Merge pull request #3952 from pipecat-ai/mb/settings-alias
Add Settings class attribute alias to all service classes
This commit is contained in:
@@ -159,6 +159,7 @@ class AnthropicLLMService(LLMService):
|
||||
Can use custom clients like AsyncAnthropicBedrock and AsyncAnthropicVertex.
|
||||
"""
|
||||
|
||||
Settings = AnthropicLLMSettings
|
||||
_settings: AnthropicLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the Anthropic one.
|
||||
|
||||
@@ -128,6 +128,7 @@ class AssemblyAISTTService(WebsocketSTTService):
|
||||
for audio processing and connection management.
|
||||
"""
|
||||
|
||||
Settings = AssemblyAISTTSettings
|
||||
_settings: AssemblyAISTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -85,6 +85,7 @@ class AsyncAITTSService(WebsocketTTSService):
|
||||
Provides text-to-speech using Async's streaming WebSocket API.
|
||||
"""
|
||||
|
||||
Settings = AsyncAITTSSettings
|
||||
_settings: AsyncAITTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -485,6 +486,7 @@ class AsyncAIHttpTTSService(TTSService):
|
||||
connection is not required or desired.
|
||||
"""
|
||||
|
||||
Settings = AsyncAITTSSettings
|
||||
_settings: AsyncAITTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -746,6 +746,7 @@ class AWSBedrockLLMService(LLMService):
|
||||
vision capabilities.
|
||||
"""
|
||||
|
||||
Settings = AWSBedrockLLMSettings
|
||||
_settings: AWSBedrockLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the Anthropic one.
|
||||
|
||||
@@ -246,6 +246,7 @@ class AWSNovaSonicLLMService(LLMService):
|
||||
and function calling capabilities using AWS Nova Sonic model.
|
||||
"""
|
||||
|
||||
Settings = AWSNovaSonicLLMSettings
|
||||
_settings: AWSNovaSonicLLMSettings
|
||||
|
||||
# Override the default adapter to use the AWSNovaSonicLLMAdapter one
|
||||
|
||||
@@ -60,6 +60,7 @@ class AWSTranscribeSTTService(WebsocketSTTService):
|
||||
final transcription results.
|
||||
"""
|
||||
|
||||
Settings = AWSTranscribeSTTSettings
|
||||
_settings: AWSTranscribeSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -148,6 +148,7 @@ class AWSPollyTTSService(TTSService):
|
||||
options including prosody controls.
|
||||
"""
|
||||
|
||||
Settings = AWSPollyTTSSettings
|
||||
_settings: AWSPollyTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -382,6 +383,8 @@ class PollyTTSService(AWSPollyTTSService):
|
||||
|
||||
"""
|
||||
|
||||
Settings = AWSPollyTTSSettings
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
"""Initialize the deprecated PollyTTSService.
|
||||
|
||||
|
||||
@@ -43,6 +43,7 @@ class AzureImageGenServiceREST(ImageGenService):
|
||||
and automatic image download and processing.
|
||||
"""
|
||||
|
||||
Settings = AzureImageGenSettings
|
||||
_settings: AzureImageGenSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -31,6 +31,8 @@ class AzureLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = AzureLLMSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -35,6 +35,7 @@ class AzureRealtimeLLMService(OpenAIRealtimeLLMService):
|
||||
real-time audio and text communication capabilities as the base OpenAI service.
|
||||
"""
|
||||
|
||||
Settings = AzureRealtimeLLMSettings
|
||||
_settings: AzureRealtimeLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -66,6 +66,7 @@ class AzureSTTService(STTService):
|
||||
provides real-time transcription results with timing information.
|
||||
"""
|
||||
|
||||
Settings = AzureSTTSettings
|
||||
_settings: AzureSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -246,6 +246,8 @@ class AzureTTSService(TTSService, AzureBaseTTSService):
|
||||
available for lower latency playback and accurate word-level synchronization.
|
||||
"""
|
||||
|
||||
Settings = AzureTTSSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
@@ -749,6 +751,8 @@ class AzureHttpTTSService(TTSService, AzureBaseTTSService):
|
||||
required and simpler integration is preferred.
