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

Replace Any with specific types and add | _NotGiven to all *Settings field annotations across 49 service files

Browse Source 
Every `*Settings` dataclass field whose default is `NOT_GIVEN` now carries `_NotGiven` in its type union so the type system accurately reflects the three-state semantics (real value, `None` where applicable, or not-yet-specified). Fields previously typed as bare `Any`, `str`, `float`, `bool`, `list`, `dict`, or `Optional[X]` are now narrowed to the specific type from the corresponding `InputParams` Pydantic model.
This commit is contained in:
Paul Kompfner
2026-02-19 11:28:29 -05:00
parent a7edd8e441
commit 421696e1c2
49 changed files with 314 additions and 286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
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, is_given
from pipecat.services.settings import LLMSettings, _NotGiven, is_given
from pipecat.utils.tracing.service_decorators import traced_llm
try:
@@ -79,8 +79,10 @@ class AnthropicLLMSettings(LLMSettings):
thinking: Extended thinking configuration.
"""
enable_prompt_caching: Any = field(default_factory=lambda: _NOT_GIVEN)
thinking: Any = field(default_factory=lambda: _NOT_GIVEN)
enable_prompt_caching: bool | _NotGiven = field(default_factory=lambda: _NOT_GIVEN)
thinking: "AnthropicLLMService.ThinkingConfig" | _NotGiven = field(
default_factory=lambda: _NOT_GIVEN
)
@classmethod
def from_mapping(cls, settings):

6
src/pipecat/services/assemblyai/stt.py
View File

@@ -30,7 +30,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import ASSEMBLYAI_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language
@@ -64,7 +64,9 @@ class AssemblyAISTTSettings(STTSettings):
connection_params: Connection configuration parameters.
"""
connection_params: AssemblyAIConnectionParams = field(default_factory=lambda: NOT_GIVEN)
connection_params: AssemblyAIConnectionParams | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
class AssemblyAISTTService(WebsocketSTTService):

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

@@ -28,7 +28,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import AudioContextTTSService, TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -84,9 +84,9 @@ class AsyncAITTSSettings(TTSSettings):
output_sample_rate: Audio sample rate in Hz.
"""
output_container: str = field(default_factory=lambda: NOT_GIVEN)
output_encoding: str = field(default_factory=lambda: NOT_GIVEN)
output_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
output_container: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@classmethod
def from_mapping(cls, settings: Mapping[str, Any]) -> "AsyncAITTSSettings":

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

@@ -56,7 +56,7 @@ from pipecat.processors.aggregators.openai_llm_context import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.llm_service import LLMService
from pipecat.services.settings import NOT_GIVEN, LLMSettings
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven
from pipecat.utils.tracing.service_decorators import traced_llm
try:
@@ -80,8 +80,10 @@ class AWSBedrockLLMSettings(LLMSettings):
additional_model_request_fields: Additional model-specific parameters.
"""
latency: Any = field(default_factory=lambda: NOT_GIVEN)
additional_model_request_fields: Any = field(default_factory=lambda: NOT_GIVEN)
latency: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
additional_model_request_fields: Dict[str, Any] | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
@dataclass

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

@@ -29,7 +29,7 @@ from pipecat.frames.frames import (
TranscriptionFrame,
)
from pipecat.services.aws.utils import build_event_message, decode_event, get_presigned_url
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import AWS_TRANSCRIBE_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -57,11 +57,11 @@ class AWSTranscribeSTTSettings(STTSettings):
enable_channel_identification: Whether to enable channel identification.
"""
sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
media_encoding: str = field(default_factory=lambda: NOT_GIVEN)
number_of_channels: int = field(default_factory=lambda: NOT_GIVEN)
show_speaker_label: bool = field(default_factory=lambda: NOT_GIVEN)
enable_channel_identification: bool = field(default_factory=lambda: NOT_GIVEN)
sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
media_encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
number_of_channels: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
show_speaker_label: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_channel_identification: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class AWSTranscribeSTTService(WebsocketSTTService):

12
src/pipecat/services/aws/tts.py
View File

@@ -25,7 +25,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -135,11 +135,11 @@ class AWSPollyTTSSettings(TTSSettings):
lexicon_names: List of pronunciation lexicons to apply.
"""
engine: str = field(default_factory=lambda: NOT_GIVEN)
pitch: str = field(default_factory=lambda: NOT_GIVEN)
rate: str = field(default_factory=lambda: NOT_GIVEN)
volume: str = field(default_factory=lambda: NOT_GIVEN)
lexicon_names: List[str] = field(default_factory=lambda: NOT_GIVEN)
engine: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pitch: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
rate: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
volume: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
lexicon_names: List[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class AWSPollyTTSService(TTSService):

6
src/pipecat/services/azure/stt.py
View File

@@ -26,7 +26,7 @@ from pipecat.frames.frames import (
TranscriptionFrame,
)
from pipecat.services.azure.common import language_to_azure_language
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import AZURE_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language
@@ -59,8 +59,8 @@ class AzureSTTSettings(STTSettings):
sample_rate: Audio sample rate in Hz.
"""
region: str = field(default_factory=lambda: NOT_GIVEN)
sample_rate: Optional[int] = field(default_factory=lambda: NOT_GIVEN)
region: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
sample_rate: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class AzureSTTService(STTService):

