Fix copyright

Run the content filter concurrently with LLM text generation
using ParallelPipeline, with a ContentFilterGate that blocks
output until the filter approves or rejects the content.

.claude/skills/changelog/SKILL.md

@@ -32,20 +32,6 @@ Create changelog files for the important commits in this PR. The PR number is pr
 
 6. Use ⚠️ emoji prefix for breaking changes.
 
-7. **Write changes in user-facing terms first.** Lead with what users of the framework will notice: new APIs, changed behavior, new parameters, fixed bugs they might have hit, etc. Implementation details (internal refactoring, how something is wired up under the hood) can be included as secondary context after the user-facing description, but should never be the *only* content of a changelog entry when there is a user-visible effect.
-
-   **Good** (user-facing first, implementation detail as context):
-   ```
-   - Turn completion instructions now persist correctly across full context updates when using `system_instruction`. Previously they were injected as a context system message, which caused warning spam and didn't survive context updates.
-   ```
-
-   **Bad** (implementation detail only, no user-facing framing):
-   ```
-   - Fixed turn completion instructions being injected as a context system message instead of using `system_instruction`.
-   ```
-
-   Ask yourself: "If I'm a developer building on Pipecat, what would I notice changed?" Start there.
-
 ## Example
 
 For PR #3519 with a new feature and a bug fix:
@@ -57,5 +43,5 @@ For PR #3519 with a new feature and a bug fix:
 
 `changelog/3519.fixed.md`:
 ```
-- Fixed an issue where something was not working correctly in some user-visible scenario. The root cause was an internal implementation detail.
+- Fixed an issue where something was not working correctly.
 ```

CHANGELOG.md

@@ -7,271 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 <!-- towncrier release notes start -->
 