|
||||
"""
|
||||
|
||||
Settings = AzureTTSSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -168,6 +168,7 @@ class CambTTSService(TTSService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = CambTTSSettings
|
||||
_settings: CambTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -146,6 +146,7 @@ class CartesiaSTTService(WebsocketSTTService):
|
||||
See: https://docs.cartesia.ai/api-reference/stt/stt
|
||||
"""
|
||||
|
||||
Settings = CartesiaSTTSettings
|
||||
_settings: CartesiaSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -210,6 +210,7 @@ class CartesiaTTSService(WebsocketTTSService):
|
||||
customization options including generation configuration.
|
||||
"""
|
||||
|
||||
Settings = CartesiaTTSSettings
|
||||
_settings: CartesiaTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -681,6 +682,7 @@ class CartesiaHttpTTSService(TTSService):
|
||||
integration is preferred.
|
||||
"""
|
||||
|
||||
Settings = CartesiaTTSSettings
|
||||
_settings: CartesiaTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -31,6 +31,7 @@ class CerebrasLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = CerebrasLLMSettings
|
||||
_settings: CerebrasLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -115,6 +115,7 @@ class DeepgramFluxSTTService(WebsocketSTTService):
|
||||
...
|
||||
"""
|
||||
|
||||
Settings = DeepgramFluxSTTSettings
|
||||
_settings: DeepgramFluxSTTSettings
|
||||
_CONFIGURE_FIELDS = {"keyterm", "eot_threshold", "eager_eot_threshold", "eot_timeout_ms"}
|
||||
|
||||
|
||||
@@ -78,6 +78,7 @@ class DeepgramSageMakerSTTService(STTService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = DeepgramSageMakerSTTSettings
|
||||
_settings: DeepgramSageMakerSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -67,6 +67,7 @@ class DeepgramSageMakerTTSService(TTSService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = DeepgramSageMakerTTSSettings
|
||||
_settings: DeepgramSageMakerTTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -266,6 +266,7 @@ class DeepgramSTTService(STTService):
|
||||
...
|
||||
"""
|
||||
|
||||
Settings = DeepgramSTTSettings
|
||||
_settings: DeepgramSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -58,6 +58,7 @@ class DeepgramTTSService(WebsocketTTSService):
|
||||
message for conversational AI use cases.
|
||||
"""
|
||||
|
||||
Settings = DeepgramTTSSettings
|
||||
_settings: DeepgramTTSSettings
|
||||
|
||||
SUPPORTED_ENCODINGS = ("linear16", "mulaw", "alaw")
|
||||
@@ -381,6 +382,7 @@ class DeepgramHttpTTSService(TTSService):
|
||||
configurable sample rates and quality settings.
|
||||
"""
|
||||
|
||||
Settings = DeepgramTTSSettings
|
||||
_settings: DeepgramTTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -31,6 +31,7 @@ class DeepSeekLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = DeepSeekLLMSettings
|
||||
_settings: DeepSeekLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -216,6 +216,7 @@ class ElevenLabsSTTService(SegmentedSTTService):
|
||||
The service uploads audio files to ElevenLabs and receives transcription results directly.
|
||||
"""
|
||||
|
||||
Settings = ElevenLabsSTTSettings
|
||||
_settings: ElevenLabsSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -448,6 +449,7 @@ class ElevenLabsRealtimeSTTService(WebsocketSTTService):
|
||||
commit transcript segments, providing consistency with other STT services.
|
||||
"""
|
||||
|
||||
Settings = ElevenLabsRealtimeSTTSettings
|
||||
_settings: ElevenLabsRealtimeSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -316,6 +316,7 @@ class ElevenLabsTTSService(WebsocketTTSService):
|
||||
customization options including stability, similarity boost, and speed controls.
|
||||
"""
|
||||
|
||||
Settings = ElevenLabsTTSSettings
|
||||
_settings: ElevenLabsTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -904,6 +905,7 @@ class ElevenLabsHttpTTSService(TTSService):
|
||||
connection is not required or desired.
