scripts(evals): run evals in parallel

Merge pull request #4179 from pipecat-ai/pk/fix-gemini-live-vertex
Don't send history_config for Gemini Live Vertex (unsupported)
2026-03-27 15:37:01 -07:00 · 2026-03-27 17:34:29 -04:00 · 2026-03-27 17:30:47 -04:00 · 2026-03-27 17:20:06 -04:00 · 2026-03-27 17:13:17 -04:00 · 2026-03-27 16:50:37 -04:00
453 changed files with 14233 additions and 5555 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,316 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 <!-- towncrier release notes start -->

+## [0.0.107] - 2026-03-23
+
+### Added
+
+- Added `frame_order` parameter to `SyncParallelPipeline`. Set
+  `frame_order=FrameOrder.PIPELINE` to push synchronized output frames in
+  pipeline definition order (all frames from the first pipeline, then the
+  second, etc.) instead of the default arrival order.
+  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
+
+- Added `sync_with_audio` field to `OutputImageRawFrame`. When set to `True`,
+  the output transport queues image frames with audio so they are displayed
+  only after all preceding audio has been sent, enabling synchronized
+  audio/image playback.
+  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
+
+- Added `OpenAIResponsesLLMService`, a new LLM service that uses the OpenAI
+  Responses API. Supports streaming text, function calling, usage metrics, and
+  out-of-band inference. Works with the universal `LLMContext` and
+  `LLMContextAggregatorPair`. See
+  `examples/foundational/07-interruptible-openai-responses.py` and
+  `14-function-calling-openai-responses.py`.
+  (PR [#4074](https://github.com/pipecat-ai/pipecat/pull/4074))
+
+- Added `audio_out_auto_silence` parameter to `TransportParams` (defaults to
+  `True`). When set to `False`, the transport waits for audio data instead of
+  inserting silence when the output queue is empty, which is useful for
+  scenarios that require uninterrupted audio playback without artificial gaps.
+  (PR [#4104](https://github.com/pipecat-ai/pipecat/pull/4104))
+
+### Changed
+
+- Renamed tracing span attributes to align with OpenTelemetry GenAI semantic
+  conventions: `gen_ai.system` to `gen_ai.provider.name`, `system` to
+  `gen_ai.system_instructions`, `gen_ai.usage.cache_read_input_tokens` to
+  `gen_ai.usage.cache_read.input_tokens`, and
+  `gen_ai.usage.cache_creation_input_tokens` to
+  `gen_ai.usage.cache_creation.input_tokens`.
+  (PR [#3449](https://github.com/pipecat-ai/pipecat/pull/3449))
+
+- `DeepgramSageMakerTTSService` now correctly routes audio through the base
+  `TTSService` audio context queue. Audio frames are delivered via
+  `append_to_audio_context()` instead of being pushed directly, enabling proper
+  ordering, interruption handling, and start/stop frame lifecycle management.
+  Interruptions now trigger a `Clear` message to Deepgram (flushing its text
+  buffer) at the right time via `on_audio_context_interrupted`.
+  (PR [#4083](https://github.com/pipecat-ai/pipecat/pull/4083))
+
+- `GradiumTTSService` now sends a per-context `setup` message with
+  `client_req_id` before the first text message for each TTS context, following
+  Gradium's multiplexing protocol. Previously, a single setup message was sent
+  at connection time without a `client_req_id`, which prevented Gradium from
+  associating requests with their sessions when using `close_ws_on_eos=False`.
+  (PR [#4091](https://github.com/pipecat-ai/pipecat/pull/4091))
+
+### Fixed
+
+- Fixed stale `system_instruction` in LLM tracing spans by reading from
+  `_settings.system_instruction` instead of the removed `_system_instruction`
+  attribute.
+  (PR [#3449](https://github.com/pipecat-ai/pipecat/pull/3449))
+
+- Fixed `SyncParallelPipeline` breaking the Whisker debugger.
+  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
+
+- Fixed `SyncParallelPipeline` race condition where concurrent SystemFrame
+  processing (e.g. from RTVI) could corrupt sink queues and cause deadlocks.
+  SystemFrames now take a fast path that passes them through without draining
+  queued output.
+  (PR [#4029](https://github.com/pipecat-ai/pipecat/pull/4029))
+
+- Fixed TTS frame ordering so that non-system frames always arrive in correct
+  order relative to the `TTSStartedFrame`/`TTSAudioRawFrame`/`TTSStoppedFrame`
+  sequence. Previously these frames could race ahead of or behind audio context
+  frames, producing out-of-order output downstream.
+  (PR [#4075](https://github.com/pipecat-ai/pipecat/pull/4075))
+
+- Fixed `SarvamTTSService` audio and error frames now route through
+  `append_to_audio_context()` instead of `push_frame()`, ensuring correct
+  behavior with audio contexts and interruptions.
+  (PR [#4082](https://github.com/pipecat-ai/pipecat/pull/4082))
+
+- Fixed audio frame ordering and interruption handling in Fish Audio, LMNT,
+  Neuphonic, and Rime NonJson TTS services. These services were bypassing the
+  base `TTSService` audio context serialization queue by pushing audio frames
+  directly, which could cause out-of-order frames and broken interruptions
+  during speech.
+  (PR [#4090](https://github.com/pipecat-ai/pipecat/pull/4090))
+
+- Fixed Genesys AudioHook serializer to always include the `parameters` field in
+  protocol messages. The AudioHook protocol requires every message to carry a
+  `parameters` object (even if empty), but `_create_message` omitted it when no
+  parameters were provided. This caused clients that validate message structure
+  (including the Genesys reference implementation) to reject `pong` and
+  parameter-less `closed` responses, breaking server sequence tracking and
+  preventing `outputVariables` from reaching the Architect flow.
+  (PR [#4093](https://github.com/pipecat-ai/pipecat/pull/4093))
+
+## [0.0.106] - 2026-03-18
+
+### Added
+
+- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its
+  subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`,
+  `STTUpdateSettingsFrame`) to target a specific service instance. When
+  `service` is set, only the matching service applies the settings; others
+  forward the frame unchanged. This enables updating a single service when
+  multiple services of the same type exist in the pipeline.
+  (PR [#4004](https://github.com/pipecat-ai/pipecat/pull/4004))
+
+- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily
+  runner. These convenience parameters let callers specify a SIP provider name
+  and geographic region directly without manually constructing
+  `DailyRoomProperties` and `DailyRoomSipParams`.
+  (PR [#4005](https://github.com/pipecat-ai/pipecat/pull/4005))
+
+- Added `PerplexityLLMAdapter` that automatically transforms conversation
+  messages to satisfy Perplexity's stricter API constraints (strict role
+  alternation, no non-initial system messages, last message must be user/tool).
+  Previously, certain conversation histories could cause Perplexity API errors
+  that didn't occur with OpenAI (`PerplexityLLMService` subclasses
+  `OpenAILLMService` since Perplexity uses an OpenAI-compatible API).
+  (PR [#4009](https://github.com/pipecat-ai/pipecat/pull/4009))
+
+- Added DTMF input event support to the Daily transport. Incoming DTMF tones
+  are now received via Daily's `on_dtmf_event` callback and pushed into the
+  pipeline as `InputDTMFFrame`, enabling bots to react to keypad presses from
+  phone callers.
+  (PR [#4047](https://github.com/pipecat-ai/pipecat/pull/4047))
+
+- Added `WakePhraseUserTurnStartStrategy` for triggering user turns based on
+  wake phrases, with support for `single_activation` mode. Deprecates
+  `WakeCheckFilter`.
+  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
+
+- Added `default_user_turn_start_strategies()` and
+  `default_user_turn_stop_strategies()` helper functions for composing custom
+  strategy lists.
+  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
+
+### Changed
+
+- Changed tool result JSON serialization to use `ensure_ascii=False`,
+  preserving UTF-8 characters instead of escaping them. This reduces context
+  size and token usage for non-English languages.
+  (PR [#3457](https://github.com/pipecat-ai/pipecat/pull/3457))
+
+- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of
+  `OpenAIRealtimeSTTSettings`, making it runtime-updatable via
+  `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is
+  deprecated as of 0.0.106.
+  (PR [#3991](https://github.com/pipecat-ai/pipecat/pull/3991))
+
+- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable
+  release).
+  (PR [#3997](https://github.com/pipecat-ai/pipecat/pull/3997))
+
+- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`,
+  aligning it with the HeyGen and Tavus video services. It supports
+  `SimliVideoService.Settings(...)` for configuration and uses
+  `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage
+  (`api_key`, `face_id`, etc.) remains unchanged.
+  (PR [#4001](https://github.com/pipecat-ai/pipecat/pull/4001))
+
+- Update `pipecat-ai-small-webrtc-prebuilt` to `2.4.0`.
+  (PR [#4023](https://github.com/pipecat-ai/pipecat/pull/4023))
+
+- Nova Sonic assistant text transcripts are now delivered in real-time using
+  speculative text events instead of delayed final text events. Previously,
+  assistant text only arrived after all audio had finished playing, causing
+  laggy transcripts in client UIs. Speculative text arrives before each audio
+  chunk, providing text synchronized with what the bot is saying. This also
+  simplifies the internal text handling by removing the interruption re-push
+  hack and assistant text buffer.
+  (PR [#4042](https://github.com/pipecat-ai/pipecat/pull/4042))
+
+- Updated `daily-python` dependency to 0.25.0.
+  (PR [#4047](https://github.com/pipecat-ai/pipecat/pull/4047))
+
+- Added `enable_dialout` parameter to `configure()` in `pipecat.runner.daily`
+  to support dial-out rooms. Also narrowed misleading `Optional` type hints and
+  deduplicated token expiry calculation.
+  (PR [#4048](https://github.com/pipecat-ai/pipecat/pull/4048))
+
+- Extended `ProcessFrameResult` to stop strategies, allowing a stop strategy to
+  short-circuit evaluation of subsequent strategies by returning `STOP`.
+  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
+
+- `GradiumSTTService` now takes both an `encoding` and `sample_rate`
+  constructor argument which is assmebled in the class to form the
+  `input_format`. PCM accepts `8000`, `16000`, and `24000` Hz sample rates.
+  (PR [#4066](https://github.com/pipecat-ai/pipecat/pull/4066))
+
+- Improved `GradiumSTTService` transcription accuracy by reworking how text
+  fragments are accumulated and finalized. Previously, trailing words could be
+  dropped when the server's `flushed` response arrived before all text tokens
+  were delivered. The service now uses a short aggregation delay after flush to
+  capture trailing tokens, producing complete utterances.
+  (PR [#4066](https://github.com/pipecat-ai/pipecat/pull/4066))
+
+### Deprecated
+
+- `SimliVideoService.InputParams` is deprecated. Use the direct constructor
+  parameters `max_session_length`, `max_idle_time`, and `enable_logging`
+  instead.
+  (PR [#4001](https://github.com/pipecat-ai/pipecat/pull/4001))
+
+- Deprecated `LocalSmartTurnAnalyzerV2` and `LocalCoreMLSmartTurnAnalyzer`. Use
+  `LocalSmartTurnAnalyzerV3` instead. Instantiating these analyzers will now
+  emit a `DeprecationWarning`.
+  (PR [#4012](https://github.com/pipecat-ai/pipecat/pull/4012))
+
+- Deprecated `WakeCheckFilter` in favor of `WakePhraseUserTurnStartStrategy`.
+  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
+
+### Fixed
+
+- Fixed an issue where the default model for `OpenAILLMService` and
+  `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now
+  restored to `gpt-4.1`.
+  (PR [#4000](https://github.com/pipecat-ai/pipecat/pull/4000))
+
+- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut
+  down before in-flight frames (e.g. LLM function call responses) finished
+  processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline
+  as `ControlFrame`s, ensuring all pending work is flushed before shutdown
+  begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate
+  (`SystemFrame`).
+  (PR [#4006](https://github.com/pipecat-ai/pipecat/pull/4006))
+
+- Fixed `ParallelPipeline` dropping or misordering frames during lifecycle
+  synchronization. Buffered frames are now flushed in the correct order
+  relative to synchronization frames (`StartFrame` goes first,
+  `EndFrame`/`CancelFrame` go after), and frames added to the buffer during
+  flush are also drained.
+  (PR [#4007](https://github.com/pipecat-ai/pipecat/pull/4007))
+
+- Fixed `TTSService` potentially canceling in-flight audio during shutdown. The
+  stop sequence now waits for all queued audio contexts to finish processing
+  before canceling the stop frame task.
+  (PR [#4007](https://github.com/pipecat-ai/pipecat/pull/4007))
+
+- Fixed `Language` enum values (e.g. `Language.ES`) not being converted to
+  service-specific codes when passed via
+  `settings=Service.Settings(language=Language.ES)` at init time. This caused
+  API errors (e.g. 400 from Rime) because the raw enum was sent instead of the
+  expected language code (e.g. `"spa"`). Runtime updates via
+  `UpdateSettingsFrame` were unaffected. The fix centralizes conversion in the
+  base `TTSService` and `STTService` classes so all services handle this
+  consistently.
+  (PR [#4024](https://github.com/pipecat-ai/pipecat/pull/4024))
+
+- Fixed `DeepgramSTTService` ignoring the `base_url` scheme when using `ws://`
+  or `http://`. Previously these were silently overwritten with `wss://` /
+  `https://`, breaking air-gapped or private deployments that don't use TLS.
+  All scheme choices (`wss://`, `https://`, `ws://`, `http://`, or bare
+  hostname) are now respected.
+  (PR [#4026](https://github.com/pipecat-ai/pipecat/pull/4026))
+
+- Fixed `LLMSwitcher.register_function()` and `register_direct_function()` not
+  accepting or forwarding the `timeout_secs` parameter.
+  (PR [#4037](https://github.com/pipecat-ai/pipecat/pull/4037))
+
+- Fixed empty user transcriptions in Nova Sonic causing spurious interruptions.
+  Previously, an empty transcription could trigger an interruption of the
+  assistant's response even though the user hadn't actually spoken.
+  (PR [#4042](https://github.com/pipecat-ai/pipecat/pull/4042))
+
+- Fixed `SonioxSTTService` and `OpenAIRealtimeSTTService` crash when language
+  parameters contain plain strings instead of `Language` enum values.
+  (PR [#4046](https://github.com/pipecat-ai/pipecat/pull/4046))
+
+- Fixed premature user turn stops caused by late transcriptions arriving
+  between turns. A stale transcript from the previous turn could persist into
+  the next turn and trigger a stop before the current turn's real transcript
+  arrived. Stop strategies are now reset at both turn start and turn stop to
+  prevent state from leaking across turn boundaries.
+  (PR [#4057](https://github.com/pipecat-ai/pipecat/pull/4057))
+
+- Fixed raw language strings like `"de-DE"` silently failing when passed to
+  TTS/STT services (e.g. ElevenLabs producing no audio). Raw strings now go
+  through the same `Language` enum resolution as enum values, so regional codes
+  like `"de-DE"` are properly converted to service-expected formats like
+  `"de"`. Unrecognized strings log a warning instead of failing silently.
+  (PR [#4058](https://github.com/pipecat-ai/pipecat/pull/4058))
+
+- Fixed Deepgram STT list-type settings (`keyterm`, `keywords`, `search`,
+  `redact`, `replace`) being stringified instead of passed as lists to the SDK,
+  which caused them to be sent as literal strings (e.g. `"['pipecat']"`) in the
+  WebSocket query params.
+  (PR [#4063](https://github.com/pipecat-ai/pipecat/pull/4063))
+
+- Fixed `MinWordsUserTurnStartStrategy` including text below the word threshold
+  in the output by resetting aggregation when the minimum word count is not
+  met.
+  (PR [#4064](https://github.com/pipecat-ai/pipecat/pull/4064))
+
+- Fixed audio overlap and potential dropped TTS content when multiple assistant
+  turns occur in quick succession. `TTSService` now flushes remaining text
+  before pausing frame processing on `LLMFullResponseEndFrame`/`EndFrame`,
+  instead of pausing first.
+  (PR [#4071](https://github.com/pipecat-ai/pipecat/pull/4071))
+
+### Security
+
+- Bumped PyJWT minimum version from 2.10.1 to 2.12.0 in the `livekit` extra to
+  address CVE-2026-32597 (GHSA-752w-5fwx-jx9f), where PyJWT <= 2.11.0 accepted
+  unknown `crit` header extensions.
+  (PR [#4035](https://github.com/pipecat-ai/pipecat/pull/4035))
+
 ## [0.0.105] - 2026-03-10