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

@@ -26,7 +26,7 @@ from pipecat.frames.frames import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.azure.common import language_to_azure_language
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService, WordTTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -82,14 +82,14 @@ class AzureTTSSettings(TTSSettings):
volume: Volume level (e.g., "+20%", "loud", "x-soft").
"""
emphasis: str = field(default_factory=lambda: NOT_GIVEN)
language: str = field(default_factory=lambda: NOT_GIVEN)
pitch: str = field(default_factory=lambda: NOT_GIVEN)
rate: str = field(default_factory=lambda: NOT_GIVEN)
role: str = field(default_factory=lambda: NOT_GIVEN)
style: str = field(default_factory=lambda: NOT_GIVEN)
style_degree: str = field(default_factory=lambda: NOT_GIVEN)
volume: str = field(default_factory=lambda: NOT_GIVEN)
emphasis: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
language: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pitch: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
rate: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
role: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
style: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
style_degree: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
volume: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class AzureBaseTTSService:

4
src/pipecat/services/camb/tts.py
View File

@@ -32,7 +32,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -144,7 +144,7 @@ class CambTTSSettings(TTSSettings):
Ignored for other models. Max 1000 characters.
"""
user_instructions: str = field(default_factory=lambda: NOT_GIVEN)
user_instructions: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class CambTTSService(TTSService):

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

@@ -28,7 +28,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import CARTESIA_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language
@@ -52,7 +52,7 @@ class CartesiaSTTSettings(STTSettings):
encoding: Audio encoding format (e.g. ``"pcm_s16le"``).
"""
encoding: str = field(default_factory=lambda: NOT_GIVEN)
encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class CartesiaLiveOptions:

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

@@ -28,7 +28,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import AudioContextWordTTSService, TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
@@ -209,13 +209,13 @@ class CartesiaTTSSettings(TTSSettings):
custom pronunciations.
"""
output_container: str = field(default_factory=lambda: NOT_GIVEN)
output_encoding: str = field(default_factory=lambda: NOT_GIVEN)
output_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
speed: str = field(default_factory=lambda: NOT_GIVEN)
emotion: List[str] = field(default_factory=lambda: NOT_GIVEN)
generation_config: GenerationConfig = field(default_factory=lambda: NOT_GIVEN)
pronunciation_dict_id: str = field(default_factory=lambda: NOT_GIVEN)
output_container: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: Literal["slow", "normal", "fast"] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
emotion: List[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
generation_config: GenerationConfig | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pronunciation_dict_id: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@classmethod
def from_mapping(cls, settings: Mapping[str, Any]) -> "CartesiaTTSSettings":

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

@@ -24,7 +24,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import DEEPGRAM_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language
@@ -55,7 +55,7 @@ class DeepgramSTTSettings(STTSettings):
live_options: Deepgram ``LiveOptions`` for detailed configuration.
"""
live_options: LiveOptions = field(default_factory=lambda: NOT_GIVEN)
live_options: LiveOptions | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class DeepgramSTTService(STTService):

4
src/pipecat/services/deepgram/stt_sagemaker.py
View File

@@ -32,7 +32,7 @@ from pipecat.frames.frames import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.aws.sagemaker.bidi_client import SageMakerBidiClient
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import DEEPGRAM_SAGEMAKER_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language
@@ -57,7 +57,7 @@ class DeepgramSageMakerSTTSettings(STTSettings):
live_options: Deepgram ``LiveOptions`` for detailed configuration.
"""
live_options: LiveOptions = field(default_factory=lambda: NOT_GIVEN)
live_options: LiveOptions | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class DeepgramSageMakerSTTService(STTService):

4
src/pipecat/services/deepgram/tts.py
View File

@@ -30,7 +30,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService, WebsocketTTSService
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -53,7 +53,7 @@ class DeepgramTTSSettings(TTSSettings):
encoding: Audio encoding format (linear16, mulaw, alaw).
"""
encoding: str = field(default_factory=lambda: NOT_GIVEN)
encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class DeepgramTTSService(WebsocketTTSService):

20
src/pipecat/services/elevenlabs/stt.py
View File

@@ -35,7 +35,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import ELEVENLABS_REALTIME_TTFS_P99, ELEVENLABS_TTFS_P99
from pipecat.services.stt_service import SegmentedSTTService, WebsocketSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -185,7 +185,7 @@ class ElevenLabsSTTSettings(STTSettings):
tag_audio_events: Whether to include audio event tags in transcription.
"""
tag_audio_events: bool = field(default_factory=lambda: NOT_GIVEN)
tag_audio_events: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@dataclass
@@ -205,14 +205,14 @@ class ElevenLabsRealtimeSTTSettings(STTSettings):
include_language_detection: Whether to include language detection in transcripts.
"""
commit_strategy: CommitStrategy = field(default_factory=lambda: NOT_GIVEN)
vad_silence_threshold_secs: float = field(default_factory=lambda: NOT_GIVEN)
vad_threshold: float = field(default_factory=lambda: NOT_GIVEN)
min_speech_duration_ms: int = field(default_factory=lambda: NOT_GIVEN)
min_silence_duration_ms: int = field(default_factory=lambda: NOT_GIVEN)
include_timestamps: bool = field(default_factory=lambda: NOT_GIVEN)
enable_logging: bool = field(default_factory=lambda: NOT_GIVEN)
include_language_detection: bool = field(default_factory=lambda: NOT_GIVEN)
commit_strategy: CommitStrategy | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
vad_silence_threshold_secs: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
vad_threshold: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
min_speech_duration_ms: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
min_silence_duration_ms: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
include_timestamps: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_logging: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
include_language_detection: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class ElevenLabsSTTService(SegmentedSTTService):

