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

Remove typed-settings migration scaffolding and rename _update_settings_from_typed to _update_settings.

Browse Source 
Now that all services use typed `ServiceSettings` objects, this removes the interim scaffolding that supported both dict-based and typed settings paths in parallel. Specifically: removes old dict-based `_update_settings(settings: Mapping)` methods from base classes, removes `isinstance(self._settings, ServiceSettings)` guards, simplifies `process_frame` branching, and renames `_update_settings_from_typed` to `_update_settings` across all ~30 service implementations. Also renames the no-arg `_update_settings()` helper on realtime services to `_send_session_update()` to avoid collision, adds `from_mapping` overrides on `GoogleLLMSettings` and `AnthropicLLMSettings` for ThinkingConfig dict-to-object conversion, and replaces a broken no-arg `_update_settings()` call in Gemini Live with a TODO.
This commit is contained in:
Paul Kompfner
2026-02-13 14:30:49 -05:00
parent ab92a0e1d7
commit b08548af9d
57 changed files with 291 additions and 407 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/pipecat/frames/frames.py
View File

@@ -2113,13 +2113,13 @@ class TTSStoppedFrame(ControlFrame):
class ServiceUpdateSettingsFrame(ControlFrame):
"""Base frame for updating service settings.
Supports both the legacy ``settings`` dict and the new typed ``update``
object. When both are provided, ``update`` takes precedence.
Supports both a ``settings`` dict (for backward compatibility) and an
``update`` object. When both are provided, ``update`` takes precedence.
Parameters:
settings: Dictionary of setting name to value mappings (legacy).
update: Typed :class:`~pipecat.services.settings.ServiceSettings`
object describing the delta to apply.
update: :class:`~pipecat.services.settings.ServiceSettings` object
describing the delta to apply.
"""
settings: Mapping[str, Any] = field(default_factory=dict)

69
src/pipecat/services/ai_service.py
View File

@@ -10,7 +10,7 @@ Provides the foundation for all AI services in the Pipecat framework, including
model management, settings handling, and frame processing lifecycle methods.
"""
from typing import Any, AsyncGenerator, Dict, Mapping, Set
from typing import Any, AsyncGenerator, Dict, Set
from loguru import logger
@@ -43,7 +43,7 @@ class AIService(FrameProcessor):
"""
super().__init__(**kwargs)
self._model_name: str = ""
self._settings: Dict[str, Any] | ServiceSettings = {}
self._settings: ServiceSettings = ServiceSettings()
self._session_properties: Dict[str, Any] = {}
@property
@@ -97,71 +97,22 @@ class AIService(FrameProcessor):
"""
pass
async def _update_settings(self, settings: Mapping[str, Any]):
from pipecat.services.openai.realtime.events import SessionProperties
async def _update_settings(self, update: ServiceSettings) -> Set[str]:
"""Apply a settings update and return the set of changed field names.
for key, value in settings.items():
logger.debug("Update request for:", key, value)
The update is applied to ``_settings`` and the changed-field set is
returned. The ``model`` field is handled specially: when it changes,
``set_model_name`` is called.
if key in self._settings:
logger.info(f"Updating LLM setting {key} to: [{value}]")
self._settings[key] = value
elif key in SessionProperties.model_fields:
logger.debug("Attempting to update", key, value)
try:
from pipecat.services.openai.realtime.events import TurnDetection
if isinstance(self._session_properties, SessionProperties):
current_properties = self._session_properties
else:
current_properties = SessionProperties(**self._session_properties)
if key == "turn_detection" and isinstance(value, dict):
turn_detection = TurnDetection(**value)
setattr(current_properties, key, turn_detection)
else:
setattr(current_properties, key, value)
validated_properties = SessionProperties.model_validate(
current_properties.model_dump()
)
logger.info(f"Updating LLM setting {key} to: [{value}]")
self._session_properties = validated_properties.model_dump()
except Exception as e:
logger.warning(f"Unexpected error updating session property {key}: {e}")
elif key == "model":
logger.info(f"Updating LLM setting {key} to: [{value}]")
self.set_model_name(value)
else:
logger.warning(f"Unknown setting for {self.name} service: {key}")
async def _update_settings_from_typed(self, update: ServiceSettings) -> Set[str]:
"""Apply a typed settings update and return the set of changed field names.
If ``_settings`` is a :class:`ServiceSettings` object, the update is
applied to it and the changed-field set is returned. The ``model``
field is handled specially: when it changes, ``set_model_name`` is
called.
Services that have been migrated to typed settings should override
this method (calling ``super()``) to react to specific changed fields
(e.g. reconnect on voice change).
Concrete services should override this method (calling ``super()``)
to react to specific changed fields (e.g. reconnect on voice change).
Args:
update: A typed settings delta.
update: A settings delta.
Returns:
Set of field names whose values actually changed.
"""
if not isinstance(self._settings, ServiceSettings):
logger.warning(
f"{self.name}: received typed settings update but _settings "
f"is not a ServiceSettings — falling back to dict-based update"
)
await self._update_settings(update.to_dict())
return set()
changed = self._settings.apply_update(update)
if "model" in changed:

16
src/pipecat/services/anthropic/llm.py
View File

@@ -59,7 +59,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.llm_service import FunctionCallFromLLM, LLMService
from pipecat.services.settings import NOT_GIVEN as _NOT_GIVEN
from pipecat.services.settings import LLMSettings
from pipecat.services.settings import LLMSettings, is_given
from pipecat.utils.tracing.service_decorators import traced_llm
try:
@@ -72,7 +72,7 @@ except ModuleNotFoundError as e:
@dataclass
class AnthropicLLMSettings(LLMSettings):
"""Typed settings for Anthropic LLM services.
"""Settings for Anthropic LLM services.
Parameters:
enable_prompt_caching: Whether to enable prompt caching.
@@ -82,6 +82,18 @@ class AnthropicLLMSettings(LLMSettings):
enable_prompt_caching: Any = field(default_factory=lambda: _NOT_GIVEN)
thinking: Any = field(default_factory=lambda: _NOT_GIVEN)
@classmethod
def from_mapping(cls, settings):
"""Convert a plain dict to settings, coercing thinking dicts.
For backward compatibility, a ``thinking`` value that is a plain dict
is converted to a :class:`AnthropicLLMService.ThinkingConfig`.
"""
instance = super().from_mapping(settings)
if is_given(instance.thinking) and isinstance(instance.thinking, dict):
instance.thinking = AnthropicLLMService.ThinkingConfig(**instance.thinking)
return instance
@dataclass
class AnthropicContextAggregatorPair:

8
src/pipecat/services/assemblyai/stt.py
View File

@@ -56,7 +56,7 @@ except ModuleNotFoundError as e:
@dataclass
class AssemblyAISTTSettings(STTSettings):
"""Typed settings for the AssemblyAI STT service.
"""Settings for the AssemblyAI STT service.
See :class:`AssemblyAIConnectionParams` for detailed parameter descriptions.
@@ -184,8 +184,8 @@ class AssemblyAISTTService(WebsocketSTTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update and reconnect if anything changed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update and reconnect if anything changed.
Any change triggers a WebSocket reconnect since all connection
parameters are encoded in the WebSocket URL.
@@ -196,7 +196,7 @@ class AssemblyAISTTService(WebsocketSTTService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

2
src/pipecat/services/asyncai/tts.py
View File

@@ -76,7 +76,7 @@ def language_to_async_language(language: Language) -> Optional[str]:
@dataclass
class AsyncAITTSSettings(TTSSettings):
"""Typed settings for Async AI TTS services.
"""Settings for Async AI TTS services.
Parameters:
output_container: Audio container format (e.g. "raw").

2
src/pipecat/services/aws/llm.py
View File

@@ -73,7 +73,7 @@ except ModuleNotFoundError as e:
@dataclass
class AWSBedrockLLMSettings(LLMSettings):
"""Typed settings for AWS Bedrock LLM services.
"""Settings for AWS Bedrock LLM services.
Parameters:
latency: Performance mode - "standard" or "optimized".