-## [0.0.105] - 2026-03-10
-
-### Added
-
-- Added concurrent audio context support: `CartesiaTTSService` can now
-  synthesize the next sentence while the previous one is still playing, by
-  setting `pause_frame_processing=False` and routing each sentence through its
-  own audio context queue.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
-- Added custom video track support to Daily transport. Use
-  `video_out_destinations` in `DailyParams` to publish multiple video tracks
-  simultaneously, mirroring the existing `audio_out_destinations` feature.
-  (PR [#3831](https://github.com/pipecat-ai/pipecat/pull/3831))
-
-- Added `ServiceSwitcherStrategyFailover` that automatically switches to the
-  next service when the active service reports a non-fatal error. Recovery
-  policies can be implemented via the `on_service_switched` event handler.
-  (PR [#3861](https://github.com/pipecat-ai/pipecat/pull/3861))
-
-- Added optional `timeout_secs` parameter to `register_function()` and
-  `register_direct_function()` for per-tool function call timeout control,
-  overriding the global `function_call_timeout_secs` default.
-  (PR [#3915](https://github.com/pipecat-ai/pipecat/pull/3915))
-
-- Added `cloud-audio-only` recording option to Daily transport's
-  `enable_recording` property.
-  (PR [#3916](https://github.com/pipecat-ai/pipecat/pull/3916))
-
-- Wired up `system_instruction` in `BaseOpenAILLMService`,
-  `AnthropicLLMService`, and `AWSBedrockLLMService` so it works as a default
-  system prompt, matching the behavior of the Google services. This enables
-  sharing a single `LLMContext` across multiple LLM services, where each
-  service provides its own system instruction independently.
-
-    ```python
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        system_instruction="You are a helpful assistant.",
-    )
-
-    context = LLMContext()
-
-    @transport.event_handler("on_client_connected")
-    async def on_client_connected(transport, client):
-        context.add_message({"role": "user", "content": "Please introduce yourself."})
-        await task.queue_frames([LLMRunFrame()])
-    ```
-  (PR [#3918](https://github.com/pipecat-ai/pipecat/pull/3918))
-
-- Added `vad_threshold` parameter to `AssemblyAIConnectionParams` for
-  configuring voice activity detection sensitivity in U3 Pro. Aligning this
-  with external VAD thresholds (e.g., Silero VAD) prevents the "dead zone"
-  where AssemblyAI transcribes speech that VAD hasn't detected yet.
-  (PR [#3927](https://github.com/pipecat-ai/pipecat/pull/3927))
-
-- Added `push_empty_transcripts` parameter to `BaseWhisperSTTService` and
-  `OpenAISTTService` to allow empty transcripts to be pushed downstream as
-  `TranscriptionFrame` instead of discarding them (the default behavior). This
-  is intended for situations where VAD fires even though the user did not
-  speak. In these cases, it is useful to know that nothing was transcribed so
-  that the agent can resume speaking, instead of waiting longer for a
-  transcription.
-  (PR [#3930](https://github.com/pipecat-ai/pipecat/pull/3930))
-
-- LLM services (`BaseOpenAILLMService`, `AnthropicLLMService`,
-  `AWSBedrockLLMService`) now log a warning when both `system_instruction` and
-  a system message in the context are set. The constructor's
-  `system_instruction` takes precedence.
-  (PR [#3932](https://github.com/pipecat-ai/pipecat/pull/3932))
-
-- Runtime settings updates (via `STTUpdateSettingsFrame`) now work for AWS
-  Transcribe, Azure, Cartesia, Deepgram, ElevenLabs Realtime, Gradium, and
-  Soniox STT services. Previously, changing settings at runtime only stored the
-  new values without reconnecting.
-  (PR [#3946](https://github.com/pipecat-ai/pipecat/pull/3946))
-
-- Exposed `on_summary_applied` event on `LLMAssistantAggregator`, allowing
-  users to listen for context summarization events without accessing private
-  members.
-  (PR [#3947](https://github.com/pipecat-ai/pipecat/pull/3947))
-
-- Deepgram Flux STT settings (`keyterm`, `eot_threshold`,
-  `eager_eot_threshold`, `eot_timeout_ms`) can now be updated mid-stream via
-  `STTUpdateSettingsFrame` without triggering a reconnect. The new values are
-  sent to Deepgram as a Configure WebSocket message on the existing connection.
-  (PR [#3953](https://github.com/pipecat-ai/pipecat/pull/3953))
-
-- Added `system_instruction` parameter to `run_inference` across all LLM
-  services, allowing callers to override the system prompt for one-shot
-  inference calls. Used by `_generate_summary` to pass the summarization prompt
-  cleanly.
-  (PR [#3968](https://github.com/pipecat-ai/pipecat/pull/3968))
-
-### Changed
-
-- Audio context management (previously in `AudioContextTTSService`) is now
-  built into `TTSService`. All WebSocket providers (`cartesia`, `elevenlabs`,
-  `asyncai`, `inworld`, `rime`, `gradium`, `resembleai`) now inherit from
-  `WebsocketTTSService` directly. Word-timestamp baseline is set automatically
-  on the first audio chunk of each context instead of requiring each provider
-  to call `start_word_timestamps()` in their receive loop.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
-- Daily transport now uses `CustomVideoSource`/`CustomVideoTrack` instead of
-  `VirtualCameraDevice` for the default camera output, mirroring how audio
-  already works with `CustomAudioSource`/`CustomAudioTrack`.
-  (PR [#3831](https://github.com/pipecat-ai/pipecat/pull/3831))
-
-- ⚠️ Updated `DeepgramSTTService` to use `deepgram-sdk` v6. The `LiveOptions`
-  class was removed from the SDK and is now provided by pipecat directly;
-  import it from `pipecat.services.deepgram.stt` instead of `deepgram`.
-  (PR [#3848](https://github.com/pipecat-ai/pipecat/pull/3848))
-
-- `ServiceSwitcherStrategy` base class now provides a `handle_error()` hook for
-  subclasses to implement error-based switching. `ServiceSwitcher` defaults to
-  `ServiceSwitcherStrategyManual` and `strategy_type` is now optional.
-  (PR [#3861](https://github.com/pipecat-ai/pipecat/pull/3861))
-
-- Support for Voice Focus 2.0 models.
-    - Updated `aic-sdk` to `~=2.1.0` to support Voice Focus 2.0 models.
-    - Cleaned unused `ParameterFixedError` exception handling in `AICFilter`
-      parameter setup.
-  (PR [#3889](https://github.com/pipecat-ai/pipecat/pull/3889))
-
-- `max_context_tokens` and `max_unsummarized_messages` in
-  `LLMAutoContextSummarizationConfig` (and deprecated
-  `LLMContextSummarizationConfig`) can now be set to `None` independently to
-  disable that summarization threshold. At least one must remain set.
-  (PR [#3914](https://github.com/pipecat-ai/pipecat/pull/3914))
-
-- ⚠️ Removed `formatted_finals` and `word_finalization_max_wait_time` from
-  `AssemblyAIConnectionParams` as these were v2 API parameters not supported in
-  v3. Clarified that `format_turns` only applies to Universal-Streaming models;
-  U3 Pro has automatic formatting built-in.
-  (PR [#3927](https://github.com/pipecat-ai/pipecat/pull/3927))
-
-- Changed `DeepgramTTSService` to send a Clear message on interruption instead
-  of disconnecting and reconnecting the WebSocket, allowing the connection to
-  persist throughout the session.
-  (PR [#3958](https://github.com/pipecat-ai/pipecat/pull/3958))
-
-- Re-added `enhancement_level` support to `AICFilter` with runtime
-  `FilterEnableFrame` control, applying `ProcessorParameter.Bypass` and
-  `ProcessorParameter.EnhancementLevel` together.
-  (PR [#3961](https://github.com/pipecat-ai/pipecat/pull/3961))
-
-- Updated `daily-python` dependency from `~=0.23.0` to `~=0.24.0`.
-  (PR [#3970](https://github.com/pipecat-ai/pipecat/pull/3970))
-
-- Updated `FishAudioTTSService` default model from `s1` to `s2-pro`, matching
-  Fish Audio's latest recommended model for improved quality and speed.
-  (PR [#3973](https://github.com/pipecat-ai/pipecat/pull/3973))
-
-- `AzureSTTService` `region` parameter is now optional when `private_endpoint`
-  is provided. A `ValueError` is raised if neither is given, and a warning is
-  logged if both are provided (`private_endpoint` takes priority).
-  (PR [#3974](https://github.com/pipecat-ai/pipecat/pull/3974))
-
-### Deprecated
-
-- Deprecated `AudioContextTTSService` and `AudioContextWordTTSService`.
-  Subclass `WebsocketTTSService` directly instead; audio context management is
-  now part of the base `TTSService`.
-  - Deprecated `WordTTSService`, `WebsocketWordTTSService`, and
-    `InterruptibleWordTTSService`. Word timestamp logic is now always active in
-    `TTSService` and no longer needs to be opted into via a subclass.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
-- Deprecated `pipecat.services.google.llm_vertex`,
-  `pipecat.services.google.llm_openai`, and
-  `pipecat.services.google.gemini_live.llm_vertex` modules. Use
-  `pipecat.services.google.vertex.llm`, `pipecat.services.google.openai.llm`,
-  and `pipecat.services.google.gemini_live.vertex.llm` instead. The old import
-  paths still work but will emit a `DeprecationWarning`.
-  (PR [#3980](https://github.com/pipecat-ai/pipecat/pull/3980))
-
-### Removed
-
-- ⚠️ Removed `supports_word_timestamps` parameter from `TTSService.__init__()`.
-  Word timestamp logic is now always active. Remove this argument from any
-  custom subclass `super().__init__()` calls.
-  (PR [#3804](https://github.com/pipecat-ai/pipecat/pull/3804))
-
-### Fixed
-
-- Fixed `DeepgramSTTService` keepalive ping timeout disconnections. The
-  deepgram-sdk v6 removed automatic keepalive; pipecat now sends explicit
-  `KeepAlive` messages every 5 seconds, within the recommended 3–5 second
-  interval before Deepgram's 10-second inactivity timeout.
-  (PR [#3848](https://github.com/pipecat-ai/pipecat/pull/3848))
-
-- Fixed `BufferError: Existing exports of data: object cannot be re-sized` in
-  `AICFilter` caused by holding a `memoryview` on the mutable audio buffer
-  across async yield points.
-  (PR [#3889](https://github.com/pipecat-ai/pipecat/pull/3889))
-
-- Fixed TTS context not being appended to the assistant message history when
-  using `TTSSpeakFrame` with `append_to_context=True` with some TTS providers.
-  (PR [#3936](https://github.com/pipecat-ai/pipecat/pull/3936))
-
-- Fixed context summarization leaving orphaned tool responses in the kept
-  context when tool calls were moved to the summarized portion.
-  (PR [#3937](https://github.com/pipecat-ai/pipecat/pull/3937))
-
-- Fixed turn completion state not resetting at end of LLM responses.
-  `LLMFullResponseEndFrame` is pushed (not received) by the LLM service, so the
-  mixin now handles it in `push_frame` instead of `process_frame`.
-  (PR [#3956](https://github.com/pipecat-ai/pipecat/pull/3956))
-
-- Fixed turn completion instructions being injected as a context system message
-  instead of using `system_instruction`. This caused warning spam when
-  `system_instruction` was also set and didn't persist across full context
-  updates.
-  (PR [#3957](https://github.com/pipecat-ai/pipecat/pull/3957))
-
-- Fixed `TTSService` audio context queue getting blocked when
-  `append_to_audio_context()` was called with a `None` context ID, which
-  prevented subsequent audio from being delivered.
-  (PR [#3958](https://github.com/pipecat-ai/pipecat/pull/3958))
-
-- Fixed `on_call_state_updated` event handler in LiveKit transport receiving
-  incorrect number of arguments due to redundant `self` passed to
-  `_call_event_handler`.
-  (PR [#3959](https://github.com/pipecat-ai/pipecat/pull/3959))
-
-- Fixed OpenAI Realtime, OpenAI Realtime Beta, and Grok realtime services
-  treating `conversation_already_has_active_response` as a fatal error. These
-  services now log it as a non-fatal debug event when a response is already in
-  progress.
-  (PR [#3960](https://github.com/pipecat-ai/pipecat/pull/3960))
-
-- Fixed `SmallWebRTCConnection` silently discarding messages sent before the
-  data channel is open by queuing them and flushing once the channel is ready.
-  A bounded queue (`MAX_MESSAGE_QUEUE_SIZE = 50`) prevents unbounded memory
-  growth, and a 10-second timeout after connection clears the queue and falls
-  back to discard mode if the data channel never opens.
-  (PR [#3962](https://github.com/pipecat-ai/pipecat/pull/3962))
-
-- Fixed `AzureSTTService` failing to initialize when `private_endpoint` is
-  provided. The Azure Speech SDK's `SpeechConfig` does not accept both `region`
-  and `endpoint` simultaneously, so they are now passed conditionally.
-  (PR [#3967](https://github.com/pipecat-ai/pipecat/pull/3967))
-
-- Fixed `GoogleLLMService` ignoring the `system_instruction` set via
-  constructor or `GoogleLLMSettings` when a system message was also present in
-  the context. The settings value now correctly takes priority, and a warning
-  is logged when both are set.
-  (PR [#3976](https://github.com/pipecat-ai/pipecat/pull/3976))
-
-### Other
-
-- Updated foundational examples to use `system_instruction` on LLM services
-  instead of adding system messages to `LLMContext`.
-  (PR [#3918](https://github.com/pipecat-ai/pipecat/pull/3918))
-
-- Updated AssemblyAI turn detection example to use `keyterms_prompt` list
-  format instead of `prompt` string for improved clarity.
-  (PR [#3929](https://github.com/pipecat-ai/pipecat/pull/3929))
-
-- Updated foundational examples and eval scripts to use `"user"` role instead
-  of `"system"` when adding messages to `LLMContext`, since system prompts
-  should be set via `system_instruction` on the LLM service.
-  (PR [#3931](https://github.com/pipecat-ai/pipecat/pull/3931))
-
 ## [0.0.104] - 2026-03-02
 