 ### Added
--- a/COMMUNITY_INTEGRATIONS.md
+++ b/COMMUNITY_INTEGRATIONS.md
@@ -65,12 +65,25 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel

 #### Websocket-based Services

+**Base class:** `WebsocketSTTService`
+
+**Use for:** Services where you manage the websocket connection directly. Combines `STTService` with `WebsocketService` for automatic reconnection and keepalive support.
+
+**Examples:**
+
+- [CartesiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/stt.py)
+- [ElevenLabsRealtimeSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/stt.py)
+
+#### SDK-based Streaming Services
+
 **Base class:** `STTService`

+**Use for:** Streaming services where the provider's Python SDK manages the connection internally.
+
 **Examples:**

 - [DeepgramSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/deepgram/stt.py)
- [SpeechmaticsSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/speechmatics/stt.py)
+- [GoogleSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/stt.py)

 #### File-based Services

@@ -108,55 +121,59 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel

 #### Key requirements:

- **Frame sequence:** Output must follow this frame sequence pattern:
-  - `LLMFullResponseStartFrame` - Signals the start of an LLM response
-  - `LLMTextFrame` - Contains LLM content, typically streamed as tokens
-  - `LLMFullResponseEndFrame` - Signals the end of an LLM response
+- **`_process_context(self, context: LLMContext)`** — The main method that processes an LLM context and generates a response. Each LLM service overrides `process_frame` to extract context from `LLMContextFrame` and calls `_process_context`.

