverage.yaml

@@ -33,7 +33,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
+          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra websocket
 
       - name: Run tests with coverage
         run: |

.github/workflows/tests.yaml

@@ -37,7 +37,7 @@ jobs:
 
       - name: Install dependencies
         run: |
-          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
+          uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra websocket
 
       - name: Test with pytest
         run: |

.gitignore

@@ -51,4 +51,7 @@ docs/api/_build/
 docs/api/api
 
 # uv
-.python-version
+.python-version
+
+# Pipecat
+whisker_setup.py

CHANGELOG.md

@@ -7,6 +7,541 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- towncrier release notes start -->
 
+## [0.0.99] - 2026-01-13
+
+### Added
+
+- Introducing user turn strategies. User turn strategies indicate when the user
+  turn starts or stops. In conversational agents, these are often referred to
+  as start/stop speaking or turn-taking plans or policies.
+
+  User turn start strategies indicate when the user starts speaking (e.g.
+  using VAD events or when a user says one or more words).
+
+  User turn stop strategies indicate when the user stops speaking (e.g. using
+  an end-of-turn detection model or by observing incoming transcriptions).
+
+  A list of strategies can be specified for both strategies; strategies are
+  evaluated in order until one evaluates to true.
+
+  Available user turn start strategies:
+
+  - VADUserTurnStartStrategy
+  - TranscriptionUserTurnStartStrategy
+  - MinWordsUserTurnStartStrategy
+  - ExternalUserTurnStartStrategy
+
+  Available user turn stop strategies:
+
+  - TranscriptionUserTurnStopStrategy
+  - TurnAnalyzerUserTurnStopStrategy
+  - ExternalUserTurnStopStrategy
+
+  The default strategies are:
+
+  - start: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
+  - stop: [TranscriptionUserTurnStopStrategy]
+
+  Turn strategies are configured when setting up `LLMContextAggregatorPair`.
+  For example:
+
+  ```python
+  context_aggregator = LLMContextAggregatorPair(
+      context,
+      user_params=LLMUserAggregatorParams(
+          user_turn_strategies=UserTurnStrategies(
+              stop=[
+                  TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
+                  )
+              ],
+          )
+      ),
+  )
+  ```
+
+  In order to use the user turn strategies you must update to the new
+  universal `LLMContext` and `LLMContextAggregatorPair`.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural
+  network via pyrnnoise library.
+  (PR [#3205](https://github.com/pipecat-ai/pipecat/pull/3205))
+
+- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time
+  voice conversations:
+
+  - Support for real-time audio streaming with WebSocket connection
+  - Built-in server-side VAD (Voice Activity Detection)
+  - Multiple voice options: Ara, Rex, Sal, Eve, Leo
+  - Built-in tools support: web_search, x_search, file_search
+  - Custom function calling with standard Pipecat tools schema
+  - Configurable audio formats (PCM at 8kHz-48kHz)
+    (PR [#3267](https://github.com/pipecat-ai/pipecat/pull/3267))
+
+- Added an approximation of TTFB for Ultravox.
+  (PR [#3268](https://github.com/pipecat-ai/pipecat/pull/3268))
+
+- Added a new `AudioContextTTSService` to the TTS service base classes. The
+  `AudioContextWordTTSService` now inherits from `AudioContextTTSService` and
+  `WebsocketWordTTSService`.
+  (PR [#3289](https://github.com/pipecat-ai/pipecat/pull/3289))
+
+- `LLMUserAggregator` now exposes the following events:
+
+  - `on_user_turn_started`: triggered when a user turn starts
+  - `on_user_turn_stopped`: triggered when a user turn ends
+  - `on_user_turn_stop_timeout`: triggered when a user turn does not stop
+    and times out
+    (PR [#3291](https://github.com/pipecat-ai/pipecat/pull/3291))
+
+- Introducing user mute strategies. User mute strategies indicate when user
+  input should be muted based on the current system state.
+
+  In conversational agents, user mute strategies are used to prevent user
+  input from interrupting bot speech, tool execution, or other critical system
+  operations.
+
+  A list of strategies can be specified; all strategies are evaluated for
+  every frame so that each strategy can maintain its internal state. A user
+  frame is muted if any of the configured strategies indicates it should be
+  muted.
+
+  Available user mute strategies:
+
+  - `FirstSpeechUserMuteStrategy`
+  - `MuteUntilFirstBotCompleteUserMuteStrategy`
+  - `AlwaysUserMuteStrategy`
+  - `FunctionCallUserMuteStrategy`
+
+  User mute strategies replace the legacy `STTMuteFilter` and provide a more
+  flexible and composable approach to muting user input.
+
+  User mute strategies are configured when setting up the
+  `LLMContextAggregatorPair`. For example:
+
+  ```python
+  context_aggregator = LLMContextAggregatorPair(
+      context,
+      user_params=LLMUserAggregatorParams(
+          user_mute_strategies=[
+              FirstSpeechUserMuteStrategy(),
+          ]
+      ),
+  )
+  ```
+
+  In order to use user mute strategies you should update to the new universal
+  `LLMContext` and `LLMContextAggregatorPair`.
+  (PR [#3292](https://github.com/pipecat-ai/pipecat/pull/3292))
+
+- Added `use_ssl` parameter to `NvidiaSTTService`, `NvidiaSegmentedSTTService`
+  and `NvidiaTTSService`.
+  (PR [#3300](https://github.com/pipecat-ai/pipecat/pull/3300))
+
+- Added `enable_interruptions` constructor argument to all user turn
+  strategies. This tells the `LLMUserAggregator` to push or not push an
+  `InterruptionFrame`.
+  (PR [#3316](https://github.com/pipecat-ai/pipecat/pull/3316))
+
+- Added `split_sentences` parameter to `SpeechmaticsSTTService` to control
+  sentence splitting behavior for finals on sentence boundaries.
+  (PR [#3328](https://github.com/pipecat-ai/pipecat/pull/3328))
+