|
||||
"""
|
||||
|
||||
Settings = ElevenLabsHttpTTSSettings
|
||||
_settings: ElevenLabsHttpTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -70,6 +70,9 @@ class FalImageGenService(ImageGenService):
|
||||
parameters for image quality, safety, and format options.
|
||||
"""
|
||||
|
||||
Settings = FalImageGenSettings
|
||||
_settings: FalImageGenSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
"""Input parameters for Fal.ai image generation.
|
||||
|
||||
|
||||
@@ -155,6 +155,7 @@ class FalSTTService(SegmentedSTTService):
|
||||
segments. It inherits from SegmentedSTTService to handle audio buffering and speech detection.
|
||||
"""
|
||||
|
||||
Settings = FalSTTSettings
|
||||
_settings: FalSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -31,6 +31,7 @@ class FireworksLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = FireworksLLMSettings
|
||||
_settings: FireworksLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -84,6 +84,7 @@ class FishAudioTTSService(InterruptibleTTSService):
|
||||
audio generation with interruption handling.
|
||||
"""
|
||||
|
||||
Settings = FishAudioTTSSettings
|
||||
_settings: FishAudioTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -230,6 +230,7 @@ class GladiaSTTService(WebsocketSTTService):
|
||||
Use :class:`~pipecat.services.gladia.config.GladiaInputParams` directly instead.
|
||||
"""
|
||||
|
||||
Settings = GladiaSTTSettings
|
||||
_settings: GladiaSTTSettings
|
||||
|
||||
# Maintain backward compatibility
|
||||
|
||||
@@ -642,6 +642,7 @@ class GeminiLiveLLMService(LLMService):
|
||||
responses, and tool usage.
|
||||
"""
|
||||
|
||||
Settings = GeminiLiveLLMSettings
|
||||
_settings: GeminiLiveLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the Gemini one.
|
||||
|
||||
@@ -57,6 +57,7 @@ class GeminiLiveVertexLLMService(GeminiLiveLLMService):
|
||||
responses, and tool usage.
|
||||
"""
|
||||
|
||||
Settings = GeminiLiveVertexLLMSettings
|
||||
_settings: GeminiLiveVertexLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -59,6 +59,9 @@ class GoogleImageGenService(ImageGenService):
|
||||
prompting for enhanced control over generated content.
|
||||
"""
|
||||
|
||||
Settings = GoogleImageGenSettings
|
||||
_settings: GoogleImageGenSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
"""Configuration parameters for Google image generation.
|
||||
|
||||
@@ -75,8 +78,6 @@ class GoogleImageGenService(ImageGenService):
|
||||
model: str = Field(default="imagen-3.0-generate-002")
|
||||
negative_prompt: Optional[str] = Field(default=None)
|
||||
|
||||
_settings: GoogleImageGenSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -743,6 +743,7 @@ class GoogleLLMService(LLMService):
|
||||
expected by the Google AI model.
|
||||
"""
|
||||
|
||||
Settings = GoogleLLMSettings
|
||||
_settings: GoogleLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the Gemini one.
|
||||
|
||||
@@ -58,6 +58,7 @@ class GoogleLLMOpenAIBetaService(OpenAILLMService):
|
||||
https://ai.google.dev/gemini-api/docs/openai
|
||||
"""
|
||||
|
||||
Settings = GoogleOpenAILLMSettings
|
||||
_settings: GoogleOpenAILLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -59,6 +59,7 @@ class GoogleVertexLLMService(GoogleLLMService):
|
||||
https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference
|
||||
"""
|
||||
|
||||
Settings = GoogleVertexLLMSettings
|
||||
_settings: GoogleVertexLLMSettings
|
||||
|
||||
class InputParams(GoogleLLMService.InputParams):
|
||||
|
||||
@@ -414,6 +414,7 @@ class GoogleSTTService(STTService):
|
||||
ValueError: If project ID is not found in credentials.
|
||||
"""
|
||||
|
||||
Settings = GoogleSTTSettings
|
||||
_settings: GoogleSTTSettings
|
||||
|
||||
# Google Cloud's STT service has a connection time limit of 5 minutes per stream.
|
||||
|
||||
@@ -558,6 +558,7 @@ class GoogleHttpTTSService(TTSService):
|
||||
Chirp and Journey voices don't support SSML and will use plain text input.