- **Context aggregation:** Implement context aggregation to collect user and assistant content:
-  - Aggregators come in pairs with a `user()` instance and `assistant()` instance
-  - Context must adhere to the `LLMContext` universal format
-  - Aggregators should handle adding messages, function calls, and images to the context
+- **`adapter_class`** — Class attribute pointing to a `BaseLLMAdapter` subclass. Defaults to `OpenAILLMAdapter`. Non-OpenAI services must implement their own adapter (see `src/pipecat/adapters/base_llm_adapter.py`) with methods:
+  - `get_llm_invocation_params(context)` — Extract provider-specific params from universal context
+  - `to_provider_tools_format(tools_schema)` — Convert standard tools to provider format
+  - `get_messages_for_logging(context)` — Format messages for logging
+  - Reference adapters: `src/pipecat/adapters/services/` (anthropic, gemini, bedrock, etc.)
+
+- **Frame sequence:** Output must follow this frame sequence pattern:
+  - `LLMFullResponseStartFrame` — Signals the start of an LLM response
+  - `LLMTextFrame` — Contains LLM content, typically streamed as tokens
+  - `LLMFullResponseEndFrame` — Signals the end of an LLM response
+
+- **Thought frames (reasoning models):** If the model supports extended thinking / chain-of-thought, emit thought frames alongside the response:
+  - `LLMThoughtStartFrame` — Signals the start of a thought
+  - `LLMThoughtTextFrame` — Contains thought content, streamed as tokens
+  - `LLMThoughtEndFrame` — Signals the end of a thought
+
+- **Context aggregation** is handled by the framework via `LLMContext` + `LLMContextAggregatorPair`. The LLM service just processes context it receives — no need to implement aggregators.

 ### TTS (Text-to-Speech) Services

-#### AudioContextWordTTSService
+#### WebsocketTTSService

-**Use for:** Websocket-based services supporting word/timestamp alignment
+**Use for:** Websocket-based streaming services (with or without word timestamps)

-**Example:**
+**Examples:**

 - [CartesiaTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/cartesia/tts.py)
+- [ElevenLabsTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)

 #### InterruptibleTTSService

-**Use for:** Websocket-based services without word/timestamp alignment, requiring disconnection on interruption
+**Use for:** Websocket-based services without word timestamps that reconnect on interruption (e.g. don't support a context ID or interruption message)

 **Example:**

 - [SarvamTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/sarvam/tts.py)

-#### WordTTSService
-
-**Use for:** HTTP-based services supporting word/timestamp alignment
-
-**Example:**
-
- [ElevenLabsHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/elevenlabs/tts.py)
-
 #### TTSService

-**Use for:** HTTP-based services without word/timestamp alignment
+**Use for:** HTTP-based services (word timestamps are supported in the base class)

-**Example:**
+**Examples:**

 - [GoogleHttpTTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/google/tts.py)
+- [OpenAITTSService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/openai/tts.py)

 #### Key requirements:

- For websocket services, use asyncio WebSocket implementation (required for v13+ support)
+- For websocket services, use asyncio WebSocket implementation
 - Handle idle service timeouts with keepalives
- TTSServices push both audio (`TTSRawAudioFrame`) and text (`TTSTextFrame`) frames
+- TTS services push both audio (`TTSAudioRawFrame`) and text (`TTSTextFrame`) frames

 ### Telephony Serializers

@@ -200,9 +217,9 @@ Vision services process images and provide analysis such as descriptions, object

 #### Key requirements:

- Must implement `run_vision` method that takes an `LLMContext` and returns an `AsyncGenerator[Frame, None]`
- The method processes the latest image in the context and yields frames with analysis results
- Typically yields `TextFrame` objects containing descriptions or answers
+- Must implement `run_vision` method that takes a `UserImageRawFrame` and returns an `AsyncGenerator[Frame, None]`
+- The method processes the image frame and yields frames with analysis results
+- Must yield the frame sequence: `VisionFullResponseStartFrame`, `VisionTextFrame`, `VisionFullResponseEndFrame`

 ## Implementation Guidelines

@@ -381,7 +398,7 @@ Note that `self.sample_rate` is a `@property` set in the TTSService base class,

 Use Pipecat's tracing decorators:

- **STT:** `@traced_stt` - decorate a function that handles `transcript`, `is_final`, `language` as args
+- **STT:** `@traced_stt` - decorate `_handle_transcription(self, transcript, is_final, language)` (the standard method name convention)
 - **LLM:** `@traced_llm` - decorate the `_process_context()` method
 - **TTS:** `@traced_tts` - decorate the `run_tts()` method

@@ -403,17 +420,15 @@ For REST-based communication, use aiohttp. Pipecat includes this as a required d
 - Wrap API calls in appropriate try/catch blocks
 - Handle rate limits and network failures gracefully
 - Provide meaningful error messages
- When errors occur, raise exceptions AND push `ErrorFrame`s to notify the pipeline:
+- When errors occur, raise exceptions AND push errors to notify the pipeline:

 ```python
-from pipecat.frames.frames import ErrorFrame
-
 try:
    # Your API call
    result = await self._make_api_call()
 except Exception as e:
-    # Push error frame to pipeline
-    await self.push_error(ErrorFrame(error=f"{self} error: {e}"))
+    # Push error upstream to notify the pipeline
+    await self.push_error(f"{self} error: {e}", exception=e)
    # Raise or handle as appropriate
    raise
 ```
--- a/README.md
+++ b/README.md
@@ -65,6 +65,10 @@ claude plugin marketplace add pipecat-ai/skills

 and install any of the available plugins.

+### 🧩 Community Integrations
+
+Build and share your own Pipecat service integrations! Browse existing [community integrations](https://docs.pipecat.ai/server/services/community-integrations) or check out our [guide](COMMUNITY_INTEGRATIONS.md) to create your own.
+
 ### 📺️ Pipecat TV Channel

 Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.youtube.com/playlist?list=PLzU2zoMTQIHjqC3v4q2XVSR3hGSzwKFwH) channel.
@@ -81,19 +85,20 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout

 ## 🧩 Available services

-| Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
-| ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [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)                                                                                                                                                                                                                                                                                                                             |
-| 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), [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), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [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         | [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), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [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/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
-| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
+| 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), [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), [Novita](https://docs.pipecat.ai/server/services/llm/novita), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nvidia), [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), [Sarvam](https://docs.pipecat.ai/server/services/llm/sarvam), [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), [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), [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), [Resemble](https://docs.pipecat.ai/server/services/tts/resemble), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Smallest](https://docs.pipecat.ai/server/services/tts/smallest), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [xAI](https://docs.pipecat.ai/server/services/tts/xai), [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         | [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), [LemonSlice](https://docs.pipecat.ai/server/services/video/lemonslice), [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/google-imagen), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| Community           | [Browse community integrations →](https://docs.pipecat.ai/server/services/community-integrations)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |

 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)