+- Added word-level timestamp support to `AzureTTSService` for accurate
+  text-to-audio synchronization.
+  (PR [#3334](https://github.com/pipecat-ai/pipecat/pull/3334))
+
+- Added `pronunciation_dict_id` parameter to `CartesiaTTSService.InputParams`
+  and `CartesiaHttpTTSService.InputParams` to support Cartesia's pronunciation
+  dictionary feature for custom pronunciations.
+  (PR [#3346](https://github.com/pipecat-ai/pipecat/pull/3346))
+
+- Added support for using the HeyGen LiveAvatar API with the `HeyGenTransport`
+  (see https://www.liveavatar.com/).
+  (PR [#3357](https://github.com/pipecat-ai/pipecat/pull/3357))
+
+- Added image support to `OpenAIRealtimeLLMService` via `InputImageRawFrame`:
+
+  - New `start_video_paused` parameter to control initial video input state
+  - New `video_frame_detail` parameter to set image processing quality
+    ("auto",
+    "low", or "high"). This corresponds to OpenAI Realtime's `image_detail`
+    parameter.
+  - `set_video_input_paused()` method to pause/resume video input at runtime
+  - `set_video_frame_detail()` method to adjust video frame quality
+    dynamically
+  - Automatic rate limiting (1 frame per second) to prevent API overload
+    (PR [#3360](https://github.com/pipecat-ai/pipecat/pull/3360))
+
+- Added `UserTurnProcessor`, a frame processor built on `UserTurnController`
+  that pushes `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames
+  and interruptions based on the controller's user turn strategies.
+  (PR [#3372](https://github.com/pipecat-ai/pipecat/pull/3372))
+
+- Added `UserTurnController` to manage user turns. It emits
+  `on_user_turn_started`, `on_user_turn_stopped`, and
+  `on_user_turn_stop_timeout` events, and can be integrated into processors to
+  detect and handle user turns. `LLMUserAggregator` and `UserTurnProcessor` are
+  implemented using this controller.
+  (PR [#3372](https://github.com/pipecat-ai/pipecat/pull/3372))
+
+- Added `should_interrupt` property to `DeepgramFluxSTTService`,
+  `DeepgramSTTService`, and `SpeechmaticsSTTService` to configure whether the
+  bot should be interrupted when the external service detects user speech.
+  (PR [#3374](https://github.com/pipecat-ai/pipecat/pull/3374))
+
+- `LLMAssistantAggregator` now exposes the following events:
+
+  - `on_assistant_turn_started`: triggered when the assistant turn starts
+  - `on_assistant_turn_stopped`: triggered when the assistant turn ends
+  - `on_assistant_thought`: triggered when there's an assistant thought
+    available
+    (PR [#3385](https://github.com/pipecat-ai/pipecat/pull/3385))
+
+- Added `KrispVivaTurn` analyzer for end of turn detection using the Krisp VIVA
+  SDK (requires `krisp_audio`).
+  (PR [#3391](https://github.com/pipecat-ai/pipecat/pull/3391))
+
+- Added support for setting up a pipeline task from external files. You can now
+  register custom pipeline task setup files by setting the
+  `PIPECAT_SETUP_FILES` environment variable. This variable should contain a
+  colon-separated list of Python files (e.g. `export
+PIPECAT_SETUP_FILES="setup1.py:setup.py:..."`). Each file must define a
+  function with the following signature:
+
+  ```python
+  async def setup_pipeline_task(task: PipelineTask):
+      ...
+  ```
+
+  (PR [#3397](https://github.com/pipecat-ai/pipecat/pull/3397))
+
+- Added a keepalive task for `InworldTTSService` to keep the service connected
+  in the event of no generations for longer periods of time.
+  (PR [#3403](https://github.com/pipecat-ai/pipecat/pull/3403))
+
+- Added `enable_vad` to `Params` for use in the `GladiaSTTService`. When
+  enabled, `GladiaSTTService` acts as the turn controller, emitting
+  `UserStartedSpeakingFrame`, `UserStoppedSpeakingFrame`, and optionally
+  `InterruptionFrame`.
+  (PR [#3404](https://github.com/pipecat-ai/pipecat/pull/3404))
+
+- Added `should_interrupt` property to `GladiaSTTService` to configure whether
+  the bot should be interrupted when the external service detects user speech.
+  (PR [#3404](https://github.com/pipecat-ai/pipecat/pull/3404))
+
+- Added `VonageFrameSerializer` for the Vonage Video API Audio Connector
+  WebSocket protocol.
+  (PR [#3410](https://github.com/pipecat-ai/pipecat/pull/3410))
+
+- Added `append_trailing_space` parameter to `TTSService` to automatically
+  append a trailing space to text before sending to TTS, helping prevent some
+  services from vocalizing trailing punctuation.
+  (PR [#3424](https://github.com/pipecat-ai/pipecat/pull/3424))
+
+### Changed
+
+- Updated `ElevenLabsRealtimeSTTService` to accept the
+  `include_language_detection` parameter to detect language.
+
+  ```python
+    stt = ElevenLabsRealtimeSTTService(
+        api_key=os.getenv("ELEVENLABS_API_KEY"),
+        include_language_detection=True
+    )
+  ```
+
+  (PR [#3216](https://github.com/pipecat-ai/pipecat/pull/3216))
+
+- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved
+  VAD, Smart Turn capabilities, and brings dramatic improvements to latency
+  without any impact on accuracy. Use the `turn_detection_mode` parameter to control
+  the endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
+  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
+
+  ```python
+      stt = SpeechmaticsSTTService(
+          api_key=os.getenv("SPEECHMATICS_API_KEY"),
+          params=SpeechmaticsSTTService.InputParams(
+              language=Language.EN,
+              turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
+              speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
+          ),
+      )
+  ```
+
+  (PR [#3225](https://github.com/pipecat-ai/pipecat/pull/3225))
+
+- `daily-python` updated to 0.23.0.
+  (PR [#3257](https://github.com/pipecat-ai/pipecat/pull/3257))
+
+- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by
+  `DailyTransport` now include the transport source (i.e., the originating
+  audio track).