8
src/pipecat/services/aws/stt.py
View File

@@ -47,7 +47,7 @@ except ModuleNotFoundError as e:
@dataclass
class AWSTranscribeSTTSettings(STTSettings):
"""Typed settings for the AWS Transcribe STT service.
"""Settings for the AWS Transcribe STT service.
Parameters:
sample_rate: Audio sample rate in Hz (8000 or 16000).
@@ -140,13 +140,13 @@ class AWSTranscribeSTTService(WebsocketSTTService):
}
return encoding_map.get(encoding, encoding)
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, reconnecting if needed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, reconnecting if needed.
Any change to connection-relevant settings (model, language, etc.)
triggers a WebSocket reconnect so the new configuration takes effect.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed and self._websocket:
await self._disconnect()

2
src/pipecat/services/aws/tts.py
View File

@@ -125,7 +125,7 @@ def language_to_aws_language(language: Language) -> Optional[str]:
@dataclass
class AWSPollyTTSSettings(TTSSettings):
"""Typed settings for AWS Polly TTS service.
"""Settings for AWS Polly TTS service.
Parameters:
engine: TTS engine to use ('standard', 'neural', etc.).

8
src/pipecat/services/azure/stt.py
View File

@@ -52,7 +52,7 @@ except ModuleNotFoundError as e:
@dataclass
class AzureSTTSettings(STTSettings):
"""Typed settings for the Azure STT service.
"""Settings for the Azure STT service.
Parameters:
region: Azure region for the Speech service.
@@ -123,13 +123,13 @@ class AzureSTTService(STTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, reconfiguring the recognizer if needed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, reconfiguring the recognizer if needed.
When ``language`` changes the ``SpeechConfig`` is updated and the
speech recognizer is restarted so that the new language takes effect.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if "language" in changed:
# Convert Language enum to Azure language code if needed.

2
src/pipecat/services/azure/tts.py
View File

@@ -69,7 +69,7 @@ def sample_rate_to_output_format(sample_rate: int) -> SpeechSynthesisOutputForma
@dataclass
class AzureTTSSettings(TTSSettings):
"""Typed settings for Azure TTS services.
"""Settings for Azure TTS services.
Parameters:
emphasis: Emphasis level for speech ("strong", "moderate", "reduced").

2
src/pipecat/services/camb/tts.py
View File

@@ -137,7 +137,7 @@ def _get_aligned_audio(buffer: bytes) -> tuple[bytes, bytes]:
@dataclass
class CambTTSSettings(TTSSettings):
"""Typed settings for Camb.ai TTS service.
"""Settings for Camb.ai TTS service.
Parameters:
user_instructions: Custom instructions for mars-instruct model only.

8
src/pipecat/services/cartesia/stt.py
View File

@@ -46,7 +46,7 @@ except ModuleNotFoundError as e:
@dataclass
class CartesiaSTTSettings(STTSettings):
"""Typed settings for the Cartesia STT service.
"""Settings for the Cartesia STT service.
Parameters:
encoding: Audio encoding format (e.g. ``"pcm_s16le"``).
@@ -294,8 +294,8 @@ class CartesiaSTTService(WebsocketSTTService):
await self._disconnect_websocket()
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update and reconnect if anything changed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update and reconnect if anything changed.
Args:
update: A :class:`STTSettings` (or ``CartesiaSTTSettings``) delta.
@@ -303,7 +303,7 @@ class CartesiaSTTService(WebsocketSTTService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed:
await self._disconnect()
await self._connect()

2
src/pipecat/services/cartesia/tts.py
View File

@@ -195,7 +195,7 @@ class CartesiaEmotion(str, Enum):
@dataclass
class CartesiaTTSSettings(TTSSettings):
"""Typed settings for Cartesia TTS services.
"""Settings for Cartesia TTS services.
Parameters:
output_container: Audio container format (e.g. "raw").

8
src/pipecat/services/deepgram/stt.py
View File

@@ -49,7 +49,7 @@ except ModuleNotFoundError as e:
@dataclass
class DeepgramSTTSettings(STTSettings):
"""Typed settings for the Deepgram STT service.
"""Settings for the Deepgram STT service.
Parameters:
live_options: Deepgram ``LiveOptions`` for detailed configuration.
@@ -195,8 +195,8 @@ class DeepgramSTTService(STTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, keeping ``live_options`` in sync.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, keeping ``live_options`` in sync.
Top-level ``model`` and ``language`` are the source of truth. When
they are given in *update* their values are propagated into
@@ -213,7 +213,7 @@ class DeepgramSTTService(STTService):
getattr(update, "language", NOT_GIVEN)
)
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

8
src/pipecat/services/deepgram/stt_sagemaker.py
View File

@@ -51,7 +51,7 @@ except ModuleNotFoundError as e:
@dataclass
class DeepgramSageMakerSTTSettings(STTSettings):
"""Typed settings for the Deepgram SageMaker STT service.
"""Settings for the Deepgram SageMaker STT service.
Parameters:
live_options: Deepgram ``LiveOptions`` for detailed configuration.
@@ -163,8 +163,8 @@ class DeepgramSageMakerSTTService(STTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, keeping ``live_options`` in sync.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, keeping ``live_options`` in sync.
Top-level ``model`` and ``language`` are the source of truth. When
they change their values are propagated into ``live_options``.
@@ -178,7 +178,7 @@ class DeepgramSageMakerSTTService(STTService):
getattr(update, "language", NOT_GIVEN)
)
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

2
src/pipecat/services/deepgram/tts.py
View File

@@ -47,7 +47,7 @@ except ModuleNotFoundError as e:
@dataclass
class DeepgramTTSSettings(TTSSettings):
"""Typed settings for Deepgram TTS service.
"""Settings for Deepgram TTS service.
Parameters:
encoding: Audio encoding format (linear16, mulaw, alaw).

16
src/pipecat/services/elevenlabs/stt.py
View File

@@ -171,7 +171,7 @@ def language_to_elevenlabs_language(language: Language) -> Optional[str]:
@dataclass
class ElevenLabsSTTSettings(STTSettings):
"""Typed settings for the ElevenLabs file-based STT service.
"""Settings for the ElevenLabs file-based STT service.
Parameters:
tag_audio_events: Whether to include audio event tags in transcription.
@@ -182,7 +182,7 @@ class ElevenLabsSTTSettings(STTSettings):
@dataclass
class ElevenLabsRealtimeSTTSettings(STTSettings):
"""Typed settings for the ElevenLabs Realtime STT service.
"""Settings for the ElevenLabs Realtime STT service.
See ``ElevenLabsRealtimeSTTService.InputParams`` for detailed descriptions.
@@ -294,8 +294,8 @@ class ElevenLabsSTTService(SegmentedSTTService):
"""
return language_to_elevenlabs_language(language)
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update.
Converts language to ElevenLabs format before applying and keeps
``_model_id`` in sync with the model setting.
@@ -312,7 +312,7 @@ class ElevenLabsSTTService(SegmentedSTTService):
if converted is not None:
update.language = converted
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if "model" in changed:
self._model_id = self._settings.model
@@ -543,8 +543,8 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update and reconnect if anything changed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update and reconnect if anything changed.
Converts language to ElevenLabs format before applying and keeps
``_model_id`` in sync.
@@ -561,7 +561,7 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
if converted is not None:
update.language = converted
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

18
src/pipecat/services/elevenlabs/tts.py
View File

@@ -154,7 +154,7 @@ def build_elevenlabs_voice_settings(
"""Build voice settings dictionary for ElevenLabs based on provided settings.
Args:
settings: Dictionary or typed settings containing voice settings parameters.
settings: Dictionary or settings containing voice settings parameters.
Returns:
Dictionary of voice settings or None if no valid settings are provided.
@@ -186,7 +186,7 @@ class PronunciationDictionaryLocator(BaseModel):
@dataclass
class ElevenLabsTTSSettings(TTSSettings):
"""Typed settings for the ElevenLabs WebSocket TTS service.
"""Settings for the ElevenLabs WebSocket TTS service.
Fields that appear in the WebSocket URL (``voice``, ``model``,
``language``) require a full reconnect when changed. Fields that
@@ -230,7 +230,7 @@ class ElevenLabsTTSSettings(TTSSettings):
@dataclass
class ElevenLabsHttpTTSSettings(TTSSettings):
"""Typed settings for the ElevenLabs HTTP TTS service.
"""Settings for the ElevenLabs HTTP TTS service.
Parameters:
optimize_streaming_latency: Latency optimization level (0-4).
@@ -471,8 +471,8 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
voice_settings[key] = val
return voice_settings or None
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update, reconnecting as needed.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update, reconnecting as needed.
Uses the declarative ``URL_FIELDS`` and ``VOICE_SETTINGS_FIELDS``
sets on :class:`ElevenLabsTTSSettings` to decide whether to
@@ -484,7 +484,7 @@ class ElevenLabsTTSService(AudioContextWordTTSService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed
@@ -958,8 +958,8 @@ class ElevenLabsHttpTTSService(WordTTSService):
def _set_voice_settings(self):
return build_elevenlabs_voice_settings(self._settings)
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and rebuild voice settings.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and rebuild voice settings.
Args:
update: A :class:`TTSSettings` (or ``ElevenLabsHttpTTSSettings``) delta.
@@ -967,7 +967,7 @@ class ElevenLabsHttpTTSService(WordTTSService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed:
self._voice_settings = self._set_voice_settings()
return changed

8
src/pipecat/services/fal/stt.py
View File

@@ -150,7 +150,7 @@ def language_to_fal_language(language: Language) -> Optional[str]:
@dataclass
class FalSTTSettings(STTSettings):
"""Typed settings for the Fal Wizper STT service.
"""Settings for the Fal Wizper STT service.
Parameters:
task: Task to perform ('transcribe' or 'translate'). Defaults to
@@ -251,9 +251,9 @@ class FalSTTService(SegmentedSTTService):
"""
return language_to_fal_language(language)
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, converting language if changed."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, converting language if changed."""
changed = await super()._update_settings(update)
if "language" in changed:
# Convert the Language enum to a Fal language code.