38
src/pipecat/services/elevenlabs/tts.py
View File

@@ -44,7 +44,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import (
AudioContextWordTTSService,
WordTTSService,
@@ -206,15 +206,17 @@ class ElevenLabsTTSSettings(TTSSettings):
apply_text_normalization: Text normalization mode ("auto", "on", "off").
"""
stability: float = field(default_factory=lambda: NOT_GIVEN)
similarity_boost: float = field(default_factory=lambda: NOT_GIVEN)
style: float = field(default_factory=lambda: NOT_GIVEN)
use_speaker_boost: bool = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
auto_mode: str = field(default_factory=lambda: NOT_GIVEN)
enable_ssml_parsing: bool = field(default_factory=lambda: NOT_GIVEN)
enable_logging: bool = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: str = field(default_factory=lambda: NOT_GIVEN)
stability: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
similarity_boost: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
style: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
use_speaker_boost: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
auto_mode: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_ssml_parsing: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_logging: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: Literal["auto", "on", "off"] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
#: Fields in the WS URL — changing any of these requires a reconnect.
URL_FIELDS: ClassVar[frozenset[str]] = frozenset({"voice", "model", "language"})
@@ -242,13 +244,15 @@ class ElevenLabsHttpTTSSettings(TTSSettings):
apply_text_normalization: Text normalization mode ("auto", "on", "off").
"""
optimize_streaming_latency: int = field(default_factory=lambda: NOT_GIVEN)
stability: float = field(default_factory=lambda: NOT_GIVEN)
similarity_boost: float = field(default_factory=lambda: NOT_GIVEN)
style: float = field(default_factory=lambda: NOT_GIVEN)
use_speaker_boost: bool = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: str = field(default_factory=lambda: NOT_GIVEN)
optimize_streaming_latency: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
stability: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
similarity_boost: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
style: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
use_speaker_boost: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: Literal["auto", "on", "off"] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
_aliases: ClassVar[Dict[str, str]] = {"voice_id": "voice"}

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

@@ -18,7 +18,7 @@ from loguru import logger
from pydantic import BaseModel
from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import FAL_TTFS_P99
from pipecat.services.stt_service import SegmentedSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -159,9 +159,9 @@ class FalSTTSettings(STTSettings):
version: Version of Wizper model to use. Defaults to '3'.
"""
task: str = field(default_factory=lambda: NOT_GIVEN)
chunk_level: str = field(default_factory=lambda: NOT_GIVEN)
version: str = field(default_factory=lambda: NOT_GIVEN)
task: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
chunk_level: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
version: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class FalSTTService(SegmentedSTTService):

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

@@ -29,7 +29,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import InterruptibleTTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -61,13 +61,13 @@ class FishAudioTTSSettings(TTSSettings):
reference_id: Reference ID of the voice model.
"""
fish_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
latency: str = field(default_factory=lambda: NOT_GIVEN)
format: str = field(default_factory=lambda: NOT_GIVEN)
normalize: bool = field(default_factory=lambda: NOT_GIVEN)
prosody_speed: float = field(default_factory=lambda: NOT_GIVEN)
prosody_volume: int = field(default_factory=lambda: NOT_GIVEN)
reference_id: str = field(default_factory=lambda: NOT_GIVEN)
fish_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
latency: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
normalize: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
prosody_speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
prosody_volume: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
reference_id: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {"voice_id": "voice", "sample_rate": "fish_sample_rate"}

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

@@ -33,7 +33,7 @@ from pipecat.frames.frames import (
UserStoppedSpeakingFrame,
)
from pipecat.services.gladia.config import GladiaInputParams
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import GLADIA_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -188,7 +188,7 @@ class GladiaSTTSettings(STTSettings):
input_params: Gladia ``GladiaInputParams`` for detailed configuration.
"""
input_params: GladiaInputParams = field(default_factory=lambda: NOT_GIVEN)
input_params: GladiaInputParams | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class GladiaSTTService(WebsocketSTTService):

20
src/pipecat/services/google/gemini_live/llm.py
View File

@@ -76,7 +76,7 @@ from pipecat.services.openai.llm import (
OpenAIAssistantContextAggregator,
OpenAIUserContextAggregator,
)
from pipecat.services.settings import NOT_GIVEN, LLMSettings
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.string import match_endofsentence
from pipecat.utils.time import time_now_iso8601
@@ -617,14 +617,16 @@ class GeminiLiveLLMSettings(LLMSettings):
proactivity: Proactivity configuration.
"""
modalities: Any = field(default_factory=lambda: NOT_GIVEN)
language: Any = field(default_factory=lambda: NOT_GIVEN)
media_resolution: Any = field(default_factory=lambda: NOT_GIVEN)
vad: Any = field(default_factory=lambda: NOT_GIVEN)
context_window_compression: Any = field(default_factory=lambda: NOT_GIVEN)
thinking: Any = field(default_factory=lambda: NOT_GIVEN)
enable_affective_dialog: Any = field(default_factory=lambda: NOT_GIVEN)
proactivity: Any = field(default_factory=lambda: NOT_GIVEN)
modalities: GeminiModalities | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
language: Language | str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
media_resolution: GeminiMediaResolution | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
vad: GeminiVADParams | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
context_window_compression: ContextWindowCompressionParams | dict | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
thinking: ThinkingConfig | dict | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_affective_dialog: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
proactivity: ProactivityConfig | dict | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class GeminiLiveLLMService(LLMService):

