wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update changelog for version 0.0.99

Browse Source
This commit is contained in:
aconchillo
2026-01-14 00:49:15 +00:00
committed by github-actions[bot]
parent 6fd5847f84
commit 4531d517da
74 changed files with 522 additions and 230 deletions
Download Patch File Download Diff File Expand all files Collapse all files

522
CHANGELOG.md
View File

@@ -7,6 +7,528 @@ 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))
- 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`
- 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 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

42
changelog/3045.added.md
View File

@@ -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`.

1
changelog/3045.deprecated.2.md
View File

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

1
changelog/3045.deprecated.3.md
View File

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

1
changelog/3045.deprecated.4.md
View File

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

1
changelog/3045.deprecated.5.md
View File

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

1
changelog/3045.deprecated.6.md
View File

@@ -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.

1
changelog/3045.deprecated.md
View File

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

1
changelog/3205.added.md
View File

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

7
changelog/3216.changed.md
View File

@@ -1,7 +0,0 @@
- 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
)
```

15
changelog/3225.changed.md
View File

@@ -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}>",
),
)
```

4
changelog/3225.deprecated.md
View File

@@ -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`.

2
changelog/3233.fixed.md
View File

@@ -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

1
changelog/3257.changed.2.md
View File

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

1
changelog/3257.changed.md
View File

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

15
changelog/3263.deprecated.md
View File

@@ -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)
```

8
changelog/3267.added.md
View File

@@ -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)

1
changelog/3268.added.md
View File

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

5
changelog/3288.changed.md
View File

@@ -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`.

1
changelog/3289.added.md
View File

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

4
changelog/3291.added.md
View File

@@ -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

29
changelog/3292.added.md
View File

@@ -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`.

1
changelog/3292.deprecated.md
View File

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

1
changelog/3292.fixed.md
View File

@@ -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.

1
changelog/3297.deprecated.2.md
View File

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

12
changelog/3297.deprecated.md
View File

@@ -1,12 +0,0 @@
- `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)],
),
),
)
```

1
changelog/3300.added.md
View File

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

1
changelog/3314.changed.md
View File

@@ -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.

1
changelog/3316.added.md
View File

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

1
changelog/3316.other.md
View File

@@ -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.

1
changelog/3322.fixed.md
View File

@@ -1 +0,0 @@
- Fixed a `RNNoiseFilter` issue that would cause a "[Errno 12] Cannot allocate memory" error when processing silence audio frames.

1
changelog/3328.added.md
View File

@@ -1 +0,0 @@
- Added `split_sentences` parameter to `SpeechmaticsSTTService` to control sentence splitting behavior for finals on sentence boundaries.

4
changelog/3328.fixed.md
View File

@@ -1,4 +0,0 @@
- 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`).

1
changelog/3329.changed.md
View File

@@ -1 +0,0 @@
- 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.

2
changelog/3334.added.md
View File

@@ -1,2 +0,0 @@
- Added word-level timestamp support to `AzureTTSService` for accurate text-to-audio synchronization.

1
changelog/3336.changed.md
View File

@@ -1 +0,0 @@
- Updated `read_audio_frame` & `read_video_frame` methods in `SmallWebRTCClient` to check if the track is enabled before logging a warning.

1
changelog/3343.fixed.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3345.fixed.md
View File

@@ -1 +0,0 @@
- Fixed an issue with DeepgramTTSService where the model would output "Dot" instead of a period in some circumstances.

1
changelog/3346.added.md
View File

@@ -1 +0,0 @@
- Added `pronunciation_dict_id` parameter to `CartesiaTTSService.InputParams` and `CartesiaHttpTTSService.InputParams` to support Cartesia's pronunciation dictionary feature for custom pronunciations.

1
changelog/3351.fixed.md
View File

@@ -1 +0,0 @@
- Fixed an issue in `traced_stt` where `model_name` in OpenTelemetry appears as `unknown`.

1
changelog/3356.fixed.md
View File

@@ -1 +0,0 @@
- Fixed an issue in GeminiLiveLLMService where TranscriptionFrames were occasionally not pushed.

1
changelog/3357.added.md
View File

@@ -1 +0,0 @@
- Added support for using the HeyGen LiveAvatar API with the `HeyGenTransport` (see https://www.liveavatar.com/).

8
changelog/3360.added.md
View File

@@ -1,8 +0,0 @@
- 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

1
changelog/3366.changed.md
View File

@@ -1 +0,0 @@
- Updated `CartesiaTTSService` to support setting `language=None`, resulting in Cartesia auto-detecting the language of the conversation.