 ### Added

COMMUNITY_INTEGRATIONS.md

@@ -231,105 +231,49 @@ def can_generate_metrics(self) -> bool:
     return True
 ```
 
-### Service Settings
+### Dynamic Settings Updates
 
-Every AI service (STT, LLM, TTS, image generation, etc.) exposes a **Settings dataclass** that serves two roles:
+STT, LLM, and TTS services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
 
-1. **Store mode** — the service's `self._settings` holds the current value of every runtime-updatable field.
-2. **Delta mode** — an update frame (e.g. `TTSUpdateSettingsFrame`) specifies only the fields that should change; unspecified fields remain `NOT_GIVEN`.
-
-#### Defining your Settings class
-
-Extend `STTSettings`, `TTSSettings`, `LLMSettings`, or `ImageGenSettings` (or, if your service directly subclasses `AIService`, `ServiceSettings`). The base classes already provide common fields (e.g. `model`, `voice`, `language`). You only need to add **service-specific knobs that should be runtime-updatable**:
+Each service declares a settings dataclass that extends the appropriate base (`STTSettings`, `TTSSettings`, `LLMSettings`). Fields default to `NOT_GIVEN` so that update objects can represent sparse deltas:
 
 ```python
 from dataclasses import dataclass, field
 
-from pipecat.services.settings import TTSSettings, NOT_GIVEN
+from pipecat.services.settings import STTSettings, NOT_GIVEN
 
 @dataclass
-class MyTTSSettings(TTSSettings):
-    """Settings for MyTTS service.
+class MySTTSettings(STTSettings):
+    """Settings for my STT service.
 
     Parameters:
-        speaking_rate: Speed multiplier (0.5–2.0).
+        region: Cloud region for the service.
     """
 
-    speaking_rate: float | None = field(default_factory=lambda: NOT_GIVEN)
+    region: str = field(default_factory=lambda: NOT_GIVEN)
 ```
 
-**What goes in Settings vs. `__init__` params:**
-
-| Belongs in Settings                                      | Stays as `__init__` params                |
-| -------------------------------------------------------- | ----------------------------------------- |
-| Model name, voice, language                              | API keys, auth tokens                     |
-| Service-specific tuning knobs (rate, pitch, temperature) | Base URLs, endpoint overrides             |
-| Anything users may want to change mid-session            | Audio encoding, sample format             |
-|                                                          | Connection parameters (timeouts, retries) |
-
-The rule of thumb: if a caller might send an update frame to change it at runtime, it belongs in Settings. Everything else is init-only config stored as `self._xxx`.
-
-#### Wiring settings into `__init__`
-
-Accept an **optional** `settings` parameter. Build a `default_settings` object with all fields set to real values, then merge any caller overrides with `apply_update`.
-
-Add a `Settings` **class attribute** that points to your settings dataclass. This lets callers access the settings class through the service itself (e.g. `MyTTSService.Settings(...)`) without a separate import:
+The service stores its current settings in `self._settings` and declares the type with a class-level annotation for editor support:
 
 ```python
-from typing import Optional
+class MySTTService(STTService):
+    _settings: MySTTSettings
 
-class MyTTSService(TTSService):
-    Settings = MyTTSSettings
-    _settings: MyTTSSettings
-
-    def __init__(
-        self,
-        *,
-        api_key: str,
-        settings: Optional[MyTTSSettings] = None,
-        **kwargs,
-    ):
-        # 1. Defaults — every field has a real value (store mode).
-        default_settings = MyTTSSettings(
-            model="my-model-v1",
-            voice="default-voice",
-            language="en",
-            speaking_rate=1.0,
+    def __init__(self, *, model: str, language: str, region: str, **kwargs):
+        # An initial value should be provided for every settings field.
+        # This will be validated at service start.
+        # (If you track sample_rate, it can be a placeholder value like 0; see
+        # "Sample Rate Handling").
+        super().__init__(
+            settings=MySTTSettings(model=model, language=language, region=region), **kwargs
         )
-
-        # 2. Merge caller overrides (only given fields win).
-        if settings is not None:
-            default_settings.apply_update(settings)
-
-        # 3. Pass the fully-populated settings to the base class.
-        super().__init__(settings=default_settings, **kwargs)
-
-        # 4. Init-only config stored separately.
-        self._api_key = api_key
 ```
 
-This pattern lets callers override only what they care about:
-
-```python
-# Uses all defaults
-svc = MyTTSService(api_key="sk-xxx")
-
-# Overrides just the voice — access Settings through the service class
-svc = MyTTSService(
-    api_key="sk-xxx",
-    settings=MyTTSService.Settings(voice="custom-voice"),
-)
-```
-
-#### Reacting to runtime changes
-
-AI services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
-
 To react to runtime setting changes, override `_update_settings`. The base implementation applies the delta to `self._settings` and returns a `dict` mapping each changed field name to its **pre-update** value. Your override should call `super()` first, then act on the changed fields. A common implementation might look like:
 
 ```python
-async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
-    """Apply a settings update, reconfiguring the connection if needed."""
+async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
+    """Apply a settings update, reconfiguring the recognizer if needed."""
     changed = await super()._update_settings(update)
 