6
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, is_given
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven, is_given
from pipecat.utils.tracing.service_decorators import traced_llm
# Suppress gRPC fork warnings
@@ -681,7 +681,9 @@ class GoogleLLMSettings(LLMSettings):
thinking: Thinking configuration.
"""
thinking: Any = field(default_factory=lambda: NOT_GIVEN)
thinking: "GoogleLLMService.ThinkingConfig" | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
@classmethod
def from_mapping(cls, settings):

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

@@ -36,7 +36,7 @@ from pipecat.frames.frames import (
StartFrame,
TranscriptionFrame,
)
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import GOOGLE_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -383,17 +383,19 @@ class GoogleSTTSettings(STTSettings):
enable_voice_activity_events: Detect voice activity in audio.
"""
languages: Any = field(default_factory=lambda: NOT_GIVEN)
language_codes: Any = field(default_factory=lambda: NOT_GIVEN)
use_separate_recognition_per_channel: Any = field(default_factory=lambda: NOT_GIVEN)
enable_automatic_punctuation: Any = field(default_factory=lambda: NOT_GIVEN)
enable_spoken_punctuation: Any = field(default_factory=lambda: NOT_GIVEN)
enable_spoken_emojis: Any = field(default_factory=lambda: NOT_GIVEN)
profanity_filter: Any = field(default_factory=lambda: NOT_GIVEN)
enable_word_time_offsets: Any = field(default_factory=lambda: NOT_GIVEN)
enable_word_confidence: Any = field(default_factory=lambda: NOT_GIVEN)
enable_interim_results: Any = field(default_factory=lambda: NOT_GIVEN)
enable_voice_activity_events: Any = field(default_factory=lambda: NOT_GIVEN)
languages: List[Language] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
language_codes: List[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
use_separate_recognition_per_channel: bool | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
enable_automatic_punctuation: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_spoken_punctuation: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_spoken_emojis: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
profanity_filter: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_word_time_offsets: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_word_confidence: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_interim_results: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_voice_activity_events: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class GoogleSTTService(STTService):

40
src/pipecat/services/google/tts.py
View File

@@ -24,7 +24,7 @@ from pipecat.utils.tracing.service_decorators import traced_tts
os.environ["GRPC_ENABLE_FORK_SUPPORT"] = "false"
from dataclasses import dataclass, field
from typing import Any, AsyncGenerator, List, Literal, Optional
from typing import Any, AsyncGenerator, Dict, List, Literal, Optional
from loguru import logger
from pydantic import BaseModel
@@ -37,7 +37,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
@@ -493,14 +493,20 @@ class GoogleHttpTTSSettings(TTSSettings):
google_style: Google-specific voice style.
"""
pitch: str = field(default_factory=lambda: NOT_GIVEN)
rate: str = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float = field(default_factory=lambda: NOT_GIVEN)
volume: str = field(default_factory=lambda: NOT_GIVEN)
emphasis: str = field(default_factory=lambda: NOT_GIVEN)
language: str = field(default_factory=lambda: NOT_GIVEN)
gender: str = field(default_factory=lambda: NOT_GIVEN)
google_style: str = field(default_factory=lambda: NOT_GIVEN)
pitch: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
rate: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
volume: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
emphasis: Literal["strong", "moderate", "reduced", "none"] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
language: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
gender: Literal["male", "female", "neutral"] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
google_style: (
Literal["apologetic", "calm", "empathetic", "firm", "lively"] | None | _NotGiven
) = field(default_factory=lambda: NOT_GIVEN)
@dataclass
@@ -512,8 +518,8 @@ class GoogleStreamTTSSettings(TTSSettings):
speaking_rate: The speaking rate, in the range [0.25, 2.0].
"""
language: str = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float = field(default_factory=lambda: NOT_GIVEN)
language: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@dataclass
@@ -527,10 +533,12 @@ class GeminiTTSSettings(TTSSettings):
speaker_configs: List of speaker configurations for multi-speaker mode.
"""
language: str = field(default_factory=lambda: NOT_GIVEN)
prompt: str = field(default_factory=lambda: NOT_GIVEN)
multi_speaker: bool = field(default_factory=lambda: NOT_GIVEN)
speaker_configs: List[dict] = field(default_factory=lambda: NOT_GIVEN)
language: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
prompt: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
multi_speaker: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaker_configs: list[dict[str, Any]] | None | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
class GoogleHttpTTSService(TTSService):

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

@@ -28,7 +28,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import GRADIUM_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -75,7 +75,7 @@ class GradiumSTTSettings(STTSettings):
generated. Higher delays allow more context but increase latency.
"""
delay_in_frames: int = field(default_factory=lambda: NOT_GIVEN)
delay_in_frames: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class GradiumSTTService(WebsocketSTTService):

4
src/pipecat/services/gradium/tts.py
View File

@@ -23,7 +23,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import InterruptibleWordTTSService
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -47,7 +47,7 @@ class GradiumTTSSettings(TTSSettings):
output_format: Audio output format.
"""
output_format: str = field(default_factory=lambda: NOT_GIVEN)
output_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class GradiumTTSService(InterruptibleWordTTSService):