3
changelog/3367.changed.md
View File

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

1
changelog/3371.changed.md
View File

@@ -1 +0,0 @@
- Updated `SpeechmaticsSTTService` dependency to `speechmatics-voice[smart]>=0.2.6`

1
changelog/3372.added.2.md
View File

@@ -1 +0,0 @@
- Added `UserTurnProcessor`, a frame processor built on `UserTurnController` that pushes `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames and interruptions based on the controller's user turn strategies.

1
changelog/3372.added.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3372.other.md
View File

@@ -1 +0,0 @@
- Added a new foundational example `53-concurrent-llm-evaluation.py` that shows how to use `UserTurnProcessor`.

1
changelog/3374.added.md
View File

@@ -1 +0,0 @@
- Added `should_interrupt` property to `DeepgramFluxSTTService`, `DeepgramSTTService`, and `SpeechmaticsSTTService` to configure whether the bot should be interrupted when the external service detects user speech.

5
changelog/3377.changed.md
View File

@@ -1,5 +0,0 @@
- 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.

4
changelog/3385.added.md
View File

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

1
changelog/3385.deprecated.md
View File

@@ -1 +0,0 @@
- `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.

1
changelog/3385.other.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3386.deprecated.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3391.added.md
View File

@@ -1 +0,0 @@
- Added `KrispVivaTurn` analyzer for end of turn detection using the Krisp VIVA SDK (requires `krisp_audio`).

1
changelog/3391.changed.md
View File

@@ -1 +0,0 @@
- Improved Krisp SDK management to allow `KrispVivaTurn` and `KrispVivaFilter` to share a single SDK instance within the same process.

1
changelog/3391.fixed.md
View File

@@ -1 +0,0 @@
- Fixed potential memory leaks and initialization issues in `KrispVivaFilter` by improving SDK lifecycle management.

6
changelog/3397.added.md
View File

@@ -1,6 +0,0 @@
- 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):
...
```

1
changelog/3397.deprecated.md
View File

@@ -1 +0,0 @@
- Loading external observers from files is deprecated, use the new pipeline task setup files and `PIPECAT_SETUP_FILES` environment variable instead.

1
changelog/3399.changed.md
View File

@@ -1 +0,0 @@
- Updated default model for `GroqTTSService` to `canopylabs/orpheus-v1-english` and voice ID to `autumn`.

1
changelog/3400.fixed.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3403.added.md
View File

@@ -1 +0,0 @@
- Added a keepalive task for `InworldTTSService` to keep the service connected in the event of no generations for longer periods of time.

1
changelog/3404.added.2.md
View File

@@ -1 +0,0 @@
- Added `enable_vad` to `Params` for use in the `GladiaSTTService`. When enabled, `GladiaSTTService` acts as the turn controller, emitting `UserStartedSpeakingFrame`, `UserStoppedSpeakingFrame`, and optionally `InterruptionFrame`.

1
changelog/3404.added.md
View File

@@ -1 +0,0 @@
- Added `should_interrupt` property to `GladiaSTTService` to configure whether the bot should be interrupted when the external service detects user speech.

1
changelog/3410.added.md
View File

@@ -1 +0,0 @@
- Added `VonageFrameSerializer` for the Vonage Video API Audio Connector WebSocket protocol.

1
changelog/3410.changed.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3422.fixed.md
View File

@@ -1 +0,0 @@
- Fixed an issue in `traced_llm` where `model_name` in OpenTelemetry appears as `unknown`.

1
changelog/3424.added.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3424.changed.md
View File

@@ -1 +0,0 @@
- `DeepgramTTSService` and `RimeTTSService` now set `append_trailing_space` to `True` to prevent punctuation (e.g., “dot”) from being pronounced.

1
changelog/3428.fixed.md
View File

@@ -1 +0,0 @@
- Fixed an issue in `traced_tts`, `traced_gemini_live`, and `traced_openai_realtime` where `model_name` in OpenTelemetry appears as `unknown`.

1
changelog/3430.fixed.md
View File

@@ -1 +0,0 @@
- 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.

1
changelog/3431.changed.md
View File

@@ -1 +0,0 @@
- Updated `GeminiLiveLLMService` to push `LLMThoughtStartFrame`, `LLMThoughtTextFrame`, and `LLMThoughtEndFrame` when the model returns thought content.

1
changelog/3435.fixed.md
View File

@@ -1 +0,0 @@
- Fixed `LLMContext.create_audio_message()` by correcting an internal helper that was incorrectly declared async while being run in `asyncio.to_thread()`.