     if not changed:
@@ -348,7 +292,7 @@ Note that, in this example, the service requires a reconnect to apply the new la
 If your service can't yet apply certain settings at runtime, call `self._warn_unhandled_updated_settings(changed)` with any unhandled field names so users get a clear log message:
 
 ```python
-async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
+async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
     changed = await super()._update_settings(update)
 
     if not changed:

README.md

@@ -81,19 +81,19 @@ 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), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                                                                                             |
+| LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                                                                                                                                                                                                                                                                                               |
+| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [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)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)
 

changelog/3848.changed.md

@@ -0,0 +1 @@
+- ⚠️ Updated `DeepgramSTTService` to use `deepgram-sdk` v6. The `LiveOptions` class was removed from the SDK and is now provided by pipecat directly; import it from `pipecat.services.deepgram.stt` instead of `deepgram`.

changelog/3848.fixed.md

@@ -0,0 +1 @@
+- Fixed `DeepgramSTTService` keepalive ping timeout disconnections. The deepgram-sdk v6 removed automatic keepalive; pipecat now sends explicit `KeepAlive` messages every 5 seconds, within the recommended 3–5 second interval before Deepgram's 10-second inactivity timeout.

changelog/3889.changed.md

@@ -0,0 +1,3 @@
+- Support for Voice Focus 2.0 models.
+  - Updated `aic-sdk` to `~=2.1.0` to support Voice Focus 2.0 models.
+  - Cleaned unused `ParameterFixedError` exception handling in `AICFilter` parameter setup. 

changelog/3889.fixed.md

@@ -0,0 +1 @@
+- Fixed `BufferError: Existing exports of data: object cannot be re-sized` in `AICFilter` caused by holding a `memoryview` on the mutable audio buffer across async yield points.

changelog/3914.changed.md

@@ -0,0 +1 @@
+- `max_context_tokens` and `max_unsummarized_messages` in `LLMAutoContextSummarizationConfig` (and deprecated `LLMContextSummarizationConfig`) can now be set to `None` independently to disable that summarization threshold. At least one must remain set.

changelog/3915.added.md

@@ -0,0 +1 @@
+- Added optional `timeout_secs` parameter to `register_function()` and `register_direct_function()` for per-tool function call timeout control, overriding the global `function_call_timeout_secs` default.

changelog/3916.added.md

@@ -0,0 +1 @@
+- Added `cloud-audio-only` recording option to Daily transport's `enable_recording` property.

changelog/3918.added.md

@@ -0,0 +1,15 @@
+- Wired up `system_instruction` in `BaseOpenAILLMService`, `AnthropicLLMService`, and `AWSBedrockLLMService` so it works as a default system prompt, matching the behavior of the Google services. This enables sharing a single `LLMContext` across multiple LLM services, where each service provides its own system instruction independently.
+
+  ```python
+  llm = OpenAILLMService(
+      api_key=os.getenv("OPENAI_API_KEY"),
+      system_instruction="You are a helpful assistant.",
+  )
+
+  context = LLMContext()
+
+  @transport.event_handler("on_client_connected")
+  async def on_client_connected(transport, client):
+      context.add_message({"role": "user", "content": "Please introduce yourself."})
+      await task.queue_frames([LLMRunFrame()])
+  ```

changelog/3918.other.md

@@ -0,0 +1 @@
+- Updated foundational examples to use `system_instruction` on LLM services instead of adding system messages to `LLMContext`.

env.example

@@ -86,6 +86,9 @@ GROK_API_KEY=...
 # Groq
 GROQ_API_KEY=...
 
+# Hathora
+HATHORA_API_KEY=...
+
 # Heygen
 HEYGEN_API_KEY=...
 HEYGEN_LIVE_AVATAR_API_KEY=...

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

@@ -39,9 +39,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         tts = PiperHttpTTSService(
-            base_url=os.getenv("PIPER_BASE_URL"),
-            aiohttp_session=session,
-            sample_rate=24000,
+            base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
         )
 
         task = PipelineTask(

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

@@ -39,10 +39,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         tts = RimeHttpTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
+            voice_id="rex",
             aiohttp_session=session,
-            settings=RimeHttpTTSService.Settings(
-                voice="rex",
-            ),
         )
 
         task = PipelineTask(

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

@@ -37,9 +37,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     task = PipelineTask(

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

@@ -29,9 +29,7 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     pipeline = Pipeline([tts, transport.output()])

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

@@ -37,9 +37,7 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     runner = PipelineRunner()

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

@@ -39,16 +39,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
-        ),
+        system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
     )
 
     task = PipelineTask(
@@ -60,7 +56,7 @@ 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": "system", "content": "Say hello to the world."})
         await task.queue_frames([LLMContextFrame(context), EndFrame()])
 
     runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

examples/foundational/03-still-frame.py

@@ -45,9 +45,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
         imagegen = FalImageGenService(
-            settings=FalImageGenService.Settings(
-                image_size="square_hd",
-            ),
+            params=FalImageGenService.InputParams(image_size="square_hd"),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )

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

@@ -37,9 +37,7 @@ async def main():
         )
 
         imagegen = FalImageGenService(
-            settings=FalImageGenService.Settings(
-                image_size="square_hd",
-            ),
+            params=FalImageGenService.InputParams(image_size="square_hd"),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )

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

@@ -67,16 +67,12 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -109,7 +105,7 @@ 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": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -50,17 +50,13 @@ async def main():
 
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
-            settings=CartesiaTTSService.Settings(
-                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            ),
+            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                model="gpt-4o",
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            model="gpt-4o",
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -93,7 +89,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -57,16 +57,12 @@ async def main():
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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.",
     )
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     context = LLMContext()

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

@@ -98,15 +98,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = CartesiaHttpTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
-            settings=CartesiaHttpTTSService.Settings(
-                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            ),
+            voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
         )
 
         imagegen = FalImageGenService(
-            settings=FalImageGenService.Settings(
-                image_size="square_hd",
-            ),
+            params=FalImageGenService.InputParams(image_size="square_hd"),
             aiohttp_session=session,
             key=os.getenv("FAL_KEY"),
         )
@@ -152,7 +148,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         ]:
             messages = [
                 {
-                    "role": "user",
+                    "role": "system",
                     "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.",
                 }
             ]

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

@@ -49,7 +49,7 @@ async def main():
         async def get_month_data(month):
             messages = [
                 {
-                    "role": "user",
+                    "role": "system",
                     "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.",
                 }
             ]
@@ -98,15 +98,11 @@ async def main():
 
             tts = CartesiaHttpTTSService(
                 api_key=os.getenv("CARTESIA_API_KEY"),
-                settings=CartesiaHttpTTSService.Settings(
-                    voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-                ),
+                voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
             )
 
             imagegen = FalImageGenService(
-                settings=FalImageGenService.Settings(
-                    image_size="square_hd",
-                ),
+                params=FalImageGenService.InputParams(image_size="square_hd"),
                 aiohttp_session=session,
                 key=os.getenv("FAL_KEY"),
             )

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

@@ -83,16 +83,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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.",
     )
 
     ml = MetricsLogger()
@@ -129,7 +125,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -100,16 +100,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()

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

@@ -6,7 +6,6 @@
 
 import os
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -53,68 +52,60 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    async with aiohttp.ClientSession() as session:
-        stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
+    stt = CartesiaSTTService(api_key=os.getenv("CARTESIA_API_KEY"))
 
-        tts = CartesiaHttpTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            aiohttp_session=session,
-            settings=CartesiaHttpTTSService.Settings(
-                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            ),
-        )
+    tts = CartesiaHttpTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
-        )
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+    )
 
-        context = LLMContext()
-        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
-            context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
-        )
+    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
-            ]
-        )
+    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,
-        )
+    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_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
 
-        @transport.event_handler("on_client_disconnected")
-        async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
-            await task.cancel()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
 
-        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 async def bot(runner_args: RunnerArguments):

examples/foundational/07-interruptible.py

@@ -24,6 +24,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.tts_service import TextAggregationMode
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -55,16 +56,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+        # Alternatively, you can use TextAggregationMode.TOKEN to stream tokens instead of
+        # sentencesfor faster response times.
+        # text_aggregation_mode=TextAggregationMode.TOKEN,
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -98,7 +98,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -21,6 +21,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
@@ -92,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SpeechmaticsSTTService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            settings=SpeechmaticsSTTService.Settings(
+            params=SpeechmaticsSTTService.InputParams(
                 language=Language.EN,
                 turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
                 # focus_speakers=["S1"],
@@ -103,21 +104,32 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = SpeechmaticsTTSService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            settings=SpeechmaticsTTSService.Settings(