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

@@ -21,7 +21,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -44,9 +44,9 @@ class GroqTTSSettings(TTSSettings):
groq_sample_rate: Audio sample rate.
"""
output_format: str = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
groq_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
output_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
groq_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {"voice_id": "voice", "sample_rate": "groq_sample_rate"}

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

@@ -19,7 +19,7 @@ from pipecat.frames.frames import (
Frame,
TranscriptionFrame,
)
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import HATHORA_TTFS_P99
from pipecat.services.stt_service import SegmentedSTTService
from pipecat.transcriptions.language import Language
@@ -39,7 +39,7 @@ class HathoraSTTSettings(STTSettings):
what is supported.
"""
config: Optional[list] = field(default_factory=lambda: NOT_GIVEN)
config: list[ConfigOption] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class HathoraSTTService(SegmentedSTTService):

6
src/pipecat/services/hathora/tts.py
View File

@@ -22,7 +22,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -58,8 +58,8 @@ class HathoraTTSSettings(TTSSettings):
what is supported.
"""
speed: float = field(default_factory=lambda: NOT_GIVEN)
config: list = field(default_factory=lambda: NOT_GIVEN)
speed: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
config: list[ConfigOption] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class HathoraTTSService(TTSService):

14
src/pipecat/services/inworld/tts.py
View File

@@ -24,7 +24,7 @@ import websockets
from loguru import logger
from pydantic import BaseModel
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
try:
from websockets.asyncio.client import connect as websocket_connect
@@ -67,12 +67,12 @@ class InworldTTSSettings(TTSSettings):
apply_text_normalization: Whether to apply text normalization.
"""
audio_encoding: str = field(default_factory=lambda: NOT_GIVEN)
audio_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float = field(default_factory=lambda: NOT_GIVEN)
temperature: float = field(default_factory=lambda: NOT_GIVEN)
auto_mode: bool = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: str = field(default_factory=lambda: NOT_GIVEN)
audio_encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audio_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
auto_mode: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
apply_text_normalization: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {
"voice_id": "voice",

4
src/pipecat/services/kokoro/tts.py
View File

@@ -23,7 +23,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -97,7 +97,7 @@ class KokoroTTSSettings(TTSSettings):
lang_code: Kokoro language code for synthesis.
"""
lang_code: str = field(default_factory=lambda: NOT_GIVEN)
lang_code: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class KokoroTTSService(TTSService):

4
src/pipecat/services/lmnt/tts.py
View File

@@ -24,7 +24,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import InterruptibleTTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -81,7 +81,7 @@ class LmntTTSSettings(TTSSettings):
format: Audio output format. Defaults to "raw".
"""
format: str = field(default_factory=lambda: NOT_GIVEN)
format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class LmntTTSService(InterruptibleTTSService):

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

@@ -26,7 +26,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -107,18 +107,18 @@ class MiniMaxTTSSettings(TTSSettings):
language_boost: Language boost string for multilingual support.
"""
stream: bool = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
volume: float = field(default_factory=lambda: NOT_GIVEN)
pitch: int = field(default_factory=lambda: NOT_GIVEN)
emotion: str = field(default_factory=lambda: NOT_GIVEN)
text_normalization: bool = field(default_factory=lambda: NOT_GIVEN)
latex_read: bool = field(default_factory=lambda: NOT_GIVEN)
audio_bitrate: int = field(default_factory=lambda: NOT_GIVEN)
audio_format: str = field(default_factory=lambda: NOT_GIVEN)
audio_channel: int = field(default_factory=lambda: NOT_GIVEN)
audio_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
language_boost: str = field(default_factory=lambda: NOT_GIVEN)
stream: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
volume: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pitch: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
emotion: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
text_normalization: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
latex_read: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audio_bitrate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audio_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audio_channel: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audio_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
language_boost: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {"voice_id": "voice"}

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

@@ -35,7 +35,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import InterruptibleTTSService, TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -85,10 +85,10 @@ class NeuphonicTTSSettings(TTSSettings):
sampling_rate: Audio sample rate.
"""
lang_code: str = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
encoding: str = field(default_factory=lambda: NOT_GIVEN)
sampling_rate: int = field(default_factory=lambda: NOT_GIVEN)
lang_code: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
encoding: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
sampling_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class NeuphonicTTSService(InterruptibleTTSService):

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

@@ -23,7 +23,7 @@ from pipecat.frames.frames import (
StartFrame,
TranscriptionFrame,
)
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import NVIDIA_TTFS_P99
from pipecat.services.stt_service import SegmentedSTTService, STTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -110,11 +110,11 @@ class NvidiaSegmentedSTTSettings(STTSettings):
boosted_lm_score: Score boost for specified words.
"""
profanity_filter: bool = field(default_factory=lambda: NOT_GIVEN)
automatic_punctuation: bool = field(default_factory=lambda: NOT_GIVEN)
verbatim_transcripts: bool = field(default_factory=lambda: NOT_GIVEN)
boosted_lm_words: Optional[List[str]] = field(default_factory=lambda: NOT_GIVEN)
boosted_lm_score: float = field(default_factory=lambda: NOT_GIVEN)
profanity_filter: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
automatic_punctuation: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
verbatim_transcripts: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
boosted_lm_words: List[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
boosted_lm_score: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class NvidiaSTTService(STTService):