8
src/pipecat/services/fish/tts.py
View File

@@ -49,7 +49,7 @@ FishAudioOutputFormat = Literal["opus", "mp3", "pcm", "wav"]
@dataclass
class FishAudioTTSSettings(TTSSettings):
"""Typed settings for Fish Audio TTS service.
"""Settings for Fish Audio TTS service.
Parameters:
fish_sample_rate: Audio sample rate sent to the API.
@@ -184,8 +184,8 @@ class FishAudioTTSService(InterruptibleTTSService):
"""
return True
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and reconnect if needed.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and reconnect if needed.
Any change to voice or model triggers a WebSocket reconnect.
@@ -195,7 +195,7 @@ class FishAudioTTSService(InterruptibleTTSService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed:
await self._disconnect()
await self._connect()

10
src/pipecat/services/gladia/stt.py
View File

@@ -182,7 +182,7 @@ class _InputParamsDescriptor:
@dataclass
class GladiaSTTSettings(STTSettings):
"""Typed settings for Gladia STT service.
"""Settings for Gladia STT service.
Parameters:
input_params: Gladia ``GladiaInputParams`` for detailed configuration.
@@ -379,19 +379,19 @@ class GladiaSTTService(WebsocketSTTService):
await super().start(frame)
await self._connect()
async def _update_settings_from_typed(self, update: GladiaSTTSettings) -> set[str]:
"""Apply typed settings update.
async def _update_settings(self, update: GladiaSTTSettings) -> set[str]:
"""Apply settings update.
Gladia sessions are fixed at creation time, so any change requires
a full session teardown and reconnect.
Args:
update: A typed settings delta.
update: A settings delta.
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

5
src/pipecat/services/google/gemini_live/llm.py
View File

@@ -604,7 +604,7 @@ class InputParams(BaseModel):
@dataclass
class GeminiLiveLLMSettings(LLMSettings):
"""Typed settings for Gemini Live LLM services.
"""Settings for Gemini Live LLM services.
Parameters:
modalities: Response modalities.
@@ -976,7 +976,8 @@ class GeminiLiveLLMService(LLMService):
# (we have an example that does just that, actually).
await self._create_single_response(frame.messages)
elif isinstance(frame, LLMSetToolsFrame):
await self._update_settings()
# TODO: implement runtime tool updates for Gemini Live.
pass
else:
await self.push_frame(frame, direction)

24
src/pipecat/services/google/llm.py
View File

@@ -58,7 +58,7 @@ from pipecat.services.openai.llm import (
OpenAIAssistantContextAggregator,
OpenAIUserContextAggregator,
)
from pipecat.services.settings import NOT_GIVEN, LLMSettings
from pipecat.services.settings import NOT_GIVEN, LLMSettings, is_given
from pipecat.utils.tracing.service_decorators import traced_llm
# Suppress gRPC fork warnings
@@ -675,7 +675,7 @@ class GoogleLLMContext(OpenAILLMContext):
@dataclass
class GoogleLLMSettings(LLMSettings):
"""Typed settings for Google LLM services.
"""Settings for Google LLM services.
Parameters:
thinking: Thinking configuration.
@@ -683,6 +683,18 @@ class GoogleLLMSettings(LLMSettings):
thinking: Any = field(default_factory=lambda: NOT_GIVEN)
@classmethod
def from_mapping(cls, settings):
"""Convert a plain dict to settings, coercing thinking dicts.
For backward compatibility, a ``thinking`` value that is a plain dict
is converted to a :class:`GoogleLLMService.ThinkingConfig`.
"""
instance = super().from_mapping(settings)
if is_given(instance.thinking) and isinstance(instance.thinking, dict):
instance.thinking = GoogleLLMService.ThinkingConfig(**instance.thinking)
return instance
class GoogleLLMService(LLMService):
"""Google AI (Gemini) LLM service implementation.
@@ -1227,14 +1239,6 @@ class GoogleLLMService(LLMService):
# Do nothing - we're shutting down anyway
pass
async def _update_settings(self, settings):
"""Override to handle ThinkingConfig validation."""
# Convert thinking dict to ThinkingConfig if needed
if "thinking" in settings and isinstance(settings["thinking"], dict):
settings = dict(settings) # Make a copy to avoid modifying the original
settings["thinking"] = self.ThinkingConfig(**settings["thinking"])
await super()._update_settings(settings)
def create_context_aggregator(
self,
context: OpenAILLMContext,

16
src/pipecat/services/google/stt.py
View File

@@ -360,7 +360,7 @@ def language_to_google_stt_language(language: Language) -> Optional[str]:
@dataclass
class GoogleSTTSettings(STTSettings):
"""Typed settings for Google Cloud Speech-to-Text V2.
"""Settings for Google Cloud Speech-to-Text V2.
Parameters:
languages: List of ``Language`` enums for recognition
@@ -628,10 +628,10 @@ class GoogleSTTService(STTService):
DeprecationWarning,
)
logger.debug(f"Switching STT languages to: {languages}")
await self._update_settings_from_typed(GoogleSTTSettings(languages=list(languages)))
await self._update_settings(GoogleSTTSettings(languages=list(languages)))
async def _update_settings_from_typed(self, update: GoogleSTTSettings) -> set[str]:
"""Apply typed settings update and reconnect if anything changed.
async def _update_settings(self, update: GoogleSTTSettings) -> set[str]:
"""Apply settings update and reconnect if anything changed.
Handles ``language`` from base ``set_language`` by converting it to
``languages``. Emits a deprecation warning if ``language_codes`` is
@@ -639,7 +639,7 @@ class GoogleSTTService(STTService):
Reconnects the stream on any change.
Args:
update: A typed settings delta.
update: A settings delta.
Returns:
Set of field names whose values actually changed.
@@ -663,7 +663,7 @@ class GoogleSTTService(STTService):
stacklevel=2,
)
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed:
await self._reconnect_if_needed()
@@ -742,7 +742,7 @@ class GoogleSTTService(STTService):
"GoogleSTTSettings(...) instead.",
DeprecationWarning,
)
# Build a typed settings delta from the provided options
# Build a settings delta from the provided options
update = GoogleSTTSettings()
if languages is not None:
@@ -770,7 +770,7 @@ class GoogleSTTService(STTService):
logger.debug(f"Updating location to: {location}")
self._location = location
await self._update_settings_from_typed(update)
await self._update_settings(update)
async def _connect(self):
"""Initialize streaming recognition config and stream."""