|
||||
"""
|
||||
|
||||
Settings = GoogleHttpTTSSettings
|
||||
_settings: GoogleHttpTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -1020,6 +1021,7 @@ class GoogleTTSService(GoogleBaseTTSService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = GoogleTTSSettings
|
||||
_settings: GoogleTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -1198,6 +1200,7 @@ class GeminiTTSService(GoogleBaseTTSService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = GeminiTTSSettings
|
||||
_settings: GeminiTTSSettings
|
||||
|
||||
GOOGLE_SAMPLE_RATE = 24000 # Google TTS always outputs at 24kHz
|
||||
|
||||
@@ -88,6 +88,7 @@ class GradiumSTTService(WebsocketSTTService):
|
||||
for audio processing and connection management.
|
||||
"""
|
||||
|
||||
Settings = GradiumSTTSettings
|
||||
_settings: GradiumSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -47,6 +47,7 @@ class GradiumTTSSettings(TTSSettings):
|
||||
class GradiumTTSService(WebsocketTTSService):
|
||||
"""Text-to-Speech service using Gradium's websocket API."""
|
||||
|
||||
Settings = GradiumTTSSettings
|
||||
_settings: GradiumTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -86,6 +86,7 @@ class GrokLLMService(OpenAILLMService):
|
||||
processing and reports final totals.
|
||||
"""
|
||||
|
||||
Settings = GrokLLMSettings
|
||||
_settings: GrokLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -202,6 +202,7 @@ class GrokRealtimeLLMService(LLMService):
|
||||
- Server-side VAD (Voice Activity Detection)
|
||||
"""
|
||||
|
||||
Settings = GrokRealtimeLLMSettings
|
||||
_settings: GrokRealtimeLLMSettings
|
||||
|
||||
# Use the Grok-specific adapter
|
||||
|
||||
@@ -30,6 +30,7 @@ class GroqLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = GroqLLMSettings
|
||||
_settings: GroqLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -37,6 +37,7 @@ class GroqSTTService(BaseWhisperSTTService):
|
||||
set via the api_key parameter or GROQ_API_KEY environment variable.
|
||||
"""
|
||||
|
||||
Settings = GroqSTTSettings
|
||||
_settings: GroqSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -51,6 +51,7 @@ class GroqTTSService(TTSService):
|
||||
and output formats.
|
||||
"""
|
||||
|
||||
Settings = GroqTTSSettings
|
||||
_settings: GroqTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -82,6 +82,9 @@ class HeyGenVideoService(AIService):
|
||||
Defaults to using the "Shawn_Therapist_public" avatar with "v2" version.
|
||||
"""
|
||||
|
||||
Settings = HeyGenVideoSettings
|
||||
_settings: HeyGenVideoSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -78,6 +78,7 @@ class HumeTTSService(TTSService):
|
||||
- Provides metrics for Time To First Byte (TTFB) and TTS usage.
|
||||
"""
|
||||
|
||||
Settings = HumeTTSSettings
|
||||
_settings: HumeTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -100,6 +100,7 @@ class InworldHttpTTSService(TTSService):
|
||||
Outputs LINEAR16 audio at configurable sample rates with word-level timestamps.
|
||||
"""
|
||||
|
||||
Settings = InworldTTSSettings
|
||||
_settings: InworldTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -487,6 +488,7 @@ class InworldTTSService(WebsocketTTSService):
|
||||
with word-level timestamps.
|
||||
"""
|
||||
|
||||
Settings = InworldTTSSettings
|
||||
_settings: InworldTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -101,6 +101,7 @@ class KokoroTTSService(TTSService):
|
||||
Automatically downloads model files on first use.
|
||||
"""
|
||||
|
||||
Settings = KokoroTTSSettings
|
||||
_settings: KokoroTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -88,6 +88,7 @@ class LmntTTSService(InterruptibleTTSService):
|
||||
language settings.