6
src/pipecat/services/openai/base_llm.py
View File

@@ -43,7 +43,7 @@ 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, _NotGiven
from pipecat.utils.tracing.service_decorators import traced_llm
@@ -56,8 +56,8 @@ class OpenAILLMSettings(LLMSettings):
service_tier: Service tier to use (e.g., "auto", "flex", "priority").
"""
max_completion_tokens: Any = field(default_factory=lambda: _NOT_GIVEN)
service_tier: Any = field(default_factory=lambda: _NOT_GIVEN)
max_completion_tokens: int | _NotGiven = field(default_factory=lambda: _NOT_GIVEN)
service_tier: str | _NotGiven = field(default_factory=lambda: _NOT_GIVEN)
class BaseOpenAILLMService(LLMService):

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

@@ -35,7 +35,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import OPENAI_REALTIME_TTFS_P99, OPENAI_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.services.whisper.base_stt import BaseWhisperSTTService, Transcription
@@ -133,7 +133,7 @@ class OpenAIRealtimeSTTSettings(STTSettings):
prompt: Optional prompt text to guide transcription style.
"""
prompt: Optional[str] = field(default_factory=lambda: NOT_GIVEN)
prompt: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class OpenAIRealtimeSTTService(WebsocketSTTService):

6
src/pipecat/services/openai/tts.py
View File

@@ -25,7 +25,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -71,8 +71,8 @@ class OpenAITTSSettings(TTSSettings):
speed: Voice speed control (0.25 to 4.0, default 1.0).
"""
instructions: str = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
instructions: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class OpenAITTSService(TTSService):

8
src/pipecat/services/openai_realtime_beta/openai.py
View File

@@ -11,7 +11,7 @@ import json
import time
import warnings
from dataclasses import dataclass, field
from typing import Any, Optional
from typing import Optional
from loguru import logger
@@ -54,7 +54,7 @@ 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.openai.llm import OpenAIContextAggregatorPair
from pipecat.services.settings import NOT_GIVEN, LLMSettings
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven
from pipecat.transcriptions.language import Language
from pipecat.utils.time import time_now_iso8601
from pipecat.utils.tracing.service_decorators import traced_openai_realtime, traced_stt
@@ -100,7 +100,9 @@ class OpenAIRealtimeBetaLLMSettings(LLMSettings):
session_properties: OpenAI Realtime session configuration.
"""
session_properties: Any = field(default_factory=lambda: NOT_GIVEN)
session_properties: events.SessionProperties | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
class OpenAIRealtimeBetaLLMService(LLMService):

12
src/pipecat/services/playht/tts.py
View File

@@ -33,7 +33,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import InterruptibleTTSService, TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -111,11 +111,11 @@ class PlayHTTTSSettings(TTSSettings):
playht_sample_rate: Audio sample rate sent to the API.
"""
output_format: str = field(default_factory=lambda: NOT_GIVEN)
voice_engine: str = field(default_factory=lambda: NOT_GIVEN)
speed: float = field(default_factory=lambda: NOT_GIVEN)
seed: int = field(default_factory=lambda: NOT_GIVEN)
playht_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
output_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
voice_engine: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speed: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
seed: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
playht_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class PlayHTTTSService(InterruptibleTTSService):

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

@@ -25,7 +25,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import AudioContextWordTTSService
from pipecat.transcriptions.language import Language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
@@ -50,9 +50,9 @@ class ResembleAITTSSettings(TTSSettings):
resemble_sample_rate: Audio sample rate sent to the API.
"""
precision: str = field(default_factory=lambda: NOT_GIVEN)
output_format: str = field(default_factory=lambda: NOT_GIVEN)
resemble_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
precision: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_format: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
resemble_sample_rate: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {
"voice_id": "voice",

36
src/pipecat/services/rime/tts.py
View File

@@ -31,7 +31,7 @@ from pipecat.frames.frames import (
TTSStoppedFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import (
AudioContextWordTTSService,
InterruptibleTTSService,
@@ -86,15 +86,15 @@ class RimeTTSSettings(TTSSettings):
inlineSpeedAlpha: Inline speed control markup.
"""
modelId: str = field(default_factory=lambda: NOT_GIVEN)
audioFormat: str = field(default_factory=lambda: NOT_GIVEN)
samplingRate: int = field(default_factory=lambda: NOT_GIVEN)
lang: str = field(default_factory=lambda: NOT_GIVEN)
speedAlpha: float = field(default_factory=lambda: NOT_GIVEN)
reduceLatency: bool = field(default_factory=lambda: NOT_GIVEN)
pauseBetweenBrackets: bool = field(default_factory=lambda: NOT_GIVEN)
phonemizeBetweenBrackets: bool = field(default_factory=lambda: NOT_GIVEN)
inlineSpeedAlpha: str = field(default_factory=lambda: NOT_GIVEN)
modelId: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audioFormat: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
samplingRate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
lang: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speedAlpha: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
reduceLatency: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pauseBetweenBrackets: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
phonemizeBetweenBrackets: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
inlineSpeedAlpha: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {"speaker": "voice"}
@@ -114,14 +114,14 @@ class RimeNonJsonTTSSettings(TTSSettings):
top_p: Cumulative probability threshold (0.0-1.0).
"""
modelId: str = field(default_factory=lambda: NOT_GIVEN)
audioFormat: str = field(default_factory=lambda: NOT_GIVEN)
samplingRate: int = field(default_factory=lambda: NOT_GIVEN)
lang: str = field(default_factory=lambda: NOT_GIVEN)
segment: str = field(default_factory=lambda: NOT_GIVEN)
repetition_penalty: float = field(default_factory=lambda: NOT_GIVEN)
temperature: float = field(default_factory=lambda: NOT_GIVEN)
top_p: float = field(default_factory=lambda: NOT_GIVEN)
modelId: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
audioFormat: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
samplingRate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
lang: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
segment: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
repetition_penalty: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
top_p: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
_aliases: ClassVar[Dict[str, str]] = {"speaker": "voice"}