26
src/pipecat/services/google/tts.py
View File

@@ -478,7 +478,7 @@ def language_to_gemini_tts_language(language: Language) -> Optional[str]:
@dataclass
class GoogleHttpTTSSettings(TTSSettings):
"""Typed settings for Google HTTP TTS service.
"""Settings for Google HTTP TTS service.
Parameters:
pitch: Voice pitch adjustment (e.g., "+2st", "-50%").
@@ -505,7 +505,7 @@ class GoogleHttpTTSSettings(TTSSettings):
@dataclass
class GoogleStreamTTSSettings(TTSSettings):
"""Typed settings for Google streaming TTS service.
"""Settings for Google streaming TTS service.
Parameters:
language: Language for synthesis. Defaults to English.
@@ -518,7 +518,7 @@ class GoogleStreamTTSSettings(TTSSettings):
@dataclass
class GeminiTTSSettings(TTSSettings):
"""Typed settings for Gemini TTS service.
"""Settings for Gemini TTS service.
Parameters:
language: Language for synthesis. Defaults to English.
@@ -680,11 +680,11 @@ class GoogleHttpTTSService(TTSService):
"""
return language_to_google_tts_language(language)
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Override to handle speaking_rate validation.
Args:
update: Typed settings delta. Can include 'speaking_rate' (float).
update: Settings delta. Can include 'speaking_rate' (float).
"""
if isinstance(update, GoogleHttpTTSSettings) and is_given(update.speaking_rate):
rate_value = float(update.speaking_rate)
@@ -693,7 +693,7 @@ class GoogleHttpTTSService(TTSService):
f"Invalid speaking_rate value: {rate_value}. Must be between 0.25 and 2.0"
)
update.speaking_rate = NOT_GIVEN
return await super()._update_settings_from_typed(update)
return await super()._update_settings(update)
def _construct_ssml(self, text: str) -> str:
ssml = "<speak>"
@@ -1024,11 +1024,11 @@ class GoogleTTSService(GoogleBaseTTSService):
credentials, credentials_path
)
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Override to handle speaking_rate validation.
Args:
update: Typed settings delta. Can include 'speaking_rate' (float).
update: Settings delta. Can include 'speaking_rate' (float).
"""
if isinstance(update, GoogleStreamTTSSettings) and is_given(update.speaking_rate):
rate_value = float(update.speaking_rate)
@@ -1037,7 +1037,7 @@ class GoogleTTSService(GoogleBaseTTSService):
f"Invalid speaking_rate value: {rate_value}. Must be between 0.25 and 2.0"
)
update.speaking_rate = NOT_GIVEN
return await super()._update_settings_from_typed(update)
return await super()._update_settings(update)
@traced_tts
async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:
@@ -1259,11 +1259,11 @@ class GeminiTTSService(GoogleBaseTTSService):
f"Current rate of {self.sample_rate}Hz may cause issues."
)
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update with voice validation.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update with voice validation.
Args:
update: Typed settings delta. Can include 'voice', 'prompt', etc.
update: Settings delta. Can include 'voice', 'prompt', etc.
Returns:
Set of field names whose values actually changed.
@@ -1271,7 +1271,7 @@ class GeminiTTSService(GoogleBaseTTSService):
if is_given(update.voice) and update.voice not in self.AVAILABLE_VOICES:
logger.warning(f"Voice '{update.voice}' not in known voices list. Using anyway.")
return await super()._update_settings_from_typed(update)
return await super()._update_settings(update)
@traced_tts
async def run_tts(self, text: str, context_id: str) -> AsyncGenerator[Frame, None]:

8
src/pipecat/services/gradium/stt.py
View File

@@ -68,7 +68,7 @@ def language_to_gradium_language(language: Language) -> Optional[str]:
@dataclass
class GradiumSTTSettings(STTSettings):
"""Typed settings for the Gradium STT service.
"""Settings for the Gradium STT service.
Parameters:
delay_in_frames: Delay in audio frames (80ms each) before text is
@@ -171,8 +171,8 @@ class GradiumSTTService(WebsocketSTTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, sync params, and reconnect.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, sync params, and reconnect.
Args:
update: A :class:`STTSettings` (or ``GradiumSTTSettings``) delta.
@@ -180,7 +180,7 @@ class GradiumSTTService(WebsocketSTTService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

8
src/pipecat/services/gradium/tts.py
View File

@@ -41,7 +41,7 @@ SAMPLE_RATE = 48000
@dataclass
class GradiumTTSSettings(TTSSettings):
"""Typed settings for the Gradium TTS service.
"""Settings for the Gradium TTS service.
Parameters:
output_format: Audio output format.
@@ -119,8 +119,8 @@ class GradiumTTSService(InterruptibleWordTTSService):
"""
return True
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and reconnect if voice changed.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and reconnect if voice changed.
Args:
update: A :class:`TTSSettings` (or ``GradiumTTSSettings``) delta.
@@ -129,7 +129,7 @@ class GradiumTTSService(InterruptibleWordTTSService):
Set of field names whose values actually changed.
"""
prev_voice = self._voice_id
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if self._voice_id != prev_voice:
await self._disconnect()
await self._connect()

28
src/pipecat/services/grok/realtime/llm.py
View File

@@ -88,7 +88,7 @@ class CurrentAudioResponse:
@dataclass
class GrokRealtimeLLMSettings(LLMSettings):
"""Typed settings for Grok Realtime LLM services.
"""Settings for Grok Realtime LLM services.
Parameters:
session_properties: Grok Realtime session configuration.
@@ -349,13 +349,13 @@ class GrokRealtimeLLMService(LLMService):
frame: The frame to process.
direction: The direction of frame flow in the pipeline.
"""
# Legacy dict path: frame.settings contains SessionProperties fields,
# not our Settings fields, so we construct SessionProperties directly.
# The new typed path (frame.update) falls through to super, which calls
# _update_settings_from_typed → our override handles the rest.
# Backward-compatible dict path: frame.settings contains SessionProperties
# fields, not our Settings fields, so we construct SessionProperties
# directly. The frame.update path falls through to super, which calls
# _update_settings → our override handles the rest.
if isinstance(frame, LLMUpdateSettingsFrame) and frame.update is None:
self._settings.session_properties = events.SessionProperties(**frame.settings)
await self._update_settings()
await self._send_session_update()
await self.push_frame(frame, direction)
return
@@ -379,7 +379,7 @@ class GrokRealtimeLLMService(LLMService):
elif isinstance(frame, LLMMessagesAppendFrame):
await self._handle_messages_append(frame)
elif isinstance(frame, LLMSetToolsFrame):
await self._update_settings()
await self._send_session_update()
await self.push_frame(frame, direction)
@@ -456,14 +456,14 @@ class GrokRealtimeLLMService(LLMService):
return
await self.push_error(error_msg=f"Error sending client event: {e}", exception=e)
async def _update_settings_from_typed(self, update):
"""Apply a typed settings update, sending a session update if needed."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update):
"""Apply a settings update, sending a session update if needed."""
changed = await super()._update_settings(update)
if "session_properties" in changed:
await self._update_settings()
await self._send_session_update()
return changed
async def _update_settings(self):
async def _send_session_update(self):
"""Update session settings on the server."""
settings = self._settings.session_properties
adapter: GrokRealtimeLLMAdapter = self.get_llm_adapter()
@@ -543,7 +543,7 @@ class GrokRealtimeLLMService(LLMService):
async def _handle_evt_conversation_created(self, evt):
"""Handle conversation.created event - first event after connecting."""
await self._update_settings()
await self._send_session_update()
async def _handle_evt_response_created(self, evt):
"""Handle response.created event - response generation started."""
@@ -746,7 +746,7 @@ class GrokRealtimeLLMService(LLMService):
self._messages_added_manually[evt.item.id] = True
await self.send_client_event(evt)
await self._update_settings()
await self._send_session_update()
self._llm_needs_conversation_setup = False
logger.debug("Creating Grok response")

2
src/pipecat/services/groq/tts.py
View File

@@ -36,7 +36,7 @@ except ModuleNotFoundError as e:
@dataclass
class GroqTTSSettings(TTSSettings):
"""Typed settings for the Groq TTS service.
"""Settings for the Groq TTS service.
Parameters:
output_format: Audio output format.

2
src/pipecat/services/hathora/stt.py
View File

@@ -31,7 +31,7 @@ from .utils import ConfigOption
@dataclass
class HathoraSTTSettings(STTSettings):
"""Typed settings for the Hathora STT service.
"""Settings for the Hathora STT service.
Parameters:
config: Some models support additional config, refer to

2
src/pipecat/services/hathora/tts.py
View File

@@ -49,7 +49,7 @@ def _decode_audio_payload(
@dataclass
class HathoraTTSSettings(TTSSettings):
"""Typed settings for Hathora TTS service.
"""Settings for Hathora TTS service.
Parameters:
speed: Speech speed multiplier (if supported by model).

2
src/pipecat/services/inworld/tts.py
View File

@@ -52,7 +52,7 @@ from pipecat.utils.tracing.service_decorators import traced_tts
@dataclass
class InworldTTSSettings(TTSSettings):
"""Typed settings for Inworld TTS services.
"""Settings for Inworld TTS services.
Parameters:
audio_encoding: Audio encoding format (e.g. LINEAR16).