--- a/changelog/3457.changed.md
+++ b/changelog/3457.changed.md
@@ -1 +0,0 @@
- Changed tool result JSON serialization to use `ensure_ascii=False`, preserving UTF-8 characters instead of escaping them. This reduces context size and token usage for non-English languages.
--- a/changelog/3978.added.md
+++ b/changelog/3978.added.md
@@ -0,0 +1 @@
+- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`, `sarvam-105b` and `sarvam-105b-32k`
--- a/changelog/3991.changed.md
+++ b/changelog/3991.changed.md
@@ -1 +0,0 @@
- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of `OpenAIRealtimeSTTSettings`, making it runtime-updatable via `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is deprecated as of 0.0.106.
--- a/changelog/3997.changed.md
+++ b/changelog/3997.changed.md
@@ -1 +0,0 @@
- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable release).
--- a/changelog/4000.fixed.md
+++ b/changelog/4000.fixed.md
@@ -1 +0,0 @@
- Fixed an issue where the default model for `OpenAILLMService` and `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now restored to `gpt-4.1`.
--- a/changelog/4001.changed.md
+++ b/changelog/4001.changed.md
@@ -1 +0,0 @@
- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`, aligning it with the HeyGen and Tavus video services. It supports `SimliVideoService.Settings(...)` for configuration and uses `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage (`api_key`, `face_id`, etc.) remains unchanged.
--- a/changelog/4001.deprecated.md
+++ b/changelog/4001.deprecated.md
@@ -1 +0,0 @@
- `SimliVideoService.InputParams` is deprecated. Use the direct constructor parameters `max_session_length`, `max_idle_time`, and `enable_logging` instead.
--- a/changelog/4004.added.md
+++ b/changelog/4004.added.md
@@ -1 +0,0 @@
- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `STTUpdateSettingsFrame`) to target a specific service instance. When `service` is set, only the matching service applies the settings; others forward the frame unchanged. This enables updating a single service when multiple services of the same type exist in the pipeline.
--- a/changelog/4005.added.md
+++ b/changelog/4005.added.md
@@ -1 +0,0 @@
- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily runner. These convenience parameters let callers specify a SIP provider name and geographic region directly without manually constructing `DailyRoomProperties` and `DailyRoomSipParams`.
--- a/changelog/4006.fixed.md
+++ b/changelog/4006.fixed.md
@@ -1 +0,0 @@
- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut down before in-flight frames (e.g. LLM function call responses) finished processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline as `ControlFrame`s, ensuring all pending work is flushed before shutdown begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate (`SystemFrame`).
--- a/changelog/4007.fixed.2.md
+++ b/changelog/4007.fixed.2.md
@@ -1 +0,0 @@
- Fixed `TTSService` potentially canceling in-flight audio during shutdown. The stop sequence now waits for all queued audio contexts to finish processing before canceling the stop frame task.
--- a/changelog/4007.fixed.md
+++ b/changelog/4007.fixed.md
@@ -1 +0,0 @@
- Fixed `ParallelPipeline` dropping or misordering frames during lifecycle synchronization. Buffered frames are now flushed in the correct order relative to synchronization frames (`StartFrame` goes first, `EndFrame`/`CancelFrame` go after), and frames added to the buffer during flush are also drained.
--- a/changelog/4009.added.md
+++ b/changelog/4009.added.md
@@ -1 +0,0 @@
- Added `PerplexityLLMAdapter` that automatically transforms conversation messages to satisfy Perplexity's stricter API constraints (strict role alternation, no non-initial system messages, last message must be user/tool). Previously, certain conversation histories could cause Perplexity API errors that didn't occur with OpenAI (`PerplexityLLMService` subclasses `OpenAILLMService` since Perplexity uses an OpenAI-compatible API).
--- a/changelog/4012.deprecated.md
+++ b/changelog/4012.deprecated.md
@@ -1 +0,0 @@
- Deprecated `LocalSmartTurnAnalyzerV2` and `LocalCoreMLSmartTurnAnalyzer`. Use `LocalSmartTurnAnalyzerV3` instead. Instantiating these analyzers will now emit a `DeprecationWarning`.
--- a/changelog/4013.added.md
+++ b/changelog/4013.added.md
@@ -0,0 +1 @@
+- Added `on_turn_context_created(context_id)` hook to `TTSService`. Override this to perform provider-specific setup (e.g. eagerly opening a server-side context) before text starts flowing. Called each time a new turn context ID is created.
--- a/changelog/4013.changed.md
+++ b/changelog/4013.changed.md
@@ -0,0 +1 @@
+- Added context prewarming path for `InworldTTSService` to improve first audio latency
--- a/changelog/4022.changed.md
+++ b/changelog/4022.changed.md
@@ -0,0 +1 @@
+- Added `KrispVivaVadAnalyzer` for Voice Activity Detection using the Krisp VIVA SDK (requires `krisp_audio`).
--- a/changelog/4023.changed.md
+++ b/changelog/4023.changed.md
@@ -1 +0,0 @@
- Update `pipecat-ai-small-webrtc-prebuilt` to `2.4.0`.
--- a/changelog/4024.fixed.md
+++ b/changelog/4024.fixed.md
@@ -1 +0,0 @@
- Fixed `Language` enum values (e.g. `Language.ES`) not being converted to service-specific codes when passed via `settings=Service.Settings(language=Language.ES)` at init time. This caused API errors (e.g. 400 from Rime) because the raw enum was sent instead of the expected language code (e.g. `"spa"`). Runtime updates via `UpdateSettingsFrame` were unaffected. The fix centralizes conversion in the base `TTSService` and `STTService` classes so all services handle this consistently.
--- a/changelog/4026.fixed.md
+++ b/changelog/4026.fixed.md
@@ -1 +0,0 @@
- Fixed `DeepgramSTTService` ignoring the `base_url` scheme when using `ws://` or `http://`. Previously these were silently overwritten with `wss://` / `https://`, breaking air-gapped or private deployments that don't use TLS. All scheme choices (`wss://`, `https://`, `ws://`, `http://`, or bare hostname) are now respected.
--- a/changelog/4028.changed.md
+++ b/changelog/4028.changed.md
@@ -0,0 +1 @@
+- Modeified `InworldTTSService` to close context at end of turn instead of relying on idle timeout
--- a/changelog/4031.added.md
+++ b/changelog/4031.added.md
@@ -0,0 +1 @@
+- Added `XAIHttpTTSService` for text-to-speech using xAI's HTTP TTS API.
--- a/changelog/4035.security.md
+++ b/changelog/4035.security.md
@@ -1 +0,0 @@
- Bumped PyJWT minimum version from 2.10.1 to 2.12.0 in the `livekit` extra to address CVE-2026-32597 (GHSA-752w-5fwx-jx9f), where PyJWT <= 2.11.0 accepted unknown `crit` header extensions.
--- a/changelog/4037.fixed.md
+++ b/changelog/4037.fixed.md
@@ -1 +0,0 @@
- Fixed `LLMSwitcher.register_function()` and `register_direct_function()` not accepting or forwarding the `timeout_secs` parameter.
--- a/changelog/4046.fixed.md
+++ b/changelog/4046.fixed.md
@@ -1 +0,0 @@
-Fixed `SonioxSTTService` and `OpenAIRealtimeSTTService` crash when language parameters contain plain strings instead of `Language` enum values.
--- a/changelog/4047.added.md
+++ b/changelog/4047.added.md
@@ -1 +0,0 @@
- Added DTMF input event support to the Daily transport. Incoming DTMF tones are now received via Daily's `on_dtmf_event` callback and pushed into the pipeline as `InputDTMFFrame`, enabling bots to react to keypad presses from phone callers.
--- a/changelog/4047.changed.md
+++ b/changelog/4047.changed.md
@@ -1 +0,0 @@
- Updated `daily-python` dependency to 0.25.0.
--- a/changelog/4048.changed.md
+++ b/changelog/4048.changed.md
@@ -1 +0,0 @@
- Added `enable_dialout` parameter to `configure()` in `pipecat.runner.daily` to support dial-out rooms. Also narrowed misleading `Optional` type hints and deduplicated token expiry calculation.
--- a/changelog/4057.fixed.md
+++ b/changelog/4057.fixed.md
@@ -1 +0,0 @@
- Fixed premature user turn stops caused by late transcriptions arriving between turns. A stale transcript from the previous turn could persist into the next turn and trigger a stop before the current turn's real transcript arrived. Stop strategies are now reset at both turn start and turn stop to prevent state from leaking across turn boundaries.
--- a/changelog/4058.fixed.md
+++ b/changelog/4058.fixed.md
@@ -1 +0,0 @@
- Fixed raw language strings like `"de-DE"` silently failing when passed to TTS/STT services (e.g. ElevenLabs producing no audio). Raw strings now go through the same `Language` enum resolution as enum values, so regional codes like `"de-DE"` are properly converted to service-expected formats like `"de"`. Unrecognized strings log a warning instead of failing silently.
--- a/changelog/4063.fixed.md
+++ b/changelog/4063.fixed.md
@@ -1 +0,0 @@
- Fixed Deepgram STT list-type settings (`keyterm`, `keywords`, `search`, `redact`, `replace`) being stringified instead of passed as lists to the SDK, which caused them to be sent as literal strings (e.g. `"['pipecat']"`) in the WebSocket query params.
--- a/changelog/4078.changed.md
+++ b/changelog/4078.changed.md
@@ -0,0 +1 @@
+- Added Gemini 3 support to the Gemini Live service.
--- a/changelog/4084.changed.md
+++ b/changelog/4084.changed.md
@@ -0,0 +1 @@
+- `TTSService`: the default `stop_frame_timeout_s` (idle time before an automatic `TTSStoppedFrame` is pushed when `push_stop_frames=True`) has changed from `2.0` to `3.0` seconds.
--- a/changelog/4089.added.md
+++ b/changelog/4089.added.md
@@ -0,0 +1 @@
+- Added support for "developer" role messages in conversation context across all LLM adapters. For non-OpenAI services (Anthropic, Google, AWS Bedrock), "developer" messages are converted to "user" messages (use `system_instruction` to set the system instruction). For OpenAI services, "developer" messages pass through in conversation history. For the Responses API, they are kept as "developer" role (matching the existing "system" → "developer" conversion).
--- a/changelog/4089.changed.md
+++ b/changelog/4089.changed.md
@@ -0,0 +1 @@
+- ⚠️ `GeminiLLMAdapter` now only treats `messages[0]` as the initial system message, matching all other adapters. Previously it searched for the first "system" message anywhere in the conversation history. A "system" message appearing later in the list will now be converted to "user" instead of being extracted as the system instruction.
--- a/changelog/4089.fixed.2.md
+++ b/changelog/4089.fixed.2.md
@@ -0,0 +1 @@
+- Fixed Gemini Live (`GoogleGeminiLiveLLMService`) not honoring `settings.system_instruction`. The system instruction was being read from a deprecated constructor parameter instead of the settings object, causing it to be silently ignored.
--- a/changelog/4089.fixed.md
+++ b/changelog/4089.fixed.md
@@ -0,0 +1 @@
+- Fixed `AWSBedrockLLMAdapter` sending an empty message list to the API when the only message in context was a system message. The lone system message is now converted to "user" role instead of being extracted, matching the existing Anthropic adapter behavior.
--- a/changelog/4092.added.md
+++ b/changelog/4092.added.md
@@ -0,0 +1 @@
+- Added `SmallestTTSService`, a WebSocket-based TTS service integration with Smallest AI's Waves API. Supports the Lightning v2 and v3.1 models with configurable voice, language, speed, consistency, similarity, and enhancement settings.
--- a/changelog/4113.changed.md
+++ b/changelog/4113.changed.md
@@ -0,0 +1 @@
+- Fixed `InworldTtsService` to fallback to full text when TTS timestamps are not received