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

@@ -32,7 +32,7 @@ from pipecat.frames.frames import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.sarvam._sdk import sdk_headers
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import SARVAM_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -142,10 +142,10 @@ class SarvamSTTSettings(STTSettings):
high_vad_sensitivity: Enable high VAD sensitivity.
"""
prompt: Optional[str] = field(default_factory=lambda: NOT_GIVEN)
mode: Optional[str] = field(default_factory=lambda: NOT_GIVEN)
vad_signals: Optional[bool] = field(default_factory=lambda: NOT_GIVEN)
high_vad_sensitivity: Optional[bool] = field(default_factory=lambda: NOT_GIVEN)
prompt: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
mode: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
vad_signals: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
high_vad_sensitivity: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class SarvamSTTService(STTService):

40
src/pipecat/services/sarvam/tts.py
View File

@@ -62,7 +62,7 @@ from pipecat.frames.frames import (
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.sarvam._sdk import sdk_headers
from pipecat.services.settings import NOT_GIVEN, TTSSettings, is_given
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven, is_given
from pipecat.services.tts_service import InterruptibleTTSService, TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -266,13 +266,13 @@ class SarvamHttpTTSSettings(TTSSettings):
sample_rate: Audio sample rate.
"""
language: str = field(default_factory=lambda: NOT_GIVEN)
enable_preprocessing: bool = field(default_factory=lambda: NOT_GIVEN)
pace: float = field(default_factory=lambda: NOT_GIVEN)
pitch: float = field(default_factory=lambda: NOT_GIVEN)
loudness: float = field(default_factory=lambda: NOT_GIVEN)
temperature: float = field(default_factory=lambda: NOT_GIVEN)
sarvam_sample_rate: int = field(default_factory=lambda: NOT_GIVEN)
language: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_preprocessing: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pace: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pitch: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
loudness: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
sarvam_sample_rate: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@dataclass
@@ -305,18 +305,18 @@ class SarvamTTSSettings(TTSSettings):
**Note:** Only supported for bulbul:v3-beta. Ignored for v2.
"""
target_language_code: str = field(default_factory=lambda: NOT_GIVEN)
speaker: str = field(default_factory=lambda: NOT_GIVEN)
speech_sample_rate: str = field(default_factory=lambda: NOT_GIVEN)
enable_preprocessing: bool = field(default_factory=lambda: NOT_GIVEN)
min_buffer_size: int = field(default_factory=lambda: NOT_GIVEN)
max_chunk_length: int = field(default_factory=lambda: NOT_GIVEN)
output_audio_codec: str = field(default_factory=lambda: NOT_GIVEN)
output_audio_bitrate: str = field(default_factory=lambda: NOT_GIVEN)
pace: float = field(default_factory=lambda: NOT_GIVEN)
pitch: float = field(default_factory=lambda: NOT_GIVEN)
loudness: float = field(default_factory=lambda: NOT_GIVEN)
temperature: float = field(default_factory=lambda: NOT_GIVEN)
target_language_code: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaker: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speech_sample_rate: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_preprocessing: bool | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
min_buffer_size: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
max_chunk_length: int | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_audio_codec: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
output_audio_bitrate: str | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pace: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
pitch: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
loudness: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | None | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class SarvamHttpTTSService(TTSService):

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

@@ -24,7 +24,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import SONIOX_TTFS_P99
from pipecat.services.stt_service import WebsocketSTTService
from pipecat.transcriptions.language import Language
@@ -144,7 +144,7 @@ class SonioxSTTSettings(STTSettings):
input_params: Soniox ``SonioxInputParams`` for detailed configuration.
"""
input_params: SonioxInputParams = field(default_factory=lambda: NOT_GIVEN)
input_params: SonioxInputParams | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class SonioxSTTService(WebsocketSTTService):