2
src/pipecat/services/kokoro/tts.py
View File

@@ -91,7 +91,7 @@ def language_to_kokoro_language(language: Language) -> str:
@dataclass
class KokoroTTSSettings(TTSSettings):
"""Typed settings for the Kokoro TTS service.
"""Settings for the Kokoro TTS service.
Parameters:
lang_code: Kokoro language code for synthesis.

51
src/pipecat/services/llm_service.py
View File

@@ -59,7 +59,7 @@ from pipecat.processors.aggregators.llm_response import (
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_service import AIService
from pipecat.services.settings import LLMSettings, ServiceSettings, is_given
from pipecat.services.settings import LLMSettings, is_given
from pipecat.turns.user_turn_completion_mixin import UserTurnCompletionLLMServiceMixin
from pipecat.utils.context.llm_context_summarization import (
LLMContextSummarizationUtil,
@@ -313,16 +313,16 @@ class LLMService(UserTurnCompletionLLMServiceMixin, AIService):
await self._cancel_sequential_runner_task()
await self._cancel_summary_task()
async def _update_settings_from_typed(self, update: LLMSettings) -> set[str]:
"""Apply a typed settings update, handling turn-completion fields.
async def _update_settings(self, update: LLMSettings) -> set[str]:
"""Apply a settings update, handling turn-completion fields.
Args:
update: A typed LLM settings delta.
update: An LLM settings delta.
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if "filter_incomplete_user_turns" in changed:
self._filter_incomplete_user_turns = self._settings.filter_incomplete_user_turns
@@ -336,35 +336,6 @@ class LLMService(UserTurnCompletionLLMServiceMixin, AIService):
return changed
async def _update_settings(self, settings: Mapping[str, Any]):
"""Update LLM service settings.
Handles turn completion settings specially since they are not model
parameters and should not be passed to the underlying LLM API.
Args:
settings: Dictionary of settings to update.
"""
# Turn completion settings to extract (not model parameters)
turn_completion_keys = {"filter_incomplete_user_turns", "user_turn_completion_config"}
# Handle turn completion settings
if "filter_incomplete_user_turns" in settings:
self._filter_incomplete_user_turns = settings["filter_incomplete_user_turns"]
logger.info(
f"{self}: Incomplete turn filtering {'enabled' if self._filter_incomplete_user_turns else 'disabled'}"
)
# Configure the mixin with config object
if self._filter_incomplete_user_turns and "user_turn_completion_config" in settings:
self.set_user_turn_completion_config(settings["user_turn_completion_config"])
# Remove turn completion settings before passing to parent
settings = {k: v for k, v in settings.items() if k not in turn_completion_keys}
# Let the parent handle remaining model parameters
await super()._update_settings(settings)
async def process_frame(self, frame: Frame, direction: FrameDirection):
"""Process a frame.
@@ -379,16 +350,12 @@ class LLMService(UserTurnCompletionLLMServiceMixin, AIService):
elif isinstance(frame, LLMConfigureOutputFrame):
self._skip_tts = frame.skip_tts
elif isinstance(frame, LLMUpdateSettingsFrame):
# New path: typed settings update object.
if frame.update is not None:
await self._update_settings_from_typed(frame.update)
# Legacy path: plain dict, but service uses typed settings — convert.
elif isinstance(self._settings, ServiceSettings):
await self._update_settings(frame.update)
elif frame.settings:
# Backward-compatible path: convert legacy dict to settings object.
update = type(self._settings).from_mapping(frame.settings)
await self._update_settings_from_typed(update)
# Legacy path: plain dict, service still uses dict-based settings.
else:
await self._update_settings(frame.settings)
await self._update_settings(update)
elif isinstance(frame, LLMContextSummaryRequestFrame):
await self._handle_summary_request(frame)

2
src/pipecat/services/lmnt/tts.py
View File

@@ -75,7 +75,7 @@ def language_to_lmnt_language(language: Language) -> Optional[str]:
@dataclass
class LmntTTSSettings(TTSSettings):
"""Typed settings for LMNT TTS service.
"""Settings for LMNT TTS service.
Parameters:
format: Audio output format. Defaults to "raw".

2
src/pipecat/services/minimax/tts.py
View File

@@ -89,7 +89,7 @@ def language_to_minimax_language(language: Language) -> Optional[str]:
@dataclass
class MiniMaxTTSSettings(TTSSettings):
"""Typed settings for MiniMax TTS service.
"""Settings for MiniMax TTS service.
Parameters:
stream: Whether to use streaming mode.

8
src/pipecat/services/neuphonic/tts.py
View File

@@ -76,7 +76,7 @@ def language_to_neuphonic_lang_code(language: Language) -> Optional[str]:
@dataclass
class NeuphonicTTSSettings(TTSSettings):
"""Typed settings for Neuphonic TTS service.
"""Settings for Neuphonic TTS service.
Parameters:
lang_code: Neuphonic language code.
@@ -181,9 +181,9 @@ class NeuphonicTTSService(InterruptibleTTSService):
"""
return language_to_neuphonic_lang_code(language)
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and reconnect with new configuration."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and reconnect with new configuration."""
changed = await super()._update_settings(update)
if changed:
await self._disconnect()
await self._connect()

10
src/pipecat/services/nvidia/stt.py
View File

@@ -93,14 +93,14 @@ def language_to_nvidia_riva_language(language: Language) -> Optional[str]:
@dataclass
class NvidiaSTTSettings(STTSettings):
"""Typed settings for the NVIDIA Riva streaming STT service."""
"""Settings for the NVIDIA Riva streaming STT service."""
pass
@dataclass
class NvidiaSegmentedSTTSettings(STTSettings):
"""Typed settings for the NVIDIA Riva segmented STT service.
"""Settings for the NVIDIA Riva segmented STT service.
Parameters:
profanity_filter: Whether to filter profanity from results.
@@ -579,8 +579,8 @@ class NvidiaSegmentedSTTService(SegmentedSTTService):
self._config = self._create_recognition_config()
logger.debug(f"Initialized NvidiaSegmentedSTTService with model: {self.model_name}")
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update and sync internal state.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update and sync internal state.
Args:
update: A :class:`STTSettings` (or ``NvidiaSegmentedSTTSettings``) delta.
@@ -588,7 +588,7 @@ class NvidiaSegmentedSTTService(SegmentedSTTService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if changed:
self._config = self._create_recognition_config()

2
src/pipecat/services/openai/base_llm.py
View File

@@ -49,7 +49,7 @@ from pipecat.utils.tracing.service_decorators import traced_llm
@dataclass
class OpenAILLMSettings(LLMSettings):
"""Typed settings for OpenAI-compatible LLM services.
"""Settings for OpenAI-compatible LLM services.
Parameters:
max_completion_tokens: Maximum completion tokens to generate.

28
src/pipecat/services/openai/realtime/llm.py
View File

@@ -93,7 +93,7 @@ class CurrentAudioResponse:
@dataclass
class OpenAIRealtimeLLMSettings(LLMSettings):
"""Typed settings for OpenAI Realtime LLM services.
"""Settings for OpenAI Realtime LLM services.
Parameters:
session_properties: OpenAI Realtime session configuration.
@@ -411,13 +411,13 @@ class OpenAIRealtimeLLMService(LLMService):
frame: The frame to process.
direction: The direction of frame flow in the pipeline.
"""
# Legacy dict path: frame.settings contains SessionProperties fields,
# not our Settings fields, so we construct SessionProperties directly.
# The new typed path (frame.update) falls through to super, which calls
# _update_settings_from_typed → our override handles the rest.
# Backward-compatible dict path: frame.settings contains SessionProperties
# fields, not our Settings fields, so we construct SessionProperties
# directly. The frame.update path falls through to super, which calls
# _update_settings → our override handles the rest.
if isinstance(frame, LLMUpdateSettingsFrame) and frame.update is None:
self._settings.session_properties = events.SessionProperties(**frame.settings)
await self._update_settings()
await self._send_session_update()
await self.push_frame(frame, direction)
return
@@ -449,7 +449,7 @@ class OpenAIRealtimeLLMService(LLMService):
elif isinstance(frame, LLMMessagesAppendFrame):
await self._handle_messages_append(frame)
elif isinstance(frame, LLMSetToolsFrame):
await self._update_settings()
await self._send_session_update()
await self.push_frame(frame, direction)
@@ -534,14 +534,14 @@ class OpenAIRealtimeLLMService(LLMService):
# treat a send-side error as fatal.
await self.push_error(error_msg=f"Error sending client event: {e}", exception=e)
async def _update_settings_from_typed(self, update):
"""Apply a typed settings update, sending a session update if needed."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update):
"""Apply a settings update, sending a session update if needed."""
changed = await super()._update_settings(update)
if "session_properties" in changed:
await self._update_settings()
await self._send_session_update()
return changed
async def _update_settings(self):
async def _send_session_update(self):
settings = self._settings.session_properties
adapter: OpenAIRealtimeLLMAdapter = self.get_llm_adapter()
@@ -613,7 +613,7 @@ class OpenAIRealtimeLLMService(LLMService):
async def _handle_evt_session_created(self, evt):
# session.created is received right after connecting. Send a message
# to configure the session properties.
await self._update_settings()
await self._send_session_update()
async def _handle_evt_session_updated(self, evt):
# If this is our first context frame, run the LLM
@@ -896,7 +896,7 @@ class OpenAIRealtimeLLMService(LLMService):
await self.send_client_event(evt)
# Send new settings if needed
await self._update_settings()
await self._send_session_update()
# We're done configuring the LLM for this session
self._llm_needs_conversation_setup = False