+  (PR [#3257](https://github.com/pipecat-ai/pipecat/pull/3257))
+
+- Updates to Inworld TTS services:
+
+  - Improved `InworldTTSService`'s websocket implementation to better flush
+    and close context to better handle long inputs.
+  - Improved docstrings for `InworldTTSService` and `InworldHttpTTSService`.
+    (PR [#3288](https://github.com/pipecat-ai/pipecat/pull/3288))
+
+- Improved the error handling and reconnection logic for `WebsocketServer` by
+  distinguishing between errors when disconnecting and websocket communication
+  errors.
+  (PR [#3392](https://github.com/pipecat-ai/pipecat/pull/3392))
+
+- Updated `DeepgramSTTService` to push user started/stopped speaking and
+  interruption frames when `vad_enabled` is set to true. This centralizes the
+  frames into the service, removing the need to have your application code
+  handle Deepgram's events and push these frames.
+  (PR [#3314](https://github.com/pipecat-ai/pipecat/pull/3314))
+
+- Added encoding validation to `DeepgramTTSService` to prevent unsupported
+  encodings from reaching the API. The service now raises `ValueError` at
+  initialization with a clear error message.
+  (PR [#3329](https://github.com/pipecat-ai/pipecat/pull/3329))
+
+- Updated `read_audio_frame` & `read_video_frame` methods in
+  `SmallWebRTCClient` to check if the track is enabled before logging a
+  warning.
+  (PR [#3336](https://github.com/pipecat-ai/pipecat/pull/3336))
+
+- Updated `CartesiaTTSService` to support setting `language=None`, resulting in
+  Cartesia auto-detecting the language of the conversation.
+  (PR [#3366](https://github.com/pipecat-ai/pipecat/pull/3366))
+
+- The bundled Smart Turn weights are now updated to v3.2, which has better
+  handling of short utterances, and is more robust against background noise.
+  (PR [#3367](https://github.com/pipecat-ai/pipecat/pull/3367))
+
+- Updated `SpeechmaticsSTTService` dependency to `speechmatics-voice[smart]>=0.2.6`
+  (PR [#3371](https://github.com/pipecat-ai/pipecat/pull/3371))
+
+- Smart Turn now takes into account `vad_start_seconds` when buffering audio,
+  meaning that the start of the turn audio is not cut off. This improves
+  accuracy for short utterances.
+
+- The default value of `pre_speech_ms` is now set to 500ms for Smart Turn.
+  (PR [#3377](https://github.com/pipecat-ai/pipecat/pull/3377))
+
+- Improved Krisp SDK management to allow `KrispVivaTurn` and `KrispVivaFilter`
+  to share a single SDK instance within the same process.
+  (PR [#3391](https://github.com/pipecat-ai/pipecat/pull/3391))
+
+- Updated default model for `GroqTTSService` to `canopylabs/orpheus-v1-english`
+  and voice ID to `autumn`.
+  (PR [#3399](https://github.com/pipecat-ai/pipecat/pull/3399))
+
+- Enhanced `FastAPIWebsocketTransport` with optional protocol-level audio
+  packetization via the `fixed_audio_packet_size` parameter to support media
+  endpoints requiring strict framing and real-time pacing.
+  (PR [#3410](https://github.com/pipecat-ai/pipecat/pull/3410))
+
+- `DeepgramTTSService` and `RimeTTSService` now set `append_trailing_space` to
+  `True` to prevent punctuation (e.g., “dot”) from being pronounced.
+  (PR [#3424](https://github.com/pipecat-ai/pipecat/pull/3424))
+
+- Updated `GeminiLiveLLMService` to push `LLMThoughtStartFrame`,
+  `LLMThoughtTextFrame`, and `LLMThoughtEndFrame` when the model returns
+  thought content.
+  (PR [#3431](https://github.com/pipecat-ai/pipecat/pull/3431))
+
+### Deprecated
+
+- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use
+  `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with
+  `LLMUserAggregator`'s new `user_turn_strategies` parameter instead.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- `FrameProcessor.interruption_strategies` is deprecated, use
+  `LLMUserAggregator`'s new `user_turn_strategies` parameter instead.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in
+  `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new
+  universal `LLMContext` and `LLMContextAggregatorPair` instead.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and
+  `UserStoppedSpeakingFrame` frames.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame`
+  frames are deprecated.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in
+  unexpected behavior, use `LLMUserAggregator`'s new `user_turn_strategies`
+  parameter instead.
+  (PR [#3045](https://github.com/pipecat-ai/pipecat/pull/3045))
+
+- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is
+  deprecated. Use the new `turn_detection_mode` parameter instead, with
+  `TurnDetectionMode.EXTERNAL`,`TurnDetectionMode.ADAPTIVE`, or
+  `TurnDetectionMode.SMART_TURN`. The `enable_vad` parameter is also
+  deprecated and is inferred from the `turn_detection_mode`.
+  (PR [#3225](https://github.com/pipecat-ai/pipecat/pull/3225))
+
+- `OpenAILLMContext` and its associated things (context aggregators, etc.) are
+  now deprecated in favor of the universal `LLMContext` and its associated
+  things.
+
+  From the developer's point of view, switching to using `LLMContext`
+  machinery will usually be a matter of going from this:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+  ```
+
+  To this:
+
+  ```
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(context)
+  ```
+
+  (PR [#3263](https://github.com/pipecat-ai/pipecat/pull/3263))
+
+- `STTMuteFilter` is deprecated and will be removed in a future version. Use
+  `LLMUserAggregator`'s new `user_mute_strategies` instead.
+  (PR [#3292](https://github.com/pipecat-ai/pipecat/pull/3292))
+
+- `FrameProcessor.interruptions_allowed` is now deprecated, use
+  `LLMUserAggregator`'s new parameter `user_mute_strategies` instead.
+  (PR [#3297](https://github.com/pipecat-ai/pipecat/pull/3297))
+
+- `PipelineParams.allow_interruptions` is now deprecated, use
+  `LLMUserAggregator`'s new parameter `user_turn_strategies` instead. For
+  example, to disable interruptions but still get user turns you can do:
+
+  ```python
+  context_aggregator = LLMContextAggregatorPair(
+      context,
+      user_params=LLMUserAggregatorParams(
+          user_turn_strategies=UserTurnStrategies(
+              start=[TranscriptionUserTurnStartStrategy(enable_interruptions=False)],
+          ),
+      ),
+  )
+  ```
+
+  (PR [#3297](https://github.com/pipecat-ai/pipecat/pull/3297))
+
+- `TranscriptProcessor` and related data classes and frames
+  (`TranscriptionMessage`, `ThoughtTranscriptionMessage`,
+  `TranscriptionUpdateFrame`) are deprecated. Use `LLMUserAggregator`'s and
+  `LLMAssistantAggregator`'s new events (`on_user_turn_stopped` and
+  `on_assistant_turn_stopped`) instead.
+  (PR [#3385](https://github.com/pipecat-ai/pipecat/pull/3385))
+
+- Deprecated support for the `vad_events` `LiveOptions` in
+  `DeepgramSTTService`. Instead, use a local Silero VAD for VAD events.
+  Additionally, deprecated `should_interrupt` which will be removed along with
+  `vad_events` support in a future release.
+  (PR [#3386](https://github.com/pipecat-ai/pipecat/pull/3386))
+
+- Loading external observers from files is deprecated, use the new pipeline
+  task setup files and `PIPECAT_SETUP_FILES` environment variable instead.
+  (PR [#3397](https://github.com/pipecat-ai/pipecat/pull/3397))
+
+### Fixed
+
+- Improved error handling in `ElevenLabsRealtimeSTTService`
+  (PR [#3233](https://github.com/pipecat-ai/pipecat/pull/3233))
+
+- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop
+  that blocks the process if the websocket disconnects due to an error
+  (PR [#3233](https://github.com/pipecat-ai/pipecat/pull/3233))
+
+- Fixed a bug in `STTMuteFilter` where the user was not always muted during
+  function calls, especially when there were multiple simultaneous calls.
+  (PR [#3292](https://github.com/pipecat-ai/pipecat/pull/3292))
+
+- Fixed a `RNNoiseFilter` issue that would cause a "[Errno 12] Cannot allocate
+  memory" error when processing silence audio frames.
+  (PR [#3322](https://github.com/pipecat-ai/pipecat/pull/3322))
+
+- Updated `SpeechmaticsSTTService` for version `0.0.99+`:
+
+  - Fixed `SpeechmaticsSTTService` to listen for `VADUserStoppedSpeakingFrame`
+    in order to finalize transcription.
+  - Default to `TurnDetectionMode.FIXED` for Pipecat-controlled end of turn
+    detection.
+  - Only emit VAD + interruption frames if VAD is enabled within the plugin
+    (modes other than `TurnDetectionMode.FIXED` or `TurnDetectionMode.EXTERNAL`).
+    (PR [#3328](https://github.com/pipecat-ai/pipecat/pull/3328))
+
+- Fixed an issue with function calling where a handler failing to invoke its
+  result callback could leave the context stuck in IN_PROGRESS, causing LLM
+  inference for subsequent function call results to block while waiting on the
+  unresolved call.
+  (PR [#3343](https://github.com/pipecat-ai/pipecat/pull/3343))
+
+- Fixed an issue with DeepgramTTSService where the model would output "Dot"
+  instead of a period in some circumstances.
+  (PR [#3345](https://github.com/pipecat-ai/pipecat/pull/3345))
+
+- Fixed an issue in `traced_stt` where `model_name` in OpenTelemetry appears as
+  `unknown`.
+  (PR [#3351](https://github.com/pipecat-ai/pipecat/pull/3351))
+
+- Fixed an issue in GeminiLiveLLMService where TranscriptionFrames were
+  occasionally not pushed.
+  (PR [#3356](https://github.com/pipecat-ai/pipecat/pull/3356))
+
+- Fixed potential memory leaks and initialization issues in `KrispVivaFilter`
+  by improving SDK lifecycle management.
+  (PR [#3391](https://github.com/pipecat-ai/pipecat/pull/3391))
+
+- Fixed timing issue in `BaseOutputTransport` where the bot speaking flag was
+  set after awaiting, allowing the event loop to re-enter the method before the
+  guard was set.
+  (PR [#3400](https://github.com/pipecat-ai/pipecat/pull/3400))
+
+- Fixed parallel function calling when using Gemini thinking.
+  (PR [3420](https://github.com/pipecat-ai/pipecat/pull/3420))
+
+- Fixed an issue in `traced_llm` where `model_name` in OpenTelemetry appears as
+  `unknown`.
+  (PR [#3422](https://github.com/pipecat-ai/pipecat/pull/3422))
+
+- Fixed an issue in `traced_tts`, `traced_gemini_live`, and
+  `traced_openai_realtime` where `model_name` in OpenTelemetry appears as
+  `unknown`.
+  (PR [#3428](https://github.com/pipecat-ai/pipecat/pull/3428))
+
+- Fixed `request_image_frame` (for backwards compatibility) and restored
+  function-call–related fields in `UserImageRequestFrame` and
+  `UserImageRawFrame`, preventing a case where adding a non-LLM message to the
+  context could trigger duplicate LLM inferences (on image arrival and on
+  function-call result), potentially causing an infinite inference loop.
+  (PR [#3430](https://github.com/pipecat-ai/pipecat/pull/3430))
+
+- Fixed `LLMContext.create_audio_message()` by correcting an internal helper
+  that was incorrectly declared async while being run in `asyncio.to_thread()`.
+  (PR [#3435](https://github.com/pipecat-ai/pipecat/pull/3435))
+
+### Other
+
+- Added `52-live-transcription.py` foundational example demonstrating live
+  transcription and translation from English to Spanish. In this example, the
+  bot is not interruptible: as the user continues speaking, English
+  transcriptions are queued, and the bot continuously translates and speaks
+  each queued sentence in Spanish without being interrupted by new user speech.
+  (PR [#3316](https://github.com/pipecat-ai/pipecat/pull/3316))
+
+- Added a new foundational example `53-concurrent-llm-evaluation.py` that shows
+  how to use `UserTurnProcessor`.
+  (PR [#3372](https://github.com/pipecat-ai/pipecat/pull/3372))
+
+- Added a new foundational example `28-user-assistant-turns.py` that shows how
+  to use the new `LLMUserAggregator` and `LLMAssistantAggregator` events to
+  gather a conversation transcript.
+  (PR [#3385](https://github.com/pipecat-ai/pipecat/pull/3385))
+
 ## [0.0.98] - 2025-12-17
 