48
src/pipecat/services/speechmatics/stt.py
View File

@@ -33,7 +33,7 @@ from pipecat.frames.frames import (
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.settings import NOT_GIVEN, STTSettings, is_given
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven, is_given
from pipecat.services.stt_latency import SPEECHMATICS_TTFS_P99
from pipecat.services.stt_service import STTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -115,28 +115,30 @@ class SpeechmaticsSTTSettings(STTSettings):
extra_params: Extra parameters for the STT engine.
"""
domain: str = field(default_factory=lambda: NOT_GIVEN)
turn_detection_mode: TurnDetectionMode = field(default_factory=lambda: NOT_GIVEN)
speaker_active_format: str = field(default_factory=lambda: NOT_GIVEN)
speaker_passive_format: str = field(default_factory=lambda: NOT_GIVEN)
focus_speakers: list = field(default_factory=lambda: NOT_GIVEN)
ignore_speakers: list = field(default_factory=lambda: NOT_GIVEN)
focus_mode: Any = field(default_factory=lambda: NOT_GIVEN)
known_speakers: list = field(default_factory=lambda: NOT_GIVEN)
additional_vocab: list = field(default_factory=lambda: NOT_GIVEN)
audio_encoding: Any = field(default_factory=lambda: NOT_GIVEN)
operating_point: Any = field(default_factory=lambda: NOT_GIVEN)
max_delay: float = field(default_factory=lambda: NOT_GIVEN)
end_of_utterance_silence_trigger: float = field(default_factory=lambda: NOT_GIVEN)
end_of_utterance_max_delay: float = field(default_factory=lambda: NOT_GIVEN)
punctuation_overrides: dict = field(default_factory=lambda: NOT_GIVEN)
include_partials: bool = field(default_factory=lambda: NOT_GIVEN)
split_sentences: bool = field(default_factory=lambda: NOT_GIVEN)
enable_diarization: bool = field(default_factory=lambda: NOT_GIVEN)
speaker_sensitivity: float = field(default_factory=lambda: NOT_GIVEN)
max_speakers: int = field(default_factory=lambda: NOT_GIVEN)
prefer_current_speaker: bool = field(default_factory=lambda: NOT_GIVEN)
extra_params: dict = field(default_factory=lambda: NOT_GIVEN)
domain: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
turn_detection_mode: TurnDetectionMode | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaker_active_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaker_passive_format: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
focus_speakers: list[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
ignore_speakers: list[str] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
focus_mode: SpeakerFocusMode | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
known_speakers: list[SpeakerIdentifier] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
additional_vocab: list[AdditionalVocabEntry] | _NotGiven = field(
default_factory=lambda: NOT_GIVEN
)
audio_encoding: AudioEncoding | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
operating_point: OperatingPoint | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
max_delay: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
end_of_utterance_silence_trigger: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
end_of_utterance_max_delay: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
punctuation_overrides: dict[str, Any] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
include_partials: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
split_sentences: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
enable_diarization: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
speaker_sensitivity: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
max_speakers: int | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
prefer_current_speaker: bool | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
extra_params: dict[str, Any] | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
#: Fields that can be updated on a live connection via the Speechmatics
#: diarization-config API — no reconnect needed.

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

@@ -56,7 +56,7 @@ 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, LLMSettings
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven
from pipecat.utils.time import time_now_iso8601
try:
@@ -75,7 +75,7 @@ class UltravoxRealtimeLLMSettings(LLMSettings):
output_medium: The output medium for the model ("voice" or "text").
"""
output_medium: str = field(default=NOT_GIVEN)
output_medium: str | _NotGiven = field(default=NOT_GIVEN)
class AgentInputParams(BaseModel):

8
src/pipecat/services/whisper/base_stt.py
View File

@@ -18,7 +18,7 @@ from openai import AsyncOpenAI
from openai.types.audio import Transcription
from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_latency import WHISPER_TTFS_P99
from pipecat.services.stt_service import SegmentedSTTService
from pipecat.transcriptions.language import Language, resolve_language
@@ -37,9 +37,9 @@ class BaseWhisperSTTSettings(STTSettings):
temperature: Sampling temperature between 0 and 1.
"""
base_url: Optional[str] = field(default_factory=lambda: NOT_GIVEN)
prompt: Optional[str] = field(default_factory=lambda: NOT_GIVEN)
temperature: Optional[float] = field(default_factory=lambda: NOT_GIVEN)
base_url: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
prompt: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
def language_to_whisper_language(language: Language) -> Optional[str]:

14
src/pipecat/services/whisper/stt.py
View File

@@ -20,7 +20,7 @@ from loguru import logger
from typing_extensions import TYPE_CHECKING, override
from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
from pipecat.services.settings import NOT_GIVEN, STTSettings
from pipecat.services.settings import NOT_GIVEN, STTSettings, _NotGiven
from pipecat.services.stt_service import SegmentedSTTService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.time import time_now_iso8601
@@ -184,9 +184,9 @@ class WhisperSTTSettings(STTSettings):
no_speech_prob: Probability threshold for filtering non-speech segments.
"""
device: str = field(default_factory=lambda: NOT_GIVEN)
compute_type: str = field(default_factory=lambda: NOT_GIVEN)
no_speech_prob: float = field(default_factory=lambda: NOT_GIVEN)
device: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
compute_type: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
no_speech_prob: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
@dataclass
@@ -199,9 +199,9 @@ class WhisperMLXSTTSettings(STTSettings):
engine: Whisper engine identifier.
"""
no_speech_prob: float = field(default_factory=lambda: NOT_GIVEN)
temperature: float = field(default_factory=lambda: NOT_GIVEN)
engine: str = field(default_factory=lambda: NOT_GIVEN)
no_speech_prob: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
temperature: float | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
engine: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class WhisperSTTService(SegmentedSTTService):

4
src/pipecat/services/xtts/tts.py
View File

@@ -25,7 +25,7 @@ from pipecat.frames.frames import (
TTSStartedFrame,
TTSStoppedFrame,
)
from pipecat.services.settings import NOT_GIVEN, TTSSettings
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -78,7 +78,7 @@ class XTTSTTSSettings(TTSSettings):
base_url: Base URL of the XTTS streaming server.
"""
base_url: str = field(default_factory=lambda: NOT_GIVEN)
base_url: str | _NotGiven = field(default_factory=lambda: NOT_GIVEN)
class XTTSService(TTSService):