10
src/pipecat/services/openai/stt.py
View File

@@ -127,7 +127,7 @@ _OPENAI_SAMPLE_RATE = 24000
@dataclass
class OpenAIRealtimeSTTSettings(STTSettings):
"""Typed settings for the OpenAI Realtime STT service.
"""Settings for the OpenAI Realtime STT service.
Parameters:
prompt: Optional prompt text to guide transcription style.
@@ -268,10 +268,10 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
"""
return True
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update and send session update if needed.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update and send session update if needed.
Keeps ``_language_code`` and ``_prompt`` in sync with typed settings
Keeps ``_language_code`` and ``_prompt`` in sync with settings
and sends a ``session.update`` to the server when the session is active.
Args:
@@ -280,7 +280,7 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

2
src/pipecat/services/openai/tts.py
View File

@@ -64,7 +64,7 @@ VALID_VOICES: Dict[str, ValidVoice] = {
@dataclass
class OpenAITTSSettings(TTSSettings):
"""Typed settings for OpenAI TTS service.
"""Settings for OpenAI TTS service.
Parameters:
instructions: Instructions to guide voice synthesis behavior.

28
src/pipecat/services/openai_realtime_beta/openai.py
View File

@@ -94,7 +94,7 @@ class CurrentAudioResponse:
@dataclass
class OpenAIRealtimeBetaLLMSettings(LLMSettings):
"""Typed settings for OpenAI Realtime Beta LLM services.
"""Settings for OpenAI Realtime Beta LLM services.
Parameters:
session_properties: OpenAI Realtime session configuration.
@@ -357,13 +357,13 @@ class OpenAIRealtimeBetaLLMService(LLMService):
frame: The frame to process.
direction: The direction of frame flow in the pipeline.
"""
# Legacy dict path: frame.settings contains SessionProperties fields,
# not our Settings fields, so we construct SessionProperties directly.
# The new typed path (frame.update) falls through to super, which calls
# _update_settings_from_typed → our override handles the rest.
# Backward-compatible dict path: frame.settings contains SessionProperties
# fields, not our Settings fields, so we construct SessionProperties
# directly. The frame.update path falls through to super, which calls
# _update_settings → our override handles the rest.
if isinstance(frame, LLMUpdateSettingsFrame) and frame.update is None:
self._settings.session_properties = events.SessionProperties(**frame.settings)
await self._update_settings()
await self._send_session_update()
await self.push_frame(frame, direction)
return
@@ -403,7 +403,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
elif isinstance(frame, RealtimeMessagesUpdateFrame):
self._context = frame.context
elif isinstance(frame, LLMSetToolsFrame):
await self._update_settings()
await self._send_session_update()
elif isinstance(frame, RealtimeFunctionCallResultFrame):
await self._handle_function_call_result(frame.result_frame)
@@ -478,14 +478,14 @@ class OpenAIRealtimeBetaLLMService(LLMService):
# treat a send-side error as fatal.
await self.push_error(error_msg=f"Error sending client event: {e}", exception=e)
async def _update_settings_from_typed(self, update):
"""Apply a typed settings update, sending a session update if needed."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update):
"""Apply a settings update, sending a session update if needed."""
changed = await super()._update_settings(update)
if "session_properties" in changed:
await self._update_settings()
await self._send_session_update()
return changed
async def _update_settings(self):
async def _send_session_update(self):
settings = self._settings.session_properties
# tools given in the context override the tools in the session properties
if self._context and self._context.tools:
@@ -540,7 +540,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
async def _handle_evt_session_created(self, evt):
# session.created is received right after connecting. Send a message
# to configure the session properties.
await self._update_settings()
await self._send_session_update()
async def _handle_evt_session_updated(self, evt):
# If this is our first context frame, run the LLM
@@ -779,7 +779,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
self._context.llm_needs_initial_messages = False
if self._context.llm_needs_settings_update:
await self._update_settings()
await self._send_session_update()
self._context.llm_needs_settings_update = False
logger.debug(f"Creating response: {self._context.get_messages_for_logging()}")

2
src/pipecat/services/playht/tts.py
View File

@@ -101,7 +101,7 @@ def language_to_playht_language(language: Language) -> Optional[str]:
@dataclass
class PlayHTTTSSettings(TTSSettings):
"""Typed settings for PlayHT TTS services.
"""Settings for PlayHT TTS services.
Parameters:
output_format: Audio output format.

2
src/pipecat/services/resembleai/tts.py
View File

@@ -42,7 +42,7 @@ except ModuleNotFoundError as e:
@dataclass
class ResembleAITTSSettings(TTSSettings):
"""Typed settings for Resemble AI TTS service.
"""Settings for Resemble AI TTS service.
Parameters:
precision: PCM bit depth (PCM_32, PCM_24, PCM_16, or MULAW).

16
src/pipecat/services/rime/tts.py
View File

@@ -72,7 +72,7 @@ def language_to_rime_language(language: Language) -> str:
@dataclass
class RimeTTSSettings(TTSSettings):
"""Typed settings for Rime WS JSON and HTTP TTS services.
"""Settings for Rime WS JSON and HTTP TTS services.
Parameters:
speaker: Voice speaker ID.
@@ -101,7 +101,7 @@ class RimeTTSSettings(TTSSettings):
@dataclass
class RimeNonJsonTTSSettings(TTSSettings):
"""Typed settings for Rime non-JSON WS TTS service.
"""Settings for Rime non-JSON WS TTS service.
Parameters:
speaker: Voice speaker ID.
@@ -271,10 +271,10 @@ class RimeTTSService(AudioContextWordTTSService):
self._extra_msg_fields["inlineSpeedAlpha"] = ",".join(speed_vals + [str(speed)])
return f"[{text}]"
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and reconnect if voice changed."""
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and reconnect if voice changed."""
prev_voice = self._voice_id
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if "voice" in changed:
self._settings.speaker = self._voice_id
await self._disconnect()
@@ -975,13 +975,13 @@ class RimeNonJsonTTSService(InterruptibleTTSService):
except Exception as e:
yield ErrorFrame(error=f"Unknown error occurred: {e}")
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and reconnect if necessary.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and reconnect if necessary.
Since all settings are WebSocket URL query parameters,
any setting change requires reconnecting to apply the new values.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
# Sync voice and model to settings dict fields
if "voice" in changed:

8
src/pipecat/services/sarvam/stt.py
View File

@@ -133,7 +133,7 @@ MODEL_CONFIGS: Dict[str, ModelConfig] = {
@dataclass
class SarvamSTTSettings(STTSettings):
"""Typed settings for the Sarvam STT service.
"""Settings for the Sarvam STT service.
Parameters:
prompt: Optional prompt to guide transcription/translation style.
@@ -306,8 +306,8 @@ class SarvamSTTService(STTService):
if self._socket_client:
await self._socket_client.flush()
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, validate, sync state, and reconnect.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, validate, sync state, and reconnect.
Args:
update: A :class:`STTSettings` (or ``SarvamSTTSettings``) delta.
@@ -336,7 +336,7 @@ class SarvamSTTService(STTService):
if not self._config.supports_mode:
raise ValueError(f"Model '{self.model_name}' does not support mode parameter.")
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