 ### Added

LICENSE

@@ -1,6 +1,6 @@
 BSD 2-Clause License
 
-Copyright (c) 2024–2025, Daily
+Copyright (c) 2024–2026, Daily
 
 Redistribution and use in source and binary forms, with or without
 modification, are permitted provided that the following conditions are met:

README.md

@@ -73,12 +73,12 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
 
 | 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), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [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), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                            |
+| 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), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [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), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [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), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [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), [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), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [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), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
+| 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), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [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), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [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), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [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), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox),                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | 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                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
-| Serializers         | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| Serializers         | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | 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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |

changelog/3045.added.md

@@ -1,42 +0,0 @@
-- Introducing user turn strategies. User turn strategies indicate when the user turn starts or stops. In conversational agents, these are often referred to as start/stop speaking or turn-taking plans or policies.
-
-  User turn start strategies indicate when the user starts speaking (e.g. using VAD events or when a user says one or more words).
-
-  User turn stop strategies indicate when the user stops speaking (e.g. using an end-of-turn detection model or by observing incoming transcriptions).
-
-  A list of strategies can be specified for both strategies; strategies are evaluated in order until one evaluates to true.
-
-  Available user turn start strategies:
-    - VADUserTurnStartStrategy
-    - TranscriptionUserTurnStartStrategy
-    - MinWordsUserTurnStartStrategy
-    - ExternalUserTurnStartStrategy
-
-  Available user turn stop strategies:
-    - TranscriptionUserTurnStopStrategy
-    - TurnAnalyzerUserTurnStopStrategy
-    - ExternalUserTurnStopStrategy
-
-  The default strategies are:
-
-    - start: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
-    - stop: [TranscriptionUserTurnStopStrategy]
-
-  Turn strategies are configured when setting up `LLMContextAggregatorPair`. For example:
-
-  ```python
-  context_aggregator = LLMContextAggregatorPair(
-      context,
-      user_params=LLMUserAggregatorParams(
-          user_turn_strategies=UserTurnStrategies(
-              stop=[
-                  TurnAnalyzerUserTurnStopStrategy(
-                      turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
-                  )
-              ],
-          )
-      ),
-  )
-  ```
-
-  In order to use the user turn strategies you must update to the new universal `LLMContext` and `LLMContextAggregatorPair`.

changelog/3045.deprecated.2.md

@@ -1 +0,0 @@
-- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in unexpected behavior, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.

changelog/3045.deprecated.3.md

@@ -1 +0,0 @@
-- `FrameProcessor.interruption_strategies` is deprecated, use `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.

changelog/3045.deprecated.4.md

@@ -1 +0,0 @@
-- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames are deprecated.

changelog/3045.deprecated.5.md

@@ -1 +0,0 @@
-- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames.

changelog/3045.deprecated.6.md

@@ -1 +0,0 @@
-- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new universal `LLMContext` and `LLMContextAggregatorPair` instead.

changelog/3045.deprecated.md

@@ -1 +0,0 @@
-- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with `LLMUserAggregator`'s new `turn_start_strategies` parameter instead.

changelog/3169.added.md

@@ -0,0 +1 @@
+- Added Hathora service to support Hathora-hosted TTS and STT models (only non-streaming)

changelog/3205.added.md

@@ -1 +0,0 @@
-- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural network via pyrnnoise library.

changelog/3225.changed.md

@@ -1,15 +0,0 @@
-- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
-  Smart Turn capabilities, and brings dramatic improvements to latency without
-  any impact on accuracy. Use the `turn_detection_mode` parameter to control the
-  endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
-  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
-  ```python
-    stt = SpeechmaticsSTTService(
-        api_key=os.getenv("SPEECHMATICS_API_KEY"),
-        params=SpeechmaticsSTTService.InputParams(
-            language=Language.EN,
-            turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
-            speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
-        ),
-    )
-  ```

changelog/3225.deprecated.md

@@ -1,4 +0,0 @@
-- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
-  Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
-  `TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
-  parameter is also deprecated and is inferred from the `turn_detection_mode`.