|
||||
"""
|
||||
|
||||
Settings = LmntTTSSettings
|
||||
_settings: LmntTTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -140,6 +140,7 @@ class MiniMaxHttpTTSService(TTSService):
|
||||
https://www.minimax.io/platform/document/T2A%20V2?key=66719005a427f0c8a5701643
|
||||
"""
|
||||
|
||||
Settings = MiniMaxTTSSettings
|
||||
_settings: MiniMaxTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -33,6 +33,7 @@ class MistralLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = MistralLLMSettings
|
||||
_settings: MistralLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -79,6 +79,9 @@ class MoondreamService(VisionService):
|
||||
including CUDA, MPS, and Intel XPU.
|
||||
"""
|
||||
|
||||
Settings = MoondreamSettings
|
||||
_settings: MoondreamSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -91,6 +91,7 @@ class NeuphonicTTSService(InterruptibleTTSService):
|
||||
parameters for high-quality speech generation.
|
||||
"""
|
||||
|
||||
Settings = NeuphonicTTSSettings
|
||||
_settings: NeuphonicTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -430,6 +431,7 @@ class NeuphonicHttpTTSService(TTSService):
|
||||
HTTP-based communication over WebSocket connections.
|
||||
"""
|
||||
|
||||
Settings = NeuphonicTTSSettings
|
||||
_settings: NeuphonicTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -36,6 +36,7 @@ class NvidiaLLMService(OpenAILLMService):
|
||||
in token usage reporting between NIM (incremental) and OpenAI (final summary).
|
||||
"""
|
||||
|
||||
Settings = NvidiaLLMSettings
|
||||
_settings: NvidiaLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -125,6 +125,7 @@ class NvidiaSTTService(STTService):
|
||||
processing for low-latency applications.
|
||||
"""
|
||||
|
||||
Settings = NvidiaSTTSettings
|
||||
_settings: NvidiaSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -439,6 +440,7 @@ class NvidiaSegmentedSTTService(SegmentedSTTService):
|
||||
audio buffering and speech detection.
|
||||
"""
|
||||
|
||||
Settings = NvidiaSegmentedSTTSettings
|
||||
_settings: NvidiaSegmentedSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -61,6 +61,7 @@ class NvidiaTTSService(TTSService):
|
||||
configurable quality settings.
|
||||
"""
|
||||
|
||||
Settings = NvidiaTTSSettings
|
||||
_settings: NvidiaTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -30,6 +30,7 @@ class OLLamaLLMService(OpenAILLMService):
|
||||
providing a compatible interface for running large language models locally.
|
||||
"""
|
||||
|
||||
Settings = OllamaLLMSettings
|
||||
_settings: OllamaLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -68,6 +68,7 @@ class BaseOpenAILLMService(LLMService):
|
||||
configurations.
|
||||
"""
|
||||
|
||||
Settings = OpenAILLMSettings
|
||||
_settings: OpenAILLMSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -48,6 +48,7 @@ class OpenAIImageGenService(ImageGenService):
|
||||
with configurable quality and style parameters.
|
||||
"""
|
||||
|
||||
Settings = OpenAIImageGenSettings
|
||||
_settings: OpenAIImageGenSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -211,6 +211,7 @@ class OpenAIRealtimeLLMService(LLMService):
|
||||
management, and real-time transcription.
|
||||
"""
|
||||
|
||||
Settings = OpenAIRealtimeLLMSettings
|
||||
_settings: OpenAIRealtimeLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the OpenAIRealtimeLLMAdapter one.
|
||||
|
||||
@@ -69,6 +69,7 @@ class OpenAISTTService(BaseWhisperSTTService):
|
||||
set via the api_key parameter or OPENAI_API_KEY environment variable.
|
||||
"""
|
||||
|
||||
Settings = OpenAISTTSettings
|
||||
_settings: OpenAISTTSettings
|
||||
|
||||
def __init__(
|
||||
@@ -224,6 +225,7 @@ class OpenAIRealtimeSTTService(WebsocketSTTService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = OpenAIRealtimeSTTSettings
|
||||
_settings: OpenAIRealtimeSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -81,6 +81,7 @@ class OpenAITTSService(TTSService):
|
||||
speech synthesis with streaming audio output.