10
src/pipecat/services/sarvam/tts.py
View File

@@ -247,7 +247,7 @@ def language_to_sarvam_language(language: Language) -> Optional[str]:
@dataclass
class SarvamHttpTTSSettings(TTSSettings):
"""Typed settings for Sarvam HTTP TTS service.
"""Settings for Sarvam HTTP TTS service.
Parameters:
language: Sarvam language code.
@@ -277,7 +277,7 @@ class SarvamHttpTTSSettings(TTSSettings):
@dataclass
class SarvamWSTTSSettings(TTSSettings):
"""Typed settings for Sarvam WebSocket TTS service.
"""Settings for Sarvam WebSocket TTS service.
Parameters:
target_language_code: Sarvam language code.
@@ -953,9 +953,9 @@ class SarvamTTSService(InterruptibleTTSService):
if isinstance(frame, (LLMFullResponseEndFrame, EndFrame)):
await self.flush_audio()
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed settings update and resend config if voice changed."""
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a settings update and resend config if voice changed."""
changed = await super()._update_settings(update)
if "voice" in changed:
await self._send_config()
return changed

26
src/pipecat/services/settings.py
View File

@@ -4,13 +4,12 @@
# SPDX-License-Identifier: BSD 2-Clause License
#
"""Typed settings infrastructure for Pipecat AI services.
"""Settings infrastructure for Pipecat AI services.
This module provides typed dataclass-based settings objects that replace the
stringly-typed ``Mapping[str, Any]`` dictionaries previously used for service
configuration. Each service type has a corresponding settings class (e.g.
``TTSSettings``, ``LLMSettings``) whose fields use the ``NOT_GIVEN`` sentinel
to distinguish "leave unchanged" from an explicit ``None``.
This module provides dataclass-based settings objects for service configuration.
Each service type has a corresponding settings class (e.g. ``TTSSettings``,
``LLMSettings``) whose fields use the ``NOT_GIVEN`` sentinel to distinguish
"leave unchanged" from an explicit ``None``.
Key concepts:
@@ -21,7 +20,7 @@ Key concepts:
``NOT_GIVEN`` are simply skipped when applying an update.
- **apply_update**: Applies a delta onto a target settings object and returns
the set of field names that actually changed.
- **from_mapping**: Constructs a typed settings object from a plain dict,
- **from_mapping**: Constructs a settings object from a plain dict,
supporting field aliases (e.g. ``"voice_id"`` → ``"voice"``).
- **Extras**: Unknown keys land in the ``extra`` dict so services that have
non-standard settings don't lose data.
@@ -91,7 +90,7 @@ _S = TypeVar("_S", bound="ServiceSettings")
@dataclass
class ServiceSettings:
"""Base class for typed service settings.
"""Base class for service settings.
Every AI service type (LLM, TTS, STT) extends this with its own fields.
Fields default to ``NOT_GIVEN`` so that an instance can represent either
@@ -188,7 +187,10 @@ class ServiceSettings:
@classmethod
def from_mapping(cls: Type[_S], settings: Mapping[str, Any]) -> _S:
"""Construct a typed settings object from a plain dictionary.
"""Construct a settings object from a plain dictionary.
This exists for backward compatibility with code that passes plain
dicts via ``*UpdateSettingsFrame(settings={...})``.
Keys are matched to dataclass fields by name. Keys listed in
``_aliases`` are translated to their canonical name first. Any
@@ -250,7 +252,7 @@ class ServiceSettings:
@dataclass
class LLMSettings(ServiceSettings):
"""Typed settings for LLM services.
"""Settings for LLM services.
Parameters:
model: LLM model identifier.
@@ -285,7 +287,7 @@ class LLMSettings(ServiceSettings):
@dataclass
class TTSSettings(ServiceSettings):
"""Typed settings for TTS services.
"""Settings for TTS services.
Parameters:
model: TTS model identifier.
@@ -301,7 +303,7 @@ class TTSSettings(ServiceSettings):
@dataclass
class STTSettings(ServiceSettings):
"""Typed settings for STT services.
"""Settings for STT services.
Parameters:
model: STT model identifier.

10
src/pipecat/services/soniox/stt.py
View File

@@ -138,7 +138,7 @@ def _prepare_language_hints(
@dataclass
class SonioxSTTSettings(STTSettings):
"""Typed settings for Soniox STT service.
"""Settings for Soniox STT service.
Parameters:
input_params: Soniox ``SonioxInputParams`` for detailed configuration.
@@ -217,8 +217,8 @@ class SonioxSTTService(WebsocketSTTService):
await super().start(frame)
await self._connect()
async def _update_settings_from_typed(self, update: SonioxSTTSettings) -> set[str]:
"""Apply a typed settings update, keeping ``input_params`` in sync.
async def _update_settings(self, update: SonioxSTTSettings) -> set[str]:
"""Apply a settings update, keeping ``input_params`` in sync.
Top-level ``model`` is the source of truth. When it is given in
*update* its value is propagated into ``input_params``. When only
@@ -228,14 +228,14 @@ class SonioxSTTService(WebsocketSTTService):
Any change triggers a WebSocket reconnect.
Args:
update: A typed settings delta.
update: A settings delta.
Returns:
Set of field names whose values actually changed.
"""
model_given = is_given(getattr(update, "model", NOT_GIVEN))
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

12
src/pipecat/services/speechmatics/stt.py
View File

@@ -85,7 +85,7 @@ class TurnDetectionMode(str, Enum):
@dataclass
class SpeechmaticsSTTSettings(STTSettings):
"""Typed settings for Speechmatics STT service.
"""Settings for Speechmatics STT service.
See ``SpeechmaticsSTTService.InputParams`` for detailed descriptions of each field.
@@ -415,7 +415,7 @@ class SpeechmaticsSTTService(STTService):
)
speaker_passive_format = params.speaker_passive_format or speaker_active_format
# Typed settings — seeded from InputParams
# Settings — seeded from InputParams
self._settings = SpeechmaticsSTTSettings(
language=params.language,
domain=params.domain,
@@ -480,8 +480,8 @@ class SpeechmaticsSTTService(STTService):
await super().start(frame)
await self._connect()
async def _update_settings_from_typed(self, update: SpeechmaticsSTTSettings) -> set[str]:
"""Apply typed settings update, reconnecting only when necessary.
async def _update_settings(self, update: SpeechmaticsSTTSettings) -> set[str]:
"""Apply settings update, reconnecting only when necessary.
Fields are classified into three categories (see
``SpeechmaticsSTTSettings``):
@@ -494,12 +494,12 @@ class SpeechmaticsSTTService(STTService):
time and therefore require a full disconnect / reconnect.
Args:
update: A typed settings delta.
update: A settings delta.
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if not changed:
return changed

53
src/pipecat/services/stt_service.py
View File

@@ -12,7 +12,7 @@ import time
import warnings
import wave
from abc import abstractmethod
from typing import Any, AsyncGenerator, Dict, Mapping, Optional
from typing import Any, AsyncGenerator, Optional
from loguru import logger
from websockets.protocol import State
@@ -35,7 +35,7 @@ from pipecat.frames.frames import (
from pipecat.metrics.metrics import TTFBMetricsData
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_service import AIService
from pipecat.services.settings import ServiceSettings, STTSettings
from pipecat.services.settings import STTSettings
from pipecat.services.stt_latency import DEFAULT_TTFS_P99
from pipecat.services.websocket_service import WebsocketService
from pipecat.transcriptions.language import Language
@@ -183,11 +183,8 @@ class STTService(AIService):
stacklevel=2,
)
logger.info(f"Switching STT model to: [{model}]")
if isinstance(self._settings, ServiceSettings):
settings_cls = type(self._settings)
await self._update_settings_from_typed(settings_cls(model=model))
else:
self.set_model_name(model)
settings_cls = type(self._settings)
await self._update_settings(settings_cls(model=model))
async def set_language(self, language: Language):
"""Set the language for speech recognition.
@@ -206,11 +203,8 @@ class STTService(AIService):
stacklevel=2,
)
logger.info(f"Switching STT language to: [{language}]")
if isinstance(self._settings, ServiceSettings):
settings_cls = type(self._settings)
await self._update_settings_from_typed(settings_cls(language=language))
else:
pass
settings_cls = type(self._settings)
await self._update_settings(settings_cls(language=language))
@abstractmethod
async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
@@ -242,23 +236,8 @@ class STTService(AIService):
await super().cleanup()
await self._cancel_ttfb_timeout()
async def _update_settings(self, settings: Mapping[str, Any]):
logger.info(f"Updating STT settings: {self._settings}")
for key, value in settings.items():
if key in self._settings:
logger.info(f"Updating STT setting {key} to: [{value}]")
self._settings[key] = value
if key == "language":
await self.set_language(value)
elif key == "language":
await self.set_language(value)
elif key == "model":
self.set_model_name(value)
else:
logger.warning(f"Unknown setting for STT service: {key}")
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed STT settings update.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply an STT settings update.
Handles ``model`` (via parent). Does **not** call ``set_language``
— concrete services should override this method and handle language
@@ -266,12 +245,12 @@ class STTService(AIService):
changed-field set.
Args:
update: A typed STT settings delta.
update: An STT settings delta.
Returns:
Set of field names whose values actually changed.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
return changed
async def process_audio_frame(self, frame: AudioRawFrame, direction: FrameDirection):
@@ -335,16 +314,12 @@ class STTService(AIService):
await self._handle_vad_user_stopped_speaking(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, STTUpdateSettingsFrame):
# New path: typed settings update object.
if frame.update is not None:
await self._update_settings_from_typed(frame.update)
# Legacy path: plain dict, but service uses typed settings — convert.
elif isinstance(self._settings, ServiceSettings):
await self._update_settings(frame.update)
elif frame.settings:
# Backward-compatible path: convert legacy dict to settings object.
update = type(self._settings).from_mapping(frame.settings)
await self._update_settings_from_typed(update)
# Legacy path: plain dict, service still uses dict-based settings.
else:
await self._update_settings(frame.settings)
await self._update_settings(update)
elif isinstance(frame, STTMuteFrame):
self._muted = frame.mute
logger.debug(f"STT service {'muted' if frame.mute else 'unmuted'}")