changelog/3233.fixed.md

@@ -1,2 +0,0 @@
-- Improved error handling in `ElevenLabsRealtimeSTTService`
-- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop that blocks the process if the websocket disconnects due to an error

changelog/3257.changed.2.md

@@ -1 +0,0 @@
-- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by `DailyTransport` now include the transport source (i.e., the originating audio track).

changelog/3257.changed.md

@@ -1 +0,0 @@
-- `daily-python` updated to 0.23.0.

changelog/3263.deprecated.md

@@ -1,15 +0,0 @@
-- `OpenAILLMContext` and its associated things (context aggregators, etc.) are now deprecated in favor of the universal `LLMContext` and its associated things.
-
-  From the developer's point of view, switching to using `LLMContext` machinery will usually be a matter of going from this:
-
-  ```python
-  context = OpenAILLMContext(messages, tools)
-  context_aggregator = llm.create_context_aggregator(context)
-  ```
-
-  To this:
-
-  ```
-  context = LLMContext(messages, tools)
-  context_aggregator = LLMContextAggregatorPair(context)
-  ```

changelog/3267.added.md

@@ -1,8 +0,0 @@
-- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time voice conversations:
-
-  - Support for real-time audio streaming with WebSocket connection
-  - Built-in server-side VAD (Voice Activity Detection)
-  - Multiple voice options: Ara, Rex, Sal, Eve, Leo
-  - Built-in tools support: web_search, x_search, file_search
-  - Custom function calling with standard Pipecat tools schema
-  - Configurable audio formats (PCM at 8kHz-48kHz)

changelog/3268.added.md

@@ -1 +0,0 @@
-- Added an approximation of TTFB for Ultravox.

changelog/3287.changed.md

@@ -0,0 +1 @@
+- Enhanced interruption handling in `AsyncAITTSService` by supporting multi-context WebSocket sessions for more robust context management.

changelog/3287.fixed.md

@@ -0,0 +1 @@
+- Corrected TTFB metric calculation in `AsyncAIHttpTTSService`.

changelog/3288.changed.md

@@ -1,5 +0,0 @@
-- Updates to Inworld TTS services:
-
-  - Improved `InworldTTSService`'s websocket implementation to better flush and
-    close context to better handle long inputs.
-  - Improved docstrings for `InworldTTSService` and `InworldHttpTTSService`.

changelog/3289.added.md

@@ -1 +0,0 @@
-- Added a new `AudioContextTTSService` to the TTS service base classes. The `AudioContextWordTTSService` now inherits from `AudioContextTTSService` and `WebsocketWordTTSService`.

changelog/3291.added.md

@@ -1,4 +0,0 @@
-- `LLMUserAggregator` now exposes the following events:
-   - `on_user_turn_started`: triggered when a user turn starts
-   - `on_user_turn_stopped`: triggered when a user turn ends
-   - `on_user_turn_stop_timeout`: triggered when a user turn does not stop and times out

changelog/3292.added.md

@@ -1,29 +0,0 @@
-- Introducing user mute strategies. User mute strategies indicate when user input should be muted based on the current system state.
-
-  In conversational agents, user mute strategies are used to prevent user input from interrupting bot speech, tool execution, or other critical system operations.
-
-  A list of strategies can be specified; all strategies are evaluated for every frame so that each strategy can maintain its internal state. A user frame is muted if any of the configured strategies indicates it should be muted.
-
-  Available user mute strategies:
-
-  * `FirstSpeechUserMuteStrategy`
-  * `MuteUntilFirstBotCompleteUserMuteStrategy`
-  * `AlwaysUserMuteStrategy`
-  * `FunctionCallUserMuteStrategy`
-
-  User mute strategies replace the legacy `STTMuteFilter` and provide a more flexible and composable approach to muting user input.
-
-  User mute strategies are configured when setting up the `LLMContextAggregatorPair`. For example:
-
-  ```python
-  context_aggregator = LLMContextAggregatorPair(
-      context,
-      user_params=LLMUserAggregatorParams(
-          user_mute_strategies=[
-              FirstSpeechUserMuteStrategy(),
-          ]
-      ),
-  )
-  ```
-
-  In order to use user mute strategies you should update to the new universal `LLMContext` and `LLMContextAggregatorPair`.

changelog/3292.deprecated.md

@@ -1 +0,0 @@
-- `STTMuteFilter` is deprecated and will be removed in a future version. Use `LLMUserAggregator`'s new `user_mute_strategies` instead.

changelog/3292.fixed.md

@@ -1 +0,0 @@
-- Fixed a bug in `STTMuteFilter` where the user was not always muted during function calls, especially when there were multiple simultaneous calls.

changelog/3297.deprecated.2.md

@@ -1 +0,0 @@
-- `FrameProcessor.interruptions_allowed` is now deprecated, use `LLMUserAggregator`'s new parameter `user_mute_strategies` instead.

changelog/3297.deprecated.md

@@ -1,12 +0,0 @@
-- `PipelineParams.allow_interruptions` is now deprecated, use `LLMUserAggregator`'s new parameter `turn_start_strategies` instead. For example, to disable interruptions but still get user turns you can do:
-
-  ```python
-  context_aggregator = LLMContextAggregatorPair(
-      context,
-      user_params=LLMUserAggregatorParams(
-          user_turn_strategies=UserTurnStrategies(
-              start=[TranscriptionUserTurnStartStrategy(enable_interruptions=False)],
-          ),
-      ),
-  )
-  ```

changelog/3300.added.md

@@ -1 +0,0 @@
-- Added `use_ssl` parameter to `NvidiaSTTService`, `NvidiaSegmentedSTTService` and `NvidiaTTSService`.

changelog/3314.changed.md

@@ -1 +0,0 @@
-- Updated `DeepgramSTTService` to push user started/stopped speaking and interruption frames when `vad_enabled` is set to true. This centralizes the frames into the service, removing the need to have your application code handle Deepgram's events and push these frames.