--- a/changelog/4115.added.md
+++ b/changelog/4115.added.md
@@ -0,0 +1 @@
+- Added warnings in turn stop strategies when `VADParams.stop_secs` differs from the recommended default (0.2s) or when `stop_secs >= STT p99 latency`, which collapses the STT wait timeout to 0s and may cause delayed turn detection. The warnings guide developers to re-run the [stt-benchmark](https://github.com/pipecat-ai/stt-benchmark) with their VAD settings.
--- a/changelog/4117.added.md
+++ b/changelog/4117.added.md
@@ -0,0 +1 @@
+- Added `domain` parameter to `AssemblyAISTTSettings` for specialized recognition modes such as Medical Mode (`domain="medical-v1"`).
--- a/changelog/4119.added.md
+++ b/changelog/4119.added.md
@@ -0,0 +1 @@
+- Added `NovitaLLMService` for using Novita AI's LLM models via their OpenAI-compatible API.
--- a/changelog/4120.added.md
+++ b/changelog/4120.added.md
@@ -0,0 +1 @@
+- Added `cleanup()` method to `VADAnalyzer` and `VADController` so VAD analyzer resources are properly released when no longer needed. Custom `VADAnalyzer` subclasses can override `cleanup()` to free any held resources.
--- a/changelog/4125.fixed.md
+++ b/changelog/4125.fixed.md
@@ -0,0 +1 @@
+- Fixed Gemini Live pipeline hanging indefinitely when an `EndFrame` was deferred while waiting for the bot to finish responding and `turn_complete` never arrived. As a possible root-cause fix, `turn_complete` messages are now handled even if they lack `usage_metadata`. As a fallback, the deferred `EndFrame` now has a 30-second safety timeout.
--- a/changelog/4126.fixed.md
+++ b/changelog/4126.fixed.md
@@ -0,0 +1 @@
+- Fixed ElevenLabs WebSocket disconnections (1008 "Maximum simultaneous contexts exceeded") caused by rapid user interruptions. When interruptions arrived before any TTS text was generated, phantom contexts were created on the ElevenLabs server that were never closed, eventually exceeding the 5-context limit.
--- a/changelog/4127.fixed.md
+++ b/changelog/4127.fixed.md
@@ -0,0 +1 @@
+- Fixed the final sentence being dropped from the conversation context when using RTVI text input with non-word-timestamp TTS services. The `LLMFullResponseEndFrame` was racing ahead of the last `TTSTextFrame`, causing the `LLMAssistantAggregator` to finalize the context before the final sentence arrived.
--- a/changelog/4128.added.md
+++ b/changelog/4128.added.md
@@ -0,0 +1 @@
+- Added `on_end_of_turn` event handler to `AssemblyAISTTService`. This fires after the final transcript is pushed, providing a reliable hook for end-of-turn logic that doesn't race with `TranscriptionFrame`. Works in both Pipecat and AssemblyAI turn detection modes.
--- a/changelog/4130.changed.md
+++ b/changelog/4130.changed.md
@@ -0,0 +1 @@
+- ⚠️ Realtime services (Gemini Live, OpenAI Realtime, Grok Realtime, Nova Sonic) now prefer `system_instruction` from service settings over an initial system message in the LLM context, matching the behavior of non-realtime services. Previously, context-provided system instructions took precedence. A warning is now logged when both are set.
--- a/changelog/4135.fixed.md
+++ b/changelog/4135.fixed.md
@@ -0,0 +1 @@
+- Fixed audio crackling and popping in recordings when both user and bot are speaking. `AudioBufferProcessor` no longer injects silence into a track's buffer while that track is actively producing audio, preventing mid-utterance interruptions in the recorded output.
--- a/changelog/4136.changed.2.md
+++ b/changelog/4136.changed.2.md
@@ -0,0 +1 @@
+- Bumped `nvidia-riva-client` minimum version to `>=2.25.1`.
--- a/changelog/4136.changed.md
+++ b/changelog/4136.changed.md
@@ -0,0 +1 @@
+- Upgraded `protobuf` from 5.x to 6.x (`>=6.31.1,<7`).
--- a/changelog/4137.changed.md
+++ b/changelog/4137.changed.md
@@ -0,0 +1 @@
+- Unrecognized language strings (e.g. Deepgram's `"multi"`) no longer produce a warning at startup. The log message has been downgraded to debug level since these are valid service-specific values that are passed through correctly.
--- a/changelog/4142.changed.md
+++ b/changelog/4142.changed.md
@@ -0,0 +1 @@
+- `GrokLLMService` and `GrokRealtimeLLMService` now live in the `pipecat.services.xai` module alongside `XAIHttpTTSService`, since all three use the same xAI API. Update imports from `pipecat.services.grok.*` to `pipecat.services.xai.*` (e.g. `from pipecat.services.xai.llm import GrokLLMService`).
--- a/changelog/4142.deprecated.md
+++ b/changelog/4142.deprecated.md
@@ -0,0 +1 @@
+- `pipecat.services.grok.llm`, `pipecat.services.grok.realtime.llm`, and `pipecat.services.grok.realtime.events` are deprecated. The old import paths still work but emit a `DeprecationWarning`; use `pipecat.services.xai.llm`, `pipecat.services.xai.realtime.llm`, and `pipecat.services.xai.realtime.events` instead.
--- a/changelog/4143.added.md
+++ b/changelog/4143.added.md
@@ -0,0 +1 @@
+- Added `DeepgramFluxSageMakerSTTService` for running Deepgram Flux speech-to-text on AWS SageMaker endpoints.  Use with `ExternalUserTurnStrategies` to take advantage of Flux's turn detection.
--- a/changelog/4145.fixed.2.md
+++ b/changelog/4145.fixed.2.md
@@ -0,0 +1 @@
+- Fixed websocket TTS word timestamps so interrupted contexts cannot leak stale words or backward PTS values into later turns.
--- a/changelog/4145.fixed.md
+++ b/changelog/4145.fixed.md
@@ -0,0 +1 @@
+- Fixed a race condition in `InterruptibleTTSService` where, if `run_tts` had been invoked but `BotStartedSpeakingFrame` had not yet been received, a user interruption could allow stale audio to leak through.
--- a/changelog/4145.removed.md
+++ b/changelog/4145.removed.md
@@ -0,0 +1 @@
+- ⚠️ `TTSService.add_word_timestamps()` no longer supports the `"Reset"` and `"TTSStoppedFrame"` sentinel strings. If you have a custom TTS service that called `await self.add_word_timestamps([("Reset", 0)])` or `await self.add_word_timestamps([("TTSStoppedFrame", 0), ("Reset", 0)], ctx_id)`, replace them with `await self.append_to_audio_context(ctx_id, TTSStoppedFrame(context_id=ctx_id))` and let `_handle_audio_context` manage the word-timestamp reset automatically.
--- a/changelog/4146.fixed.md
+++ b/changelog/4146.fixed.md
@@ -0,0 +1 @@
+- Fixed Gemini Live local VAD mode (`GeminiVADParams(disabled=True)` with external VAD) not working. The bot now correctly detects user speech and signals turn boundaries to the Gemini API.
--- a/changelog/4147.fixed.md
+++ b/changelog/4147.fixed.md
@@ -0,0 +1 @@
+- Fixed Gemini Live message handling to process all `server_content` fields independently. Gemini 3.x can bundle multiple fields (e.g. `model_turn` and `output_transcription`) on the same message, but the previous `elif` chain only processed the first match, silently dropping the rest.
--- a/changelog/4149.fixed.md
+++ b/changelog/4149.fixed.md
@@ -0,0 +1 @@
+- Fixed `ServiceSwitcher` with `ServiceSwitcherStrategyFailover` incorrectly triggering failover when `ErrorFrame`s from other pipeline stages (e.g. TTS) propagated upstream through the switcher. Previously, any non-fatal error passing through would be misattributed to the active service and trigger an unwanted service switch. Now only errors originating from the switcher's own managed services trigger failover.
--- a/changelog/4151.fixed.md
+++ b/changelog/4151.fixed.md
@@ -0,0 +1 @@
+- Fixed `LiveKitOutputTransport` not clearing the `rtc.AudioSource` internal buffer on interruption, causing the bot to continue speaking for several seconds after being interrupted.
--- a/changelog/4152.fixed.md
+++ b/changelog/4152.fixed.md
@@ -0,0 +1 @@
+- Fixed a crash in OpenAI LLM processing when the provider returns `chunk.choices[0].delta.audio = None`, which caused `'NoneType' object has no attribute 'get'` errors during audio transcript handling.
--- a/changelog/4153.fixed.md
+++ b/changelog/4153.fixed.md
@@ -0,0 +1 @@
+- Fixed error floods in `DeepgramSTTService` when the WebSocket connection drops. With Deepgram SDK 6.x, `send_media()` raises exceptions on a dead connection instead of silently failing, causing every queued audio frame to log an error. Now `send_media()` failures are caught gracefully — a single warning is logged and audio frames are skipped until the existing reconnection logic restores the connection.
--- a/changelog/4154.removed.md
+++ b/changelog/4154.removed.md
@@ -0,0 +1 @@
+- Removed `SambaNovaSTTService`. SambaNova no longer offers speech-to-text audio models. Use another STT provider instead.
--- a/changelog/4156.added.md
+++ b/changelog/4156.added.md
@@ -0,0 +1 @@
+- Added `Mem0MemoryService.get_memories()` convenience method for retrieving all stored memories outside the pipeline (e.g. to build a personalized greeting at connection time). This avoids the need to manually handle client type branching, filter construction, and async wrapping.
--- a/changelog/4156.changed.md
+++ b/changelog/4156.changed.md
@@ -0,0 +1 @@
+- ⚠️ Bumped `mem0ai` dependency from `~=0.1.94` to `>=1.0.8,<2`. Users of the `mem0` extra will need to update their mem0ai package.
--- a/changelog/4156.fixed.2.md
+++ b/changelog/4156.fixed.2.md
@@ -0,0 +1 @@
+- Fixed `Mem0MemoryService` failing to store messages when the context contained system or developer role messages. The Mem0 API only accepts user and assistant roles, so other roles are now filtered out before storing.
--- a/changelog/4156.fixed.md
+++ b/changelog/4156.fixed.md
@@ -0,0 +1 @@
+- `Mem0MemoryService` no longer blocks the event loop during memory storage and retrieval. All Mem0 API calls now run in a background thread, and message storage is fire-and-forget so it doesn't delay downstream processing.
--- a/changelog/4161.fixed.md
+++ b/changelog/4161.fixed.md
@@ -0,0 +1 @@
+- Added missing `on_dtmf_event` callback to `LemonSliceTransportClient.setup()` `DailyCallbacks` construction, fixing a `ValidationError` at pipeline setup time.
--- a/changelog/4167.fixed.2.md
+++ b/changelog/4167.fixed.2.md
@@ -0,0 +1 @@
+- Fixed an issue in `InworldTTSService` where, in cases of fast interruption, we would continue receiving audio from the previous context.
--- a/changelog/4167.fixed.md
+++ b/changelog/4167.fixed.md
@@ -0,0 +1 @@
+- Fixed a word timestamp interleaving issue in `InworldTTSService` when processing multiple sentences.
--- a/changelog/4172.fixed.md
+++ b/changelog/4172.fixed.md
@@ -0,0 +1 @@
+- Fixed duplicate `TTSStoppedFrame` being pushed in TTS services using `push_stop_frames=True`. When the stop-frame timeout fired, a second `TTSStoppedFrame` could be pushed after the normal one at context completion.
--- a/changelog/4172.performance.md
+++ b/changelog/4172.performance.md
@@ -0,0 +1 @@
+- `RimeTTSService` now handles Rime's `done` WebSocket message to complete audio contexts immediately, eliminating the 3-second idle timeout that previously added latency at the end of each utterance.
--- a/changelog/4174.fixed.md
+++ b/changelog/4174.fixed.md
@@ -0,0 +1 @@
+- ⚠️ Fixed `DeepgramSTTService` compatibility with deepgram-sdk 6.1.0. The SDK now requires explicit message objects for `send_keep_alive()`, `send_close_stream()`, and `send_finalize()`. The minimum deepgram-sdk version is now 6.1.0.
--- a/changelog/4176.fixed.md
+++ b/changelog/4176.fixed.md
@@ -0,0 +1 @@
+- Fixed RTVI events not being delivered to clients when using WebSocket transports. `ProtobufFrameSerializer` now sets `ignore_rtvi_messages=False` by default.
--- a/env.example
+++ b/env.example
@@ -80,9 +80,6 @@ GOOGLE_TEST_CREDENTIALS=...
 # Gradium
 GRAPDIUM_API_KEY=...