-                voice="sarah",
-            ),
+            voice_id="sarah",
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                temperature=0.75,
-                system_instruction="You are a helpful British assistant called Sarah. 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. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
-            ),
+            params=BaseOpenAILLMService.InputParams(temperature=0.75),
         )
 
-        context = LLMContext()
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful British assistant called Sarah. "
+                    "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. "
+                    "Always include punctuation in your responses. "
+                    "Give very short replies - do not give longer replies unless strictly necessary. "
+                    "Respond to what the user said in a concise, funny, creative and helpful way. "
+                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
+                    "Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
+                ),
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
@@ -148,7 +160,7 @@ 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."})
+            messages.append({"role": "system", "content": "Say a short hello to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

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

@@ -22,6 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.openai.base_llm import BaseOpenAILLMService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
 from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
@@ -75,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SpeechmaticsSTTService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            settings=SpeechmaticsSTTService.Settings(
+            params=SpeechmaticsSTTService.InputParams(
                 language=Language.EN,
                 speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
             ),
@@ -83,21 +84,31 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = SpeechmaticsTTSService(
             api_key=os.getenv("SPEECHMATICS_API_KEY"),
-            settings=SpeechmaticsTTSService.Settings(
-                voice="sarah",
-            ),
+            voice_id="sarah",
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                temperature=0.75,
-                system_instruction="You are a helpful British assistant called Sarah. 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. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
-            ),
+            params=BaseOpenAILLMService.InputParams(temperature=0.75),
         )
 
-        context = LLMContext()
+        messages = [
+            {
+                "role": "system",
+                "content": (
+                    "You are a helpful British assistant called Sarah. "
+                    "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. "
+                    "Always include punctuation in your responses. "
+                    "Give very short replies - do not give longer replies unless strictly necessary. "
+                    "Respond to what the user said in a concise, funny, creative and helpful way. "
+                    "Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
+                ),
+            },
+        ]
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -128,7 +139,7 @@ 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."})
+            messages.append({"role": "system", "content": "Say a short hello to the user."})
             await task.queue_frames([LLMRunFrame()])
 
         @transport.event_handler("on_client_disconnected")

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

@@ -71,9 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     prompt = ChatPromptTemplate.from_messages(

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

@@ -56,23 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramFluxSTTService(
         api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramFluxSTTService.Settings(
-            min_confidence=0.3,
-        ),
+        params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
     )
 
-    tts = DeepgramTTSService(
-        api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramTTSService.Settings(
-            voice="aura-2-andromeda-en",
-        ),
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -109,7 +100,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -59,20 +59,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = DeepgramHttpTTSService(
             api_key=os.getenv("DEEPGRAM_API_KEY"),
-            settings=DeepgramHttpTTSService.Settings(
-                voice="aura-2-andromeda-en",
-            ),
+            voice="aura-2-andromeda-en",
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
-        context = LLMContext()
+        messages = []
+
+        context = LLMContext(messages)
         user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
             context,
             user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -104,7 +102,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
+from pipecat.services.aws.llm import AWSBedrockLLMService
 from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTService
 from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -69,18 +69,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     tts = DeepgramSageMakerTTSService(
         endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
         region=os.getenv("AWS_REGION"),
-        settings=DeepgramSageMakerTTSService.Settings(
-            voice="aura-2-andromeda-en",
-        ),
+        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 LLM in a WebRTC call. 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.",
-        ),
+        model="us.amazon.nova-pro-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -114,7 +110,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -7,6 +7,7 @@
 
 import os
 
+from deepgram import LiveOptions
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -55,24 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(
         api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramSTTService.Settings(
-            vad_events=True,
-            utterance_end_ms="1000",
-        ),
+        live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
     )
 
-    tts = DeepgramTTSService(
-        api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramTTSService.Settings(
-            voice="aura-2-andromeda-en",
-        ),
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -106,7 +97,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -55,18 +55,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(
-        api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramTTSService.Settings(
-            voice="aura-2-andromeda-en",
-        ),
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -100,7 +93,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -63,17 +63,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = ElevenLabsHttpTTSService(
             api_key=os.getenv("ELEVENLABS_API_KEY", ""),
+            voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
             aiohttp_session=session,
-            settings=ElevenLabsHttpTTSService.Settings(
-                voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
-            ),
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -108,7 +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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -57,16 +57,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = ElevenLabsTTSService(
         api_key=os.getenv("ELEVENLABS_API_KEY", ""),
-        settings=ElevenLabsTTSService.Settings(
-            voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
-        ),
+        voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -100,7 +96,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -65,10 +65,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AzureLLMService(
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-        settings=AzureLLMService.Settings(
-            model=os.getenv("AZURE_CHATGPT_MODEL"),
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model=os.getenv("AZURE_CHATGPT_MODEL"),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -102,7 +100,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -65,10 +65,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = AzureLLMService(
         api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
         endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
-        settings=AzureLLMService.Settings(
-            model=os.getenv("AZURE_CHATGPT_MODEL"),
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model=os.getenv("AZURE_CHATGPT_MODEL"),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -102,7 +100,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -54,24 +54,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = OpenAISTTService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAISTTService.Settings(
-            model="gpt-4o-transcribe",
-            prompt="Expect words related to dogs, such as breed names.",
-        ),
+        model="gpt-4o-transcribe",
+        prompt="Expect words related to dogs, such as breed names.",
     )
 
-    tts = OpenAITTSService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAITTSService.Settings(
-            voice="ballad",
-        ),
-    )
+    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are very knowledgable about dogs. 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.",
-        ),
+        system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -106,7 +97,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -55,25 +55,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = OpenAIRealtimeSTTService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAIRealtimeSTTService.Settings(
-            model="gpt-4o-transcribe",
-            prompt="Expect words related to dogs, such as breed names.",
-            language=Language.EN,
-        ),
+        model="gpt-4o-transcribe",
+        prompt="Expect words related to dogs, such as breed names.",
+        language=Language.EN,
+        # Uses local VAD by default.
+        # To enable server-side VAD, set turn_detection=None or
+        # a dict with server_vad settings.
+        # turn_detection={"type": "server_vad", "threshold": 0.5},
     )
 
-    tts = OpenAITTSService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAITTSService.Settings(
-            voice="ballad",
-        ),
-    )
+    tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are very knowledgable about dogs. 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.",
-        ),
+        system_instruction="You are very knowledgable about dogs. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -108,7 +103,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -57,9 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     timestamp = int(time.time())
@@ -67,9 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         api_key=os.getenv("OPENAI_API_KEY"),
         openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
         tags={"conversation_id": f"pipecat-{timestamp}"},
-        settings=OpenPipeLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -103,7 +99,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -59,17 +59,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = XTTSService(
             aiohttp_session=session,
-            settings=XTTSService.Settings(
-                voice="Claribel Dervla",
-            ),
+            voice_id="Claribel Dervla",
             base_url="http://localhost:8000",
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -104,7 +100,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -23,7 +23,7 @@ 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.gladia.config import LanguageConfig
+from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
 from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY", ""),
         region=os.getenv("GLADIA_REGION"),
-        settings=GladiaSTTService.Settings(
+        params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],
             ),
@@ -68,19 +68,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY", ""),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY", ""),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
 
-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(
@@ -114,7 +114,7 @@ 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": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -23,7 +23,7 @@ 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.gladia.config import LanguageConfig
+from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
 from pipecat.services.gladia.stt import GladiaSTTService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transcriptions.language import Language