56
src/pipecat/services/tts_service.py
View File

@@ -19,7 +19,6 @@ from typing import (
Callable,
Dict,
List,
Mapping,
Optional,
Sequence,
Tuple,
@@ -53,7 +52,7 @@ from pipecat.frames.frames import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.ai_service import AIService
from pipecat.services.settings import ServiceSettings, TTSSettings, is_given
from pipecat.services.settings import TTSSettings, is_given
from pipecat.services.websocket_service import WebsocketService
from pipecat.transcriptions.language import Language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
@@ -280,11 +279,8 @@ class TTSService(AIService):
stacklevel=2,
)
logger.info(f"Switching TTS model to: [{model}]")
if isinstance(self._settings, ServiceSettings):
settings_cls = type(self._settings)
await self._update_settings_from_typed(settings_cls(model=model))
else:
self.set_model_name(model)
settings_cls = type(self._settings)
await self._update_settings(settings_cls(model=model))
async def set_voice(self, voice: str):
"""Set the voice for speech synthesis.
@@ -303,11 +299,8 @@ class TTSService(AIService):
stacklevel=2,
)
logger.info(f"Switching TTS voice to: [{voice}]")
if isinstance(self._settings, ServiceSettings):
settings_cls = type(self._settings)
await self._update_settings_from_typed(settings_cls(voice=voice))
else:
self._voice_id = voice
settings_cls = type(self._settings)
await self._update_settings(settings_cls(voice=voice))
def create_context_id(self) -> str:
"""Generate a unique context ID for a TTS request.
@@ -439,25 +432,8 @@ class TTSService(AIService):
if not (agg_type == aggregation_type and func == transform_function)
]
async def _update_settings(self, settings: Mapping[str, Any]):
for key, value in settings.items():
if key in self._settings:
logger.info(f"Updating TTS setting {key} to: [{value}]")
self._settings[key] = value
if key == "language":
self._settings[key] = self.language_to_service_language(value)
elif key == "model":
self.set_model_name(value)
elif key == "voice" or key == "voice_id":
self._voice_id = value
elif key == "text_filter":
for filter in self._text_filters:
await filter.update_settings(value)
else:
logger.warning(f"Unknown setting for TTS service: {key}")
async def _update_settings_from_typed(self, update: TTSSettings) -> set[str]:
"""Apply a typed TTS settings update.
async def _update_settings(self, update: TTSSettings) -> set[str]:
"""Apply a TTS settings update.
Handles ``model`` (via parent) and syncs ``_voice_id`` when voice
changes. Translates language values before applying. Does **not**
@@ -466,7 +442,7 @@ class TTSService(AIService):
returned changed-field set.
Args:
update: A typed TTS settings delta.
update: A TTS settings delta.
Returns:
Set of field names whose values actually changed.
@@ -477,10 +453,10 @@ class TTSService(AIService):
if converted is not None:
update.language = converted
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
# Keep _voice_id in sync for code that reads it directly
if "voice" in changed and isinstance(self._settings, TTSSettings):
if "voice" in changed:
self._voice_id = self._settings.voice
return changed
@@ -566,16 +542,12 @@ class TTSService(AIService):
await self.flush_audio()
self._processing_text = processing_text
elif isinstance(frame, TTSUpdateSettingsFrame):
# New path: typed settings update object.
if frame.update is not None:
await self._update_settings_from_typed(frame.update)
# Legacy path: plain dict, but service uses typed settings — convert.
elif isinstance(self._settings, ServiceSettings):
await self._update_settings(frame.update)
elif frame.settings:
# Backward-compatible path: convert legacy dict to settings object.
update = type(self._settings).from_mapping(frame.settings)
await self._update_settings_from_typed(update)
# Legacy path: plain dict, service still uses dict-based settings.
else:
await self._update_settings(frame.settings)
await self._update_settings(update)
elif isinstance(frame, BotStoppedSpeakingFrame):
await self._maybe_resume_frame_processing()
await self.push_frame(frame, direction)

4
src/pipecat/services/ultravox/llm.py
View File

@@ -325,8 +325,8 @@ class UltravoxRealtimeLLMService(LLMService):
await self.cancel_task(self._receive_task, timeout=1.0)
self._receive_task = None
async def _update_settings_from_typed(self, update: UltravoxRealtimeLLMSettings):
changed = await super()._update_settings_from_typed(update)
async def _update_settings(self, update: UltravoxRealtimeLLMSettings):
changed = await super()._update_settings(update)
if "output_medium" in changed:
await self._update_output_medium(self._settings.output_medium)
return changed

10
src/pipecat/services/whisper/base_stt.py
View File

@@ -28,7 +28,7 @@ from pipecat.utils.tracing.service_decorators import traced_stt
@dataclass
class BaseWhisperSTTSettings(STTSettings):
"""Typed settings for Whisper API-based STT services.
"""Settings for Whisper API-based STT services.
Parameters:
base_url: API base URL.
@@ -174,13 +174,13 @@ class BaseWhisperSTTService(SegmentedSTTService):
def _create_client(self, api_key: Optional[str], base_url: Optional[str]):
return AsyncOpenAI(api_key=api_key, base_url=base_url)
async def _update_settings_from_typed(self, update: STTSettings) -> set[str]:
"""Apply a typed settings update, syncing instance variables.
async def _update_settings(self, update: STTSettings) -> set[str]:
"""Apply a settings update, syncing instance variables.
Keeps ``_language``, ``_prompt``, and ``_temperature`` in sync with
the typed settings fields.
the settings fields.
"""
changed = await super()._update_settings_from_typed(update)
changed = await super()._update_settings(update)
if "language" in changed:
self._language = self.language_to_service_language(Language(self._settings.language))

4
src/pipecat/services/whisper/stt.py
View File

@@ -176,7 +176,7 @@ def language_to_whisper_language(language: Language) -> Optional[str]:
@dataclass
class WhisperSTTSettings(STTSettings):
"""Typed settings for the local Whisper (Faster Whisper) STT service.
"""Settings for the local Whisper (Faster Whisper) STT service.
Parameters:
device: Inference device ('cpu', 'cuda', or 'auto').
@@ -191,7 +191,7 @@ class WhisperSTTSettings(STTSettings):
@dataclass
class WhisperMLXSTTSettings(STTSettings):
"""Typed settings for the MLX Whisper STT service.
"""Settings for the MLX Whisper STT service.
Parameters:
no_speech_prob: Probability threshold for filtering non-speech segments.

2
src/pipecat/services/xtts/tts.py
View File

@@ -72,7 +72,7 @@ def language_to_xtts_language(language: Language) -> Optional[str]:
@dataclass
class XTTSTTSSettings(TTSSettings):
"""Typed settings for XTTS TTS service.
"""Settings for XTTS TTS service.
Parameters:
base_url: Base URL of the XTTS streaming server.