changelog/3316.added.md

@@ -1 +0,0 @@
-- Added `enable_interruptions` constructor argument to all user turn strategies. This tells the `LLMUserAggregator` to push or not push an `InterruptionFrame`.

changelog/3316.other.md

@@ -1 +0,0 @@
-- Added `52-live-transcription.py` foundational example demonstrating live transcription and translation from English to Spanish. In this example, the bot is not interruptible: as the user continues speaking, English transcriptions are queued, and the bot continuously translates and speaks each queued sentence in Spanish without being interrupted by new user speech.

changelog/3349.added.md

@@ -0,0 +1 @@
+- Added `CambTTSService`, using Camb.ai's TTS integration with MARS models (mars-flash, mars-pro, mars-instruct) for high-quality text-to-speech synthesis.

changelog/3446.fixed.md

@@ -0,0 +1,8 @@
+- Fixed an issue where the "bot-llm-text" RTVI event would not fire for realtime (speech-to-speech) services:
+
+  - `AWSNovaSonicLLMService`
+  - `GeminiLiveLLMService`
+  - `OpenAIRealtimeLLMService`
+  - `GrokRealtimeLLMService`
+
+  The issue was that these services weren't pushing `LLMTextFrame`s. Now they do.

changelog/3454.fixed.md

@@ -0,0 +1 @@
+- Fixed an issue where `on_user_turn_stop_timeout` could fire while a user is talking when using `ExternalUserTurnStrategies`.

changelog/3455.fixed.md

@@ -0,0 +1 @@
+- Fixed an issue where user turn start strategies were not being reset after a user turn started, causing incorrect strategy behavior.

changelog/3461.added.md

@@ -0,0 +1 @@
+- Added the `additional_headers` param to `WebsocketClientParams`, allowing `WebsocketClientTransport` to send custom headers on connect, for cases such as authentication.

changelog/3462.fixed.md

@@ -0,0 +1 @@
+- Fixed `MinWordsUserTurnStartStrategy` to not aggregate transcriptions, preventing incorrect turn starts when words are spoken with pauses between them.

changelog/3479.deprecated.md

@@ -0,0 +1 @@
+- For consistency with other package names, we just deprecated `pipecat.turns.mute` (introduced in Pipecat 0.0.99) in favor of `pipecat.turns.user_mute`.

changelog/3480.fixed.md

@@ -0,0 +1 @@
+- Fixed an issue where Grok Realtime would error out when running with SmallWebRTC transport.

changelog/3482.added.md

@@ -0,0 +1 @@
+- Added `UserIdleController` for detecting user idle state, integrated into `LLMUserAggregator` and `UserTurnProcessor` via optional `user_idle_timeout` parameter. Emits `on_user_turn_idle` event for application-level handling. Deprecated `UserIdleProcessor` in favor of the new compositional approach.

changelog/3483.changed.md

@@ -0,0 +1 @@
+- Throttle `UserSpeakingFrame` to broadcast at most every 200ms instead of on every audio chunk, reducing frame processing overhead during user speech.

changelog/3484.fixed.md

@@ -0,0 +1 @@
+- Fixed a `Mem0MemoryService` issue where passing `async_mode: true` was causing an error. See https://docs.mem0.ai/platform/features/async-mode-default-change.

changelog/3489.fixed.md

@@ -0,0 +1,3 @@
+- Fixed `AzureTTSService` transcript formatting issues:
+  - Punctuation now appears without extra spaces (e.g., "Hello!" instead of "Hello !")
+  - CJK languages (Chinese, Japanese, Korean) no longer have unwanted spaces between characters

changelog/3490.added.md

@@ -0,0 +1 @@
+- Added `on_user_mute_started` and `on_user_mute_stopped` event handlers to `LLMUserAggregator` for tracking user mute state changes.

docs/api/conf.py

@@ -91,6 +91,25 @@ autodoc_mock_imports = [
     # MLX dependencies (Apple Silicon specific)
     "mlx",
     "mlx_whisper",  # Note: might need underscore format too
+    # Pydantic v2 compatibility issues in third-party SDKs
+    "hume",
+    "hume.tts",
+    "hume.tts.types",
+    "cartesia",
+    "camb",
+    "sarvamai",
+    "openpipe",
+    "openai.types.beta.realtime",
+    "langchain_core",
+    "langchain_core.messages",
+    # FastAPI - Pydantic v2 compatibility issues during Sphinx autodoc
+    "fastapi",
+    "fastapi.applications",
+    "fastapi.routing",
+    "fastapi.params",
+    "fastapi.middleware",
+    "fastapi.responses",
+    "uvicorn",
 ]
 
 # HTML output settings

env.example

@@ -31,6 +31,9 @@ AZURE_DALLE_API_KEY=...
 AZURE_DALLE_ENDPOINT=https://...
 AZURE_DALLE_MODEL=...
 
+# Camb.ai
+CAMB_API_KEY=...
+
 # Cartesia
 CARTESIA_API_KEY=...
 CARTESIA_VOICE_ID=...
@@ -82,6 +85,9 @@ GROK_API_KEY=...
 # Groq
 GROQ_API_KEY=...
 
+# Hathora
+HATHORA_API_KEY=...
+
 # Heygen
 HEYGEN_API_KEY=...
 HEYGEN_LIVE_AVATAR_API_KEY=...
@@ -97,7 +103,8 @@ INWORLD_API_KEY=...
 KRISP_MODEL_PATH=...
 