@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY", ""),
         region=os.getenv("GLADIA_REGION"),
-        settings=GladiaSTTService.Settings(
+        params=GladiaInputParams(
             language_config=LanguageConfig(
                 languages=[Language.EN],
             )
@@ -66,19 +66,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY", ""),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
-    llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY", ""),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
-    )
+    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
 
-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -109,7 +109,7 @@ 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": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -54,18 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = LmntTTSService(
-        api_key=os.getenv("LMNT_API_KEY"),
-        settings=LmntTTSService.Settings(
-            voice="morgan",
-        ),
-    )
+    tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -99,7 +92,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -56,10 +56,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = GroqLLMService(
         api_key=os.getenv("GROQ_API_KEY"),
-        settings=GroqLLMService.Settings(
-            model="llama-3.1-8b-instant",
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="meta-llama/llama-4-maverick-17b-128e-instruct",
+        system_instruction="You are a helpful LLM in a WebRTC call. 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.",
     )
 
     tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))
@@ -95,7 +93,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -95,16 +95,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = AWSPollyTTSService(
         region="us-west-2",  # only specific regions support generative TTS
-        settings=AWSPollyTTSService.Settings(
-            voice="Joanna",
-            engine="generative",
-            rate="1.1",
-        ),
+        voice_id="Joanna",
+        params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
     )
 
     # Create Strands agent processor
     try:
-        agent = build_agent(model_id="us.anthropic.claude-sonnet-4-6", max_tokens=8000)
+        agent = build_agent(model_id="us.anthropic.claude-3-5-haiku-20241022-v1:0", max_tokens=8000)
         llm = StrandsAgentsProcessor(agent=agent)
         logger.info("Successfully created Strands agent for NAB customer service coaching")
     except Exception as e:
@@ -152,7 +149,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
                     messages=[
                         {
                             "role": "user",
-                            "content": f"Greet the user and introduce yourself. Don't use emojis.",
+                            "content": f"Greet the user and introduce yourself.",
                         }
                     ],
                     run_llm=True,

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

@@ -54,20 +54,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = AWSPollyTTSService(
         region="us-west-2",  # only specific regions support generative TTS
-        settings=AWSPollyTTSService.Settings(
-            voice="Joanna",
-            engine="generative",
-            rate="1.1",
-        ),
+        voice_id="Joanna",
+        params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
     )
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        settings=AWSBedrockLLMService.Settings(
-            model="us.anthropic.claude-sonnet-4-6",
-            temperature=0.8,
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()

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

@@ -70,27 +70,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
-        settings=GoogleSTTService.Settings(
-            languages=[Language.EN_US],
-        ),
     )
 
     tts = GoogleTTSService(
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
-        settings=GoogleTTSService.Settings(
-            voice="en-US-Chirp3-HD-Charon",
-            language=Language.EN_US,
-        ),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.Settings(
-            model="gemini-2.5-flash-image",
-            # model="gemini-3-pro-image-preview", # A more powerful model, but slower,
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="gemini-2.5-flash-image",
+        # model="gemini-3-pro-image-preview", # A more powerful model, but slower,
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -124,7 +118,7 @@ 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 with a styled introduction
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -54,17 +54,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot with Gemini TTS")
 
     stt = GoogleSTTService(
-        settings=GoogleSTTService.Settings(
-            languages=[Language.EN_US],
-        ),
+        params=GoogleSTTService.InputParams(languages=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
     tts = GeminiTTSService(
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
-        settings=GeminiTTSService.Settings(
-            model="gemini-2.5-flash-tts",
-            voice="Charon",
+        model="gemini-2.5-flash-tts",
+        voice_id="Charon",
+        params=GeminiTTSService.InputParams(
             language=Language.EN_US,
             prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
         ),
@@ -73,8 +71,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
         model="gemini-2.5-flash",
-        settings=GoogleLLMService.Settings(
-            system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
+        system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
 
             IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:
             - [sigh] - Insert a sigh sound
@@ -92,7 +89,6 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             - "The answer is... [long pause] ...42!"
 
             Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.""",
-        ),
     )
 
     context = LLMContext()
@@ -128,7 +124,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # Kick off the conversation
         context.add_message(
             {
-                "role": "user",
+                "role": "system",
                 "content": "You are an AI assistant. You can help with a variety of tasks. Introduce yourself and ask the user what they would like to know.",
             }
         )

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

@@ -54,31 +54,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
-        settings=GoogleSTTService.Settings(
-            languages=[Language.EN_US],
-            # Add model to use a specific model
-            # model="chirp_3",
-        ),
+        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
         location="us",
     )
 
     tts = GoogleHttpTTSService(
-        settings=GoogleHttpTTSService.Settings(
-            voice="en-US-Chirp3-HD-Charon",
-            language=Language.EN_US,
-        ),
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.Settings(
-            model="gemini-2.5-flash",
-            # force a certain amount of thinking if you want it
-            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="gemini-2.5-flash",
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -112,7 +106,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -54,31 +54,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = GoogleSTTService(
-        settings=GoogleSTTService.Settings(
-            languages=[Language.EN_US],
-            # Add model to use a specific model
-            # model="chirp_3",
-        ),
+        params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
         location="us",
     )
 
     tts = GoogleTTSService(
-        settings=GoogleTTSService.Settings(
-            voice="en-US-Chirp3-HD-Charon",
-            language=Language.EN_US,
-        ),
+        voice_id="en-US-Chirp3-HD-Charon",
+        params=GoogleTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.Settings(
-            model="gemini-2.5-flash",
-            # force a certain amount of thinking if you want it
-            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="gemini-2.5-flash",
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -112,7 +106,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -22,6 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.assemblyai.models import AssemblyAIConnectionParams
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
@@ -93,13 +94,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = AssemblyAISTTService(
         api_key=os.getenv("ASSEMBLYAI_API_KEY"),
         vad_force_turn_endpoint=False,  # Use AssemblyAI's built-in turn detection
-        settings=AssemblyAISTTService.Settings(
-            model="u3-rt-pro",
+        connection_params=AssemblyAIConnectionParams(
+            speech_model="u3-rt-pro",
             # Optional: Tune turn detection timing (defaults shown below)
             # min_turn_silence=100,  # Default
             # max_turn_silence=1000,  # Default
             # Optional: Boost accuracy for specific names/terms
-            # keyterms_prompt=["Xiomara", "Saoirse", "Krzystof", "API", "OAuth"],
+            # prompt="Names: Xiomara, Saoirse, Krzystof. Technical terms: API, OAuth.",
             # Optional: Enable speaker diarization
             # speaker_labels=True,
         ),
@@ -107,16 +108,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -153,7 +150,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -59,16 +59,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -102,7 +98,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -84,17 +84,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
     tts = CartesiaTTSService(
-        api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -134,7 +129,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -58,18 +58,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = DeepgramTTSService(
-        api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramTTSService.Settings(
-            voice="aura-helios-en",
-        ),
-    )
+    tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -103,7 +96,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -60,19 +60,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = RimeHttpTTSService(
             api_key=os.getenv("RIME_API_KEY", ""),
-            settings=RimeHttpTTSService.Settings(
-                voice="luna",
-                model="arcana",
-            ),
+            voice_id="luna",
             model="arcana",
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -107,7 +102,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -56,16 +56,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = RimeTTSService(
         api_key=os.getenv("RIME_API_KEY", ""),
-        settings=RimeTTSService.Settings(
-            voice="luna",
-        ),
+        voice_id="luna",
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -99,7 +95,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07r-interruptible-nvidia.py

@@ -56,10 +56,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = NvidiaLLMService(
         api_key=os.getenv("NVIDIA_API_KEY"),
-        settings=NvidiaLLMService.Settings(
-            model="meta/llama-3.3-70b-instruct",
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        model="meta/llama-3.3-70b-instruct",
+        system_instruction="You are a helpful LLM in a WebRTC call. 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.",
     )
 
     tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
@@ -95,7 +93,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -216,24 +216,31 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.Settings(
-            model="gemini-2.5-flash",
-            system_instruction=system_message,
-            # force a certain amount of thinking if you want it
-            # thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
-        ),
+        model="gemini-2.5-flash",
+        # force a certain amount of thinking if you want it
+        # params=GoogleLLMService.InputParams(
+        #     thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
+        # ),
     )
 
     tts = GoogleTTSService(
-        settings=GoogleTTSService.Settings(
-            voice="en-US-Chirp3-HD-Charon",
-            language=Language.EN_US,
-        ),
+        voice_id="en-US-Chirp3-HD-Charon",
         params=GoogleTTSService.InputParams(language=Language.EN_US),
         credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
     )
 
-    context = LLMContext()
+    messages = [
+        {
+            "role": "system",
+            "content": system_message,
+        },
+        {
+            "role": "user",
+            "content": "Start by saying hello.",
+        },
+    ]
+