-# Grok
-GROK_API_KEY=...
-
 # Groq
 GROQ_API_KEY=...

@@ -127,6 +124,9 @@ MISTRAL_API_KEY=...
 # Neuphonic
 NEUPHONIC_API_KEY=...

+# Novita
+NOVITA_API_KEY=...
+
 # NVIDIA
 NVIDIA_API_KEY=...

@@ -176,6 +176,9 @@ SENTRY_DSN=...
 SIMLI_API_KEY=...
 SIMLI_FACE_ID=...

+# Smallest
+SMALLEST_API_KEY=...
+
 # Smart turn
 LOCAL_SMART_TURN_MODEL_PATH=...
 FAL_SMART_TURN_API_KEY=...
@@ -209,3 +212,6 @@ WHATSAPP_TOKEN=...
 WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
 WHATSAPP_PHONE_NUMBER_ID=...
 WHATSAPP_APP_SECRET=...
+
+# xAI / Grok
+XAI_API_KEY=...
--- a/examples/foundational/02-llm-say-one-thing.py
+++ b/examples/foundational/02-llm-say-one-thing.py
@@ -60,7 +60,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        context = LLMContext()
-        context.add_message({"role": "user", "content": "Say hello to the world."})
+        context.add_message({"role": "developer", "content": "Say hello to the world."})
        await task.queue_frames([LLMContextFrame(context), EndFrame()])

    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
--- a/examples/foundational/04-transports-small-webrtc.py
+++ b/examples/foundational/04-transports-small-webrtc.py
@@ -109,7 +109,9 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/04a-transports-daily.py
+++ b/examples/foundational/04a-transports-daily.py
@@ -92,7 +92,7 @@ async def main():
            await transport.capture_participant_transcription(participant["id"])
            # Kick off the conversation.
            context.add_message(
-                {"role": "user", "content": "Please introduce yourself to the user."}
+                {"role": "developer", "content": "Please introduce yourself to the user."}
            )
            await task.queue_frames([LLMRunFrame()])

--- a/examples/foundational/05-sync-speech-and-image.py
+++ b/examples/foundational/05-sync-speech-and-image.py
@@ -16,11 +16,12 @@ from pipecat.frames.frames import (
    Frame,
    LLMContextFrame,
    LLMFullResponseStartFrame,
+    OutputImageRawFrame,
    TextFrame,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
+from pipecat.pipeline.sync_parallel_pipeline import FrameOrder, SyncParallelPipeline
 from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.sentence import SentenceAggregator
@@ -30,6 +31,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaHttpTTSService
 from pipecat.services.fal.image import FalImageGenService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.tts_service import TextAggregationMode
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams

@@ -44,6 +46,18 @@ class MonthFrame(DataFrame):
        return f"{self.name}(month: {self.month})"