 # Krisp Viva
-KRISP_VIVA_MODEL_PATH=...
+KRISP_VIVA_FILTER_MODEL_PATH=...
+KRISP_VIVA_TURN_MODEL_PATH=...
 
 # LiveKit
 LIVEKIT_API_KEY=...

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/foundational/01c-nvidia-riva-tts.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

examples/foundational/03-still-frame.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -85,7 +85,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -98,11 +98,11 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -68,7 +68,7 @@ async def main():
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(
                 user_turn_strategies=UserTurnStrategies(
@@ -82,11 +82,11 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -78,7 +78,7 @@ async def main():
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -91,11 +91,11 @@ async def main():
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -106,7 +106,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -119,12 +119,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),
             stt,
-            context_aggregator.user(),
+            user_aggregator,
             llm,
             tts,
             ml,
             transport.output(),
-            context_aggregator.assistant(),
+            assistant_aggregator,
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -138,12 +138,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),
             stt,
-            context_aggregator.user(),
+            user_aggregator,
             llm,
             tts,
             image_sync_aggregator,
             transport.output(),
-            context_aggregator.assistant(),
+            assistant_aggregator,
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -77,7 +77,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -90,11 +90,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

examples/foundational/07-interruptible.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -89,11 +89,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -131,7 +131,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
         )
@@ -140,11 +140,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -117,7 +117,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(
                 user_turn_strategies=UserTurnStrategies(
@@ -132,11 +132,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -103,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     lc = LangchainProcessor(history_chain)
 
     context = LLMContext()
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -116,11 +116,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             lc,  # Langchain
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -71,7 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
     )
@@ -80,11 +80,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -81,7 +81,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(
                 user_turn_strategies=UserTurnStrategies(
@@ -96,11 +96,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -86,7 +86,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -99,11 +99,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
     )
@@ -81,11 +81,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -88,11 +88,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -85,7 +85,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(
                 user_turn_strategies=UserTurnStrategies(
@@ -100,11 +100,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -91,11 +91,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -91,11 +91,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -80,7 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -93,11 +93,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -84,7 +84,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -97,11 +97,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -84,7 +84,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -97,11 +97,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -91,11 +91,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -83,7 +83,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -96,11 +96,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -81,7 +81,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]
 
         context = LLMContext(messages)
-        context_aggregator = LLMContextAggregatorPair(
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(
                 user_turn_strategies=UserTurnStrategies(
@@ -96,11 +96,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             [
                 transport.input(),  # Transport user input
                 stt,
-                context_aggregator.user(),  # User responses
+                user_aggregator,  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                context_aggregator.assistant(),  # Assistant spoken responses
+                assistant_aggregator,  # Assistant spoken responses
             ]
         )
 

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

@@ -0,0 +1,140 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+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.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.cartesia.tts import CartesiaTTSService
+from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
+from pipecat.services.gladia.stt import GladiaSTTService
+from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transcriptions.language import Language
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
+
+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(params=VADParams(stop_secs=0.2)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = GladiaSTTService(
+        api_key=os.getenv("GLADIA_API_KEY", ""),
+        region=os.getenv("GLADIA_REGION"),
+        params=GladiaInputParams(
+            language_config=LanguageConfig(
+                languages=[Language.EN],
+            ),
+            enable_vad=True,
+        ),
+    )
+
+    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": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # 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([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/07j-interruptible-gladia.py

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -87,7 +87,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -100,11 +100,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -75,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -88,11 +88,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User respones
+            user_aggregator,  # User respones
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -89,11 +89,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -120,7 +120,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Setup context aggregators for message handling
     context = LLMContext()
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -133,11 +133,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # Speech-to-text
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # Strands Agents processor
             tts,  # Text-to-speech
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -80,7 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -93,11 +93,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -102,7 +102,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -115,11 +115,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # Gemini TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -107,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -120,11 +120,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # Gemini TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -103,11 +103,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User respones
+            user_aggregator,  # User respones
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -103,11 +103,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User respones
+            user_aggregator,  # User respones
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,5 +1,5 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
@@ -80,7 +80,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
@@ -93,11 +93,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )
 

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

@@ -1,9 +1,26 @@
 #
-# Copyright (c) 2024–2025, Daily
+# Copyright (c) 2024-2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+"""Interruptible bot with Krisp VIVA noise filtering and turn detection.
+
+This example demonstrates a conversational bot with:
+- Krisp VIVA noise reduction on incoming audio
+- Krisp VIVA Turn detection for natural interruptions
+- Voice activity detection (VAD)
+
+Required environment variables:
+- KRISP_VIVA_FILTER_MODEL_PATH: Path to the Krisp noise filter model file (.kef)
+- KRISP_VIVA_TURN_MODEL_PATH: Path to the Krisp turn detection model file (.kef)
+- DEEPGRAM_API_KEY: Deepgram API key for STT/TTS
+- OPENAI_API_KEY: OpenAI API key for LLM
+
+Optional environment variables:
+- KRISP_NOISE_SUPPRESSION_LEVEL: Noise suppression level 0-100 (default: 100)
+  Higher values = more aggressive noise reduction
+"""
 
 import os
 
@@ -11,7 +28,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.filters.krisp_viva_filter import KrispVivaFilter
-from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
+from pipecat.audio.turn.krisp_viva_turn import KrispTurnParams, KrispVivaTurn
 from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.frames.frames import LLMRunFrame
@@ -78,11 +95,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     ]
 
     context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
             user_turn_strategies=UserTurnStrategies(
-                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
+                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=KrispVivaTurn())]
             ),
         ),
     )
@@ -91,11 +108,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         [
             transport.input(),  # Transport user input
             stt,  # STT
-            context_aggregator.user(),  # User responses
+            user_aggregator,  # User responses
             llm,  # LLM
             tts,  # TTS
             transport.output(),  # Transport bot output
-            context_aggregator.assistant(),  # Assistant spoken responses
+            assistant_aggregator,  # Assistant spoken responses
         ]
     )