+    context = LLMContext(messages)
     user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -269,7 +276,7 @@ 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": "Please introduce yourself to the user."})
+        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -57,16 +57,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = FishAudioTTSService(
         api_key=os.getenv("FISH_API_KEY"),
-        settings=FishAudioTTSService.Settings(
-            voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
-        ),
+        model="4ce7e917cedd4bc2bb2e6ff3a46acaa1",  # Barack Obama
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -100,7 +96,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -60,17 +60,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = NeuphonicHttpTTSService(
             api_key=os.getenv("NEUPHONIC_API_KEY"),
-            settings=NeuphonicHttpTTSService.Settings(
-                voice="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-            ),
+            voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -105,7 +101,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -56,16 +56,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = NeuphonicTTSService(
         api_key=os.getenv("NEUPHONIC_API_KEY"),
-        settings=NeuphonicTTSService.Settings(
-            voice="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
-        ),
+        voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb",  # Emily
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -99,7 +95,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -7,7 +7,6 @@
 
 import os
 
-import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
 
@@ -54,70 +53,62 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    async with aiohttp.ClientSession() as session:
-        stt = FalSTTService(
-            api_key=os.getenv("FAL_KEY"),
-            aiohttp_session=session,
-        )
+    stt = FalSTTService(
+        api_key=os.getenv("FAL_KEY"),
+    )
 
-        tts = CartesiaTTSService(
-            api_key=os.getenv("CARTESIA_API_KEY"),
-            settings=CartesiaTTSService.Settings(
-                voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-            ),
-        )
+    tts = CartesiaTTSService(
+        api_key=os.getenv("CARTESIA_API_KEY"),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
+    )
 
-        llm = OpenAILLMService(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
-        )
+    llm = OpenAILLMService(
+        api_key=os.getenv("OPENAI_API_KEY"),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
+    )
 
-        context = LLMContext()
-        user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
-            context,
-            user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
-        )
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(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
-            ]
-        )
+    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,
-        )
+    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_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
+        await task.queue_frames([LLMRunFrame()])
 
-        @transport.event_handler("on_client_disconnected")
-        async def on_client_disconnected(transport, client):
-            logger.info(f"Client disconnected")
-            await task.cancel()
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
 
-        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
 
-        await runner.run(task)
+    await runner.run(task)
 
 
 async def bot(runner_args: RunnerArguments):

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

@@ -44,16 +44,12 @@ async def main():
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
-        ),
+        system_instruction="You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -82,7 +78,7 @@ async def main():
         ),
     )
 
-    context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+    context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
     await task.queue_frames([LLMRunFrame()])
 
     runner = PipelineRunner()

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

@@ -63,16 +63,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             api_key=os.getenv("MINIMAX_API_KEY", ""),
             group_id=os.getenv("MINIMAX_GROUP_ID", ""),
             aiohttp_session=session,
-            settings=MiniMaxHttpTTSService.Settings(
-                language=Language.EN,
-            ),
+            params=MiniMaxHttpTTSService.InputParams(language=Language.EN),
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -107,7 +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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -59,24 +59,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async with aiohttp.ClientSession() as session:
         stt = SarvamSTTService(
             api_key=os.getenv("SARVAM_API_KEY"),
-            settings=SarvamSTTService.Settings(
-                model="saarika:v2.5",
-            ),
+            model="saarika:v2.5",
         )
 
         tts = SarvamHttpTTSService(
             api_key=os.getenv("SARVAM_API_KEY"),
             aiohttp_session=session,
-            settings=SarvamHttpTTSService.Settings(
-                language=Language.EN_IN,
-            ),
+            params=SarvamHttpTTSService.InputParams(language=Language.EN),
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -111,7 +105,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -54,23 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = SarvamSTTService(
         api_key=os.getenv("SARVAM_API_KEY"),
-        settings=SarvamSTTService.Settings(
-            model="saarika:v2.5",
-        ),
+        model="saarika:v2.5",
     )
 
     tts = SarvamTTSService(
         api_key=os.getenv("SARVAM_API_KEY"),
-        settings=SarvamTTSService.Settings(
-            model="bulbul:v2",
-            voice="manisha",
-        ),
+        model="bulbul:v2",
+        voice_id="manisha",
     )
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -103,7 +97,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
         # Optionally, you can wait for 30 seconds and then change the voice.

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

@@ -24,7 +24,7 @@ from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.cartesia.tts import CartesiaTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.soniox.stt import SonioxSTTService
+from pipecat.services.soniox.stt import SonioxInputParams, SonioxSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -53,9 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = SonioxSTTService(
         api_key=os.getenv("SONIOX_API_KEY"),
-        settings=SonioxSTTService.Settings(
-            # Add language hints to use a specific language
-            # Add strict mode to enforce the language hints
+        params=SonioxInputParams(
             language_hints=[Language.EN],
             language_hints_strict=True,
         ),
@@ -63,16 +61,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -105,7 +99,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -58,19 +58,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         tts = InworldHttpTTSService(
             api_key=os.getenv("INWORLD_API_KEY", ""),
             aiohttp_session=session,
-            streaming=True,
-            settings=InworldHttpTTSService.Settings(
-                voice="Ashley",
-                model="inworld-tts-1",
-            ),
+            voice_id="Ashley",
+            model="inworld-tts-1",
             # Set to False for non-streaming mode or True for streaming mode.
+            streaming=True,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
-            ),
+            system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
         )
 
         context = LLMContext()
@@ -112,7 +108,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             logger.info("Client connected")
             # Kick off the conversation.
             context.add_message(
-                {"role": "user", "content": "Please introduce yourself to the user."}
+                {"role": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

examples/foundational/07zb-interruptible-inworld.py

@@ -10,7 +10,8 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, TTSTextFrame
+from pipecat.observers.loggers.debug_log_observer import DebugLogObserver, FrameEndpoint
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -24,6 +25,7 @@ from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.inworld.tts import InworldTTSService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.transports.base_output import BaseOutputTransport
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,18 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = InworldTTSService(
         api_key=os.getenv("INWORLD_API_KEY", ""),
-        settings=InworldTTSService.Settings(
-            voice="Ashley",
-            model="inworld-tts-1",
-            temperature=1.1,
-        ),
+        voice_id="Ashley",
+        model="inworld-tts-1",
+        temperature=1.1,
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
-        ),
+        system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
     )
 
     context = LLMContext()
@@ -92,6 +90,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             enable_metrics=True,
             enable_usage_metrics=True,
         ),
+        observers=[
+            DebugLogObserver(
+                frame_types={
+                    TTSTextFrame: (BaseOutputTransport, FrameEndpoint.SOURCE),
+                }
+            ),
+        ],
         idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
     )
 
@@ -99,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info("Client connected")
         # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -60,17 +60,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
         tts = AsyncAIHttpTTSService(
             api_key=os.getenv("ASYNCAI_API_KEY", ""),
-            settings=AsyncAIHttpTTSService.Settings(
-                voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
-            ),
+            voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
             aiohttp_session=session,
         )
 
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
-            settings=OpenAILLMService.Settings(
-                system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-            ),
+            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
         )
 
         context = LLMContext()
@@ -105,7 +101,7 @@ 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": "system", "content": "Please introduce yourself to the user."}
             )
             await task.queue_frames([LLMRunFrame()])
 

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

@@ -57,16 +57,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = AsyncAITTSService(
         api_key=os.getenv("ASYNCAI_API_KEY", ""),
-        settings=AsyncAITTSService.Settings(
-            voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
-        ),
+        voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -100,7 +96,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

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

@@ -77,16 +77,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -128,7 +124,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         logger.info(f"Client connected")
         await audiobuffer.start_recording()
         # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @audiobuffer.event_handler("on_audio_data")

examples/foundational/07ze-interruptible-hume.py

@@ -59,16 +59,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     tts = HumeTTSService(
         api_key=os.getenv("HUME_API_KEY"),
         # Replace with your Hume voice ID
-        settings=HumeTTSService.Settings(
-            voice="f898a92e-685f-43fa-985b-a46920f0650b",
-        ),
+        voice_id="f898a92e-685f-43fa-985b-a46920f0650b",
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -113,7 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
             "💡 Word timestamps are enabled! Watch the console for TTSTextFrame logs showing each word with its PTS."
         )
         # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zf-interruptible-gradium.py

@@ -55,24 +55,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GradiumSTTService(
         api_key=os.getenv("GRADIUM_API_KEY"),
         api_endpoint_base_url="wss://us.api.gradium.ai/api/speech/asr",
-        settings=GradiumSTTService.Settings(
+        params=GradiumSTTService.InputParams(
             language=Language.EN,
         ),
     )
 
     tts = GradiumTTSService(
         api_key=os.getenv("GRADIUM_API_KEY"),
+        voice_id="YTpq7expH9539ERJ",
         url="wss://us.api.gradium.ai/api/speech/tts",