+class MarkImageForPlaybackSync(FrameProcessor):
+    """Marks output image frames to be synchronized with audio playback."""
+
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, OutputImageRawFrame):
+            frame.sync_with_audio = True
+
+        await self.push_frame(frame, direction)
+
+
 class MonthPrepender(FrameProcessor):
    def __init__(self):
        super().__init__()
@@ -101,6 +115,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            settings=CartesiaHttpTTSService.Settings(
                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
            ),
+            # No need to aggregate by sentences (the default), as we already know we're getting full sentences
+            # (Otherwise the service will unnecessarily wait for follow-up input to confirm the sentence is complete,
+            #  which, sadly, actually breaks the synchronization mechanism)
+            text_aggregation_mode=TextAggregationMode.TOKEN,
        )

        imagegen = FalImageGenService(
@@ -119,17 +137,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
        # that, each pipeline runs concurrently and `SyncParallelPipeline` will
        # wait for the input frame to be processed.
        #
+        # We use `FrameOrder.PIPELINE` so that each synchronized batch of output
+        # frames is pushed in the order the pipelines are listed: image first,
+        # then audio. This ensures the transport receives the image before the
+        # audio frames it should accompany.
+        #
        # Note that `SyncParallelPipeline` requires the last processor in each
        # of the pipelines to be synchronous. In this case, we use
-        # `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
+        # `FalImageGenService` and `CartesiaHttpTTSService` which make HTTP
        # requests and wait for the response.
        pipeline = Pipeline(
            [
                llm,  # LLM
                sentence_aggregator,  # Aggregates LLM output into full sentences
                SyncParallelPipeline(  # Run pipelines in parallel aggregating the result
+                    [
+                        imagegen,  # Generate image
+                        MarkImageForPlaybackSync(),  # Mark image as needing sync w/audio during playback
+                    ],
                    [month_prepender, tts],  # Create "Month: sentence" and output audio
-                    [imagegen],  # Generate image
+                    frame_order=FrameOrder.PIPELINE,
                ),
                transport.output(),  # Transport output
            ]
--- a/examples/foundational/05a-local-sync-speech-and-image.py
+++ b/examples/foundational/05a-local-sync-speech-and-image.py
@@ -1,202 +0,0 @@
-#
-# Copyright (c) 2024-2026, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import os
-import sys
-import tkinter as tk
-
-import aiohttp
-from dotenv import load_dotenv
-from loguru import logger
-
-from pipecat.frames.frames import (
-    Frame,
-    LLMContextFrame,
-    OutputAudioRawFrame,
-    TextFrame,
-    TTSAudioRawFrame,
-    URLImageRawFrame,
-)
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
-from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_context import LLMContext
-from pipecat.processors.aggregators.sentence import SentenceAggregator
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.services.cartesia.tts import CartesiaHttpTTSService
-from pipecat.services.fal.image import FalImageGenService
-from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
-
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    async with aiohttp.ClientSession() as session:
-        tk_root = tk.Tk()
-        tk_root.title("Calendar")
-
-        runner = PipelineRunner()
-
-        async def get_month_data(month):
-            messages = [
-                {
-                    "role": "user",
-                    "content": f"Describe a nature photograph suitable for use in a calendar, for the month of {month}. Include only the image description with no preamble. Limit the description to one sentence, please.",
-                }
-            ]
-
-            class ImageDescription(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.text = ""
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, TextFrame):
-                        self.text = frame.text
-                    await self.push_frame(frame, direction)
-
-            class AudioGrabber(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.audio = bytearray()
-                    self.frame = None
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, TTSAudioRawFrame):
-                        self.audio.extend(frame.audio)
-                        self.frame = OutputAudioRawFrame(
-                            bytes(self.audio), frame.sample_rate, frame.num_channels
-                        )
-                    await self.push_frame(frame, direction)
-
-            class ImageGrabber(FrameProcessor):
-                def __init__(self):
-                    super().__init__()
-                    self.frame = None
-
-                async def process_frame(self, frame: Frame, direction: FrameDirection):
-                    await super().process_frame(frame, direction)
-
-                    if isinstance(frame, URLImageRawFrame):
-                        self.frame = frame
-                    await self.push_frame(frame, direction)
-
-            llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
-
-            tts = CartesiaHttpTTSService(
-                api_key=os.getenv("CARTESIA_API_KEY"),
-                settings=CartesiaHttpTTSService.Settings(
-                    voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-                ),
-            )
-
-            imagegen = FalImageGenService(
-                settings=FalImageGenService.Settings(
-                    image_size="square_hd",
-                ),
-                aiohttp_session=session,
-                key=os.getenv("FAL_KEY"),
-            )
-
-            sentence_aggregator = SentenceAggregator()
-
-            description = ImageDescription()
-
-            audio_grabber = AudioGrabber()
-
-            image_grabber = ImageGrabber()
-
-            # With `SyncParallelPipeline` we synchronize audio and images by
-            # pushing them basically in order (e.g. I1 A1 A1 A1 I2 A2 A2 A2 A2
-            # I3 A3). To do that, each pipeline runs concurrently and
-            # `SyncParallelPipeline` will wait for the input frame to be
-            # processed.
-            #
-            # Note that `SyncParallelPipeline` requires the last processor in
-            # each of the pipelines to be synchronous. In this case, we use
-            # `CartesiaHttpTTSService` and `FalImageGenService` which make HTTP
-            # requests and wait for the response.
-            pipeline = Pipeline(
-                [
-                    llm,  # LLM
-                    sentence_aggregator,  # Aggregates LLM output into full sentences
-                    description,  # Store sentence
-                    SyncParallelPipeline(
-                        [tts, audio_grabber],  # Generate and store audio for the given sentence
-                        [imagegen, image_grabber],  # Generate and storeimage for the given sentence
-                    ),
-                ]
-            )
-
-            task = PipelineTask(pipeline)
-            await task.queue_frame(LLMContextFrame(LLMContext(messages)))
-            await task.stop_when_done()
-
-            await runner.run(task)
-
-            return {
-                "month": month,
-                "text": description.text,
-                "image": image_grabber.frame,
-                "audio": audio_grabber.frame,
-            }
-
-        transport = TkLocalTransport(
-            tk_root,
-            TkTransportParams(
-                audio_out_enabled=True,
-                video_out_enabled=True,
-                video_out_width=1024,
-                video_out_height=1024,
-            ),
-        )
-
-        pipeline = Pipeline([transport.output()])
-
-        task = PipelineTask(pipeline)
-
-        # We only specify a few months as we create tasks all at once and we
-        # might get rate limited otherwise.
-        months: list[str] = [
-            "January",
-            "February",
-        ]
-
-        # We create one task per month. This will be executed concurrently.
-        month_tasks = [asyncio.create_task(get_month_data(month)) for month in months]
-
-        # Now we wait for each month task in the order they're completed. The
-        # benefit is we'll have as little delay as possible before the first
-        # month, and likely no delay between months, but the months won't
-        # display in order.
-        async def show_images(month_tasks):
-            for month_data_task in asyncio.as_completed(month_tasks):
-                data = await month_data_task
-                await task.queue_frames([data["image"], data["audio"]])
-
-            await runner.stop_when_done()
-
-        async def run_tk():
-            while not task.has_finished():
-                tk_root.update()
-                tk_root.update_idletasks()
-                await asyncio.sleep(0.1)
-
-        await asyncio.gather(runner.run(task), show_images(month_tasks), run_tk())
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/examples/foundational/06-listen-and-respond.py
+++ b/examples/foundational/06-listen-and-respond.py
@@ -129,7 +129,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07-interruptible-cartesia-http.py
+++ b/examples/foundational/07-interruptible-cartesia-http.py
@@ -103,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            logger.info(f"Client connected")
            # Kick off the conversation.
            context.add_message(
-                {"role": "user", "content": "Please introduce yourself to the user."}
+                {"role": "developer", "content": "Please introduce yourself to the user."}
            )
            await task.queue_frames([LLMRunFrame()])

--- a/examples/foundational/07-interruptible-openai-responses.py
+++ b/examples/foundational/07-interruptible-openai-responses.py
@@ -4,14 +4,12 @@
 # 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
@@ -24,25 +22,14 @@ from pipecat.processors.aggregators.llm_response_universal import (
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
-from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService, GeminiModalities
+from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.openai.responses.llm import OpenAIResponsesLLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

 load_dotenv(override=True)

-
-SYSTEM_INSTRUCTION = f"""
-"You are Gemini Chatbot, a friendly, helpful robot.
-
-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. Keep your responses brief. One or two sentences at most.
-"""
-
-
 # We use lambdas to defer transport parameter creation until the transport
 # type is selected at runtime.
 transport_params = {
@@ -64,57 +51,37 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    logger.info(f"Starting bot")

-    # KNOWN ISSUE: If using GeminiLiveVertexLLMService, you cannot specify a
-    # modality other than AUDIO (at least not if using the service's default
-    # model, which is a native audio model:
-    # https://cloud.google.com/vertex-ai/generative-ai/docs/live-api/tools#native-audio).
-    llm = GeminiLiveLLMService(
-        api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GeminiLiveLLMService.Settings(
-            system_instruction=SYSTEM_INSTRUCTION,
-            modalities=GeminiModalities.TEXT,
-        ),
-        tools=[{"google_search": {}}, {"code_execution": {}}],
-    )
-
-    # Optionally, you can set the response modalities via a function
-    # llm.set_model_modalities(
-    #     GeminiMultimodalModalities.TEXT
-    # )
+    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))

    tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        settings=CartesiaTTSService.Settings(
+            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        ),
    )