-        settings=GradiumTTSService.Settings(
-            voice="YTpq7expH9539ERJ",
-        ),
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -106,7 +102,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zg-interruptible-camb.py

@@ -56,16 +56,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CambTTSService(
         api_key=os.getenv("CAMB_API_KEY"),
-        settings=CambTTSService.Settings(
-            model="mars-flash",
-        ),
+        model="mars-flash",
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
-        ),
+        system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
     )
 
     context = LLMContext()
@@ -99,7 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info("Client connected")
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zh-interruptible-hathora.py

@@ -1,17 +1,16 @@
 #
-# Copyright (c) 2024-2026, Daily
+# Copyright (c) 2024–2026, Daily
 #
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-import asyncio
 import os
 
 from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
+from pipecat.frames.frames import LLMRunFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -22,15 +21,17 @@ from pipecat.processors.aggregators.llm_response_universal import (
 )
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.hathora.stt import HathoraSTTService
+from pipecat.services.hathora.tts import HathoraTTSService
 from pipecat.services.openai.llm import OpenAILLMService
-from pipecat.services.piper.tts import PiperTTSService
 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,
@@ -50,36 +51,37 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
-
-    tts = PiperTTSService(
-        settings=PiperTTSService.Settings(
-            voice="en_US-ryan-high",
-        ),
+    stt = HathoraSTTService(
+        model="nvidia-parakeet-tdt-0.6b-v3",
     )
 
+    tts = HathoraTTSService(
+        model="hexgrad-kokoro-82m",
+    )
+
+    # See https://models.hathora.dev/model/qwen3-30b-a3b
     llm = OpenAILLMService(
-        api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        base_url="https://app-362f7ca1-6975-4e18-a605-ab202bf2c315.app.hathora.dev/v1",
+        api_key=os.getenv("HATHORA_API_KEY"),
+        model=None,
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
-    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+    context_aggregator = LLMContextAggregatorPair(
         context,
         user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
     )
 
     pipeline = Pipeline(
         [
-            transport.input(),
+            transport.input(),  # Transport user input
             stt,
-            user_aggregator,
-            llm,
-            tts,
-            transport.output(),
-            assistant_aggregator,
+            context_aggregator.user(),  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            context_aggregator.assistant(),  # Assistant spoken responses
         ]
     )
 
@@ -95,18 +97,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     @transport.event_handler("on_client_connected")
     async def on_client_connected(transport, client):
         logger.info(f"Client connected")
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        # Kick off the conversation.
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
-        # NOTE: Local Piper loads the voice model once at init, so runtime voice
-        # changes are not applied. This update will log an "unhandled settings"
-        # warning. Use PiperHttpTTSService for dynamic voice switching.
-        await asyncio.sleep(10)
-        logger.info('Updating Piper TTS settings: voice="en_US-lessac-medium"')
-        await task.queue_frame(
-            TTSUpdateSettingsFrame(delta=PiperTTSService.Settings(voice="en_US-lessac-medium"))
-        )
-
     @transport.event_handler("on_client_disconnected")
     async def on_client_disconnected(transport, client):
         logger.info(f"Client disconnected")

examples/foundational/07zi-interruptible-piper.py

@@ -54,17 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = PiperTTSService(
-        settings=PiperTTSService.Settings(
-            voice="en_US-ryan-high",
-        ),
-    )
+    tts = PiperTTSService(voice_id="en_US-ryan-high")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -98,7 +92,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zj-interruptible-kokoro.py

@@ -54,17 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
 
-    tts = KokoroTTSService(
-        settings=KokoroTTSService.Settings(
-            voice="af_heart",
-        ),
-    )
+    tts = KokoroTTSService(voice_id="af_heart")
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -98,7 +92,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/07zk-interruptible-resemble.py

@@ -59,16 +59,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = ResembleAITTSService(
         api_key=os.getenv("RESEMBLE_API_KEY"),
-        settings=ResembleAITTSService.Settings(
-            voice=os.getenv("RESEMBLE_VOICE_UUID"),
-        ),
+        voice_id=os.getenv("RESEMBLE_VOICE_UUID"),
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -102,7 +98,7 @@ 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": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/08-custom-frame-processor.py

@@ -95,16 +95,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
     )
 
     context = LLMContext()
@@ -141,7 +137,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     async def on_client_connected(transport, client):
         logger.info(f"Client connected: {client}")
         # Kick off the conversation.
-        context.add_message({"role": "user", "content": "Please introduce yourself to the user."})
+        context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
         await task.queue_frames([LLMRunFrame()])
 
     @transport.event_handler("on_client_disconnected")

examples/foundational/10-wake-phrase.py

@@ -10,7 +10,7 @@ from dotenv import load_dotenv
 from loguru import logger
 
 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import LLMRunFrame
+from pipecat.frames.frames import LLMRunFrame, TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -56,16 +56,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
-        ),
+        system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
     )
 
     hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
@@ -104,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
         # Kick off the conversation.
         context.add_message(
             {
-                "role": "user",
+                "role": "system",
                 "content": "Please introduce yourself. Tell the user they should say 'Hey Robot' before talking to you.",
             }
         )

examples/foundational/11-sound-effects.py

@@ -106,16 +106,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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.",
     )
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     context = LLMContext()

examples/foundational/12-describe-image-openai.py

@@ -53,16 +53,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        settings=OpenAILLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
     )
 
     context = LLMContext()

examples/foundational/12a-describe-image-anthropic.py

@@ -53,16 +53,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = AnthropicLLMService(
         api_key=os.getenv("ANTHROPIC_API_KEY"),
-        settings=AnthropicLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
     )
 
     context = LLMContext()

examples/foundational/12b-describe-image-aws.py

@@ -53,18 +53,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = AWSBedrockLLMService(
         aws_region="us-west-2",
-        settings=AWSBedrockLLMService.Settings(
-            model="us.anthropic.claude-sonnet-4-6",
-            temperature=0.8,
-            system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
-        ),
+        model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+        # Note: usually, prefer providing latency="optimized" param.
+        # Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
+        # which we need for image input.
+        params=AWSBedrockLLMService.InputParams(temperature=0.8),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
     )
 
     context = LLMContext()

examples/foundational/12c-describe-image-gemini-flash.py

@@ -53,16 +53,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     llm = GoogleLLMService(
         api_key=os.getenv("GOOGLE_API_KEY"),
-        settings=GoogleLLMService.Settings(
-            system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
-        ),
+        system_instruction="You are a helpful LLM in a WebRTC call. 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. You are also able to describe images.",
     )
 
     context = LLMContext()

examples/foundational/12d-describe-image-moondream.py

@@ -42,9 +42,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     tts = CartesiaTTSService(
         api_key=os.getenv("CARTESIA_API_KEY"),
-        settings=CartesiaTTSService.Settings(
-            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
-        ),
+        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
     )
 
     vision = MoondreamService()

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

@@ -16,7 +16,7 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService, Language
+from pipecat.services.deepgram.stt import DeepgramSTTService, Language, LiveOptions
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
 from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -49,9 +49,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = DeepgramSTTService(
         api_key=os.getenv("DEEPGRAM_API_KEY"),
-        settings=DeepgramSTTService.Settings(
-            language=Language.EN,
-        ),
+        live_options=LiveOptions(language=Language.EN),
     )
 
     tl = TranscriptionLogger()

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

@@ -50,11 +50,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
         region=os.getenv("GLADIA_REGION"),
-        # settings=GladiaSTTSettings(
-        #     language_config=LanguageConfig(
-        #         languages=[Language.FR],
-        #     ),
-        # ),
+        # live_options=LiveOptions(language=Language.FR),
     )
 
     tl = TranscriptionLogger()

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

@@ -17,6 +17,7 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.gladia.config import (
+    GladiaInputParams,
     LanguageConfig,
     RealtimeProcessingConfig,
     TranslationConfig,
@@ -58,16 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     stt = GladiaSTTService(
         api_key=os.getenv("GLADIA_API_KEY"),
         region=os.getenv("GLADIA_REGION"),
-        settings=GladiaSTTService.Settings(
+        params=GladiaInputParams(
             language_config=LanguageConfig(
-                languages=[Language.EN],
+                languages=[Language.EN],  # Input in English
                 code_switching=False,
             ),
             realtime_processing=RealtimeProcessingConfig(
-                translation=True,
+                translation=True,  # Enable translation
                 translation_config=TranslationConfig(
-                    target_languages=[Language.ES],
-                    model="enhanced",
+                    target_languages=[Language.ES],  # Translate to Spanish
+                    model="enhanced",  # Use the enhanced translation model
                 ),
             ),
         ),

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

@@ -16,6 +16,7 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
+from pipecat.services.assemblyai.models import AssemblyAIConnectionParams
 from pipecat.services.assemblyai.stt import AssemblyAISTTService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -49,8 +50,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     stt = AssemblyAISTTService(
         api_key=os.getenv("ASSEMBLYAI_API_KEY"),
-        settings=AssemblyAISTTService.Settings(
-            model="u3-rt-pro",
+        connection_params=AssemblyAIConnectionParams(
+            speech_model="u3-rt-pro",
         ),
     )
 

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

@@ -77,11 +77,7 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = WhisperSTTServiceMLX(
-        settings=WhisperSTTServiceMLX.Settings(
-            model=MLXModel.LARGE_V3_TURBO.value,
-        ),
-    )
+    stt = WhisperSTTServiceMLX(model=MLXModel.LARGE_V3_TURBO)
 
     tl = TranscriptionLogger()
 

examples/foundational/13g-sambanova-transcription.py

@@ -79,9 +79,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
     stt = SambaNovaSTTService(
-        settings=SambaNovaSTTService.Settings(
-            model="Whisper-Large-v3",
-        ),
+        model="Whisper-Large-v3",
         api_key=os.getenv("SAMBANOVA_API_KEY"),
     )