-    messages = [
-        {
-            "role": "user",
-            "content": 'Start by saying "Hello, I\'m Gemini".',
-        },
-    ]
+    llm = OpenAIResponsesLLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        settings=OpenAIResponsesLLMService.Settings(
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )

-    # Set up conversation context and management
-    # The context_aggregator will automatically collect conversation context
-    context = LLMContext(messages)
+    context = LLMContext()
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
-        user_params=LLMUserAggregatorParams(
-            # Set stop_secs to something roughly similar to the internal setting
-            # of the Multimodal Live api, just to align events. This doesn't
-            # really matter because we can only use the Multimodal Live API's
-            # phrase endpointing, for now.
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5))
-        ),
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    pipeline = Pipeline(
        [
-            transport.input(),
-            user_aggregator,
-            llm,
-            tts,
-            transport.output(),
-            assistant_aggregator,
+            transport.input(),  # Transport user input
+            stt,
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
        ]
    )

@@ -131,6 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07-interruptible.py
+++ b/examples/foundational/07-interruptible.py
@@ -98,7 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07a-interruptible-speechmatics-vad.py
+++ b/examples/foundational/07a-interruptible-speechmatics-vad.py
@@ -148,7 +148,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
        async def on_client_connected(transport, client):
            logger.info(f"Client connected")
            # Kick off the conversation.
-            context.add_message({"role": "user", "content": "Say a short hello to the user."})
+            context.add_message({"role": "developer", "content": "Say a short hello to the user."})
            await task.queue_frames([LLMRunFrame()])

        @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07a-interruptible-speechmatics.py
+++ b/examples/foundational/07a-interruptible-speechmatics.py
@@ -128,7 +128,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
        async def on_client_connected(transport, client):
            logger.info(f"Client connected")
            # Kick off the conversation.
-            context.add_message({"role": "user", "content": "Say a short hello to the user."})
+            context.add_message({"role": "developer", "content": "Say a short hello to the user."})
            await task.queue_frames([LLMRunFrame()])

        @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07c-interruptible-deepgram-flux-sagemaker.py
+++ b/examples/foundational/07c-interruptible-deepgram-flux-sagemaker.py
@@ -0,0 +1,151 @@
+#
+# 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.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.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
+from pipecat.services.deepgram.flux.sagemaker.stt import DeepgramFluxSageMakerSTTService
+from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
+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 use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    # Initialize Deepgram Flux SageMaker STT Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram Flux model
+    stt = DeepgramFluxSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_STT_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+        settings=DeepgramFluxSageMakerSTTService.Settings(
+            min_confidence=0.3,
+        ),
+    )
+
+    # Initialize Deepgram SageMaker TTS Service
+    # This requires:
+    # - AWS credentials configured (via environment variables or AWS CLI)
+    # - A deployed SageMaker endpoint with Deepgram TTS model
+    tts = DeepgramSageMakerTTSService(
+        endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION"),
+        settings=DeepgramSageMakerTTSService.Settings(
+            voice="aura-2-andromeda-en",
+        ),
+    )
+
+    llm = AWSBedrockLLMService(
+        aws_region=os.getenv("AWS_REGION"),
+        settings=AWSBedrockLLMSettings(
+            model="us.amazon.nova-pro-v1:0",
+            temperature=0.8,
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    context = LLMContext()
+    # Use ExternalUserTurnStrategies since Flux handles turn detection natively
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(
+            user_turn_strategies=ExternalUserTurnStrategies(),
+            vad_analyzer=SileroVADAnalyzer(),
+        ),
+    )
+
+    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.
+        context.add_message({"role": "user", "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()
+
+    @stt.event_handler("on_update")
+    async def on_deepgram_flux_update(stt, transcript):
+        logger.debug(f"On deepgram flux update: {transcript}")
+
+    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()
--- a/examples/foundational/07c-interruptible-deepgram-flux.py
+++ b/examples/foundational/07c-interruptible-deepgram-flux.py
@@ -109,7 +109,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07c-interruptible-deepgram-http.py
+++ b/examples/foundational/07c-interruptible-deepgram-http.py
@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            logger.info(f"Client connected")
            # Kick off the conversation.
            context.add_message(
-                {"role": "user", "content": "Please introduce yourself to the user."}
+                {"role": "developer", "content": "Please introduce yourself to the user."}
            )
            await task.queue_frames([LLMRunFrame()])

--- a/examples/foundational/07c-interruptible-deepgram-sagemaker.py
+++ b/examples/foundational/07c-interruptible-deepgram-sagemaker.py
@@ -114,7 +114,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07c-interruptible-deepgram-vad.py
+++ b/examples/foundational/07c-interruptible-deepgram-vad.py
@@ -106,7 +106,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07c-interruptible-deepgram.py
+++ b/examples/foundational/07c-interruptible-deepgram.py
@@ -100,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07d-interruptible-elevenlabs-http.py
+++ b/examples/foundational/07d-interruptible-elevenlabs-http.py
@@ -108,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            logger.info(f"Client connected")
            # Kick off the conversation.
            context.add_message(
-                {"role": "user", "content": "Please introduce yourself to the user."}
+                {"role": "developer", "content": "Please introduce yourself to the user."}
            )
            await task.queue_frames([LLMRunFrame()])

--- a/examples/foundational/07d-interruptible-elevenlabs.py
+++ b/examples/foundational/07d-interruptible-elevenlabs.py
@@ -100,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
--- a/examples/foundational/07e-interruptible-xai.py
+++ b/examples/foundational/07e-interruptible-xai.py
@@ -0,0 +1,128 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.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.deepgram.stt import DeepgramSTTService
+from pipecat.services.xai.llm import GrokLLMService
+from pipecat.services.xai.tts import XAIHttpTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = XAIHttpTTSService(
+            api_key=os.getenv("XAI_API_KEY"),
+            aiohttp_session=session,
+            settings=XAIHttpTTSService.Settings(
+                voice="eve",
+            ),
+        )
+
+        llm = GrokLLMService(
+            api_key=os.getenv("XAI_API_KEY"),
+            settings=GrokLLMService.Settings(
+                system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+            ),
+        )
+
+        context = LLMContext()
+        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+            context,
+            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+        )
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                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.
+            context.add_message(
+                {"role": "developer", "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()
--- a/Show More
+++ b/Show More
				`@@ -1 +0,0 @@`
				- Changed tool result JSON serialization to use `ensure_ascii=False`, preserving UTF-8 characters instead of escaping them. This reduces context size and token usage for non-English languages.
				`@@ -0,0 +1 @@`
				- Added `SarvamLLMService` with support for `sarvam-30b`, `sarvam-30b-16k`, `sarvam-105b` and `sarvam-105b-32k`
				`@@ -1 +0,0 @@`
				- `OpenAIRealtimeSTTService`'s `noise_reduction` parameter is now part of `OpenAIRealtimeSTTSettings`, making it runtime-updatable via `STTUpdateSettingsFrame`. The direct `noise_reduction` init argument is deprecated as of 0.0.106.
				`@@ -1 +0,0 @@`
				- Updated `sarvamai` dependency from `0.1.26a2` (alpha) to `0.1.26` (stable release).
				`@@ -1 +0,0 @@`
				- Fixed an issue where the default model for `OpenAILLMService` and `AzureLLMService` was mistakenly reverted to `gpt-4o`. The defaults are now restored to `gpt-4.1`.
				`@@ -1 +0,0 @@`
				- `SimliVideoService` now extends `AIService` instead of `FrameProcessor`, aligning it with the HeyGen and Tavus video services. It supports `SimliVideoService.Settings(...)` for configuration and uses `start()`/`stop()`/`cancel()` lifecycle methods. Existing constructor usage (`api_key`, `face_id`, etc.) remains unchanged.
				`@@ -1 +0,0 @@`
				- `SimliVideoService.InputParams` is deprecated. Use the direct constructor parameters `max_session_length`, `max_idle_time`, and `enable_logging` instead.
				`@@ -1 +0,0 @@`
				- Added optional `service` field to `ServiceUpdateSettingsFrame` (and its subclasses `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `STTUpdateSettingsFrame`) to target a specific service instance. When `service` is set, only the matching service applies the settings; others forward the frame unchanged. This enables updating a single service when multiple services of the same type exist in the pipeline.
				`@@ -1 +0,0 @@`
				- Added `sip_provider` and `room_geo` parameters to `configure()` in the Daily runner. These convenience parameters let callers specify a SIP provider name and geographic region directly without manually constructing `DailyRoomProperties` and `DailyRoomSipParams`.
				`@@ -1 +0,0 @@`
				- Fixed a race condition where `EndTaskFrame` could cause the pipeline to shut down before in-flight frames (e.g. LLM function call responses) finished processing. `EndTaskFrame` and `StopTaskFrame` now flow through the pipeline as `ControlFrame`s, ensuring all pending work is flushed before shutdown begins. `CancelTaskFrame` and `InterruptionTaskFrame` remain immediate (`SystemFrame`).