|
||||
"""
|
||||
|
||||
Settings = OpenAITTSSettings
|
||||
_settings: OpenAITTSSettings
|
||||
|
||||
OPENAI_SAMPLE_RATE = 24000 # OpenAI TTS always outputs at 24kHz
|
||||
|
||||
@@ -42,6 +42,7 @@ class AzureRealtimeBetaLLMService(OpenAIRealtimeBetaLLMService):
|
||||
real-time audio and text communication capabilities as the base OpenAI service.
|
||||
"""
|
||||
|
||||
Settings = AzureRealtimeBetaLLMSettings
|
||||
_settings: AzureRealtimeBetaLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -111,6 +111,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
|
||||
management, and real-time transcription.
|
||||
"""
|
||||
|
||||
Settings = OpenAIRealtimeBetaLLMSettings
|
||||
_settings: OpenAIRealtimeBetaLLMSettings
|
||||
|
||||
# Overriding the default adapter to use the OpenAIRealtimeLLMAdapter one.
|
||||
|
||||
@@ -43,6 +43,7 @@ class OpenPipeLLMService(OpenAILLMService):
|
||||
for model training and evaluation.
|
||||
"""
|
||||
|
||||
Settings = OpenPipeLLMSettings
|
||||
_settings: OpenPipeLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -34,6 +34,7 @@ class OpenRouterLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = OpenRouterLLMSettings
|
||||
_settings: OpenRouterLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -38,6 +38,7 @@ class PerplexityLLMService(OpenAILLMService):
|
||||
in token usage reporting between Perplexity (incremental) and OpenAI (final summary).
|
||||
"""
|
||||
|
||||
Settings = PerplexityLLMSettings
|
||||
_settings: PerplexityLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -46,6 +46,7 @@ class PiperTTSService(TTSService):
|
||||
match the configured sample rate.
|
||||
"""
|
||||
|
||||
Settings = PiperTTSSettings
|
||||
_settings: PiperTTSSettings
|
||||
|
||||
def __init__(
|
||||
@@ -199,6 +200,7 @@ class PiperHttpTTSService(TTSService):
|
||||
rates and automatic WAV header removal.
|
||||
"""
|
||||
|
||||
Settings = PiperHttpTTSSettings
|
||||
_settings: PiperHttpTTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -30,6 +30,7 @@ class QwenLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = QwenLLMSettings
|
||||
_settings: QwenLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -51,6 +51,7 @@ class ResembleAITTSService(WebsocketTTSService):
|
||||
multiple simultaneous synthesis requests with proper interruption support.
|
||||
"""
|
||||
|
||||
Settings = ResembleAITTSSettings
|
||||
_settings: ResembleAITTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -131,6 +131,7 @@ class RimeTTSService(WebsocketTTSService):
|
||||
within a turn.
|
||||
"""
|
||||
|
||||
Settings = RimeTTSSettings
|
||||
_settings: RimeTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -661,6 +662,7 @@ class RimeHttpTTSService(TTSService):
|
||||
Suitable for use cases where streaming is not required.
|
||||
"""
|
||||
|
||||
Settings = RimeTTSSettings
|
||||
_settings: RimeTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -885,6 +887,7 @@ class RimeNonJsonTTSService(InterruptibleTTSService):
|
||||
accepts and returns non-JSON messages.
|
||||
"""
|
||||
|
||||
Settings = RimeNonJsonTTSSettings
|
||||
_settings: RimeNonJsonTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -42,6 +42,7 @@ class SambaNovaLLMService(OpenAILLMService): # type: ignore
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = SambaNovaLLMSettings
|
||||
_settings: SambaNovaLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -35,6 +35,8 @@ class SambaNovaSTTService(BaseWhisperSTTService): # type: ignore
|
||||
Requires a SambaNova API key set via the api_key parameter or SAMBANOVA_API_KEY environment variable.
|
||||
"""
|
||||
|
||||
Settings = SambaNovaSTTSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -171,6 +171,7 @@ class SarvamSTTService(STTService):
|
||||
...
|
||||
"""
|
||||
|
||||
Settings = SarvamSTTSettings
|
||||
_settings: SarvamSTTSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -351,6 +351,7 @@ class SarvamHttpTTSService(TTSService):
|
||||
)
|
||||
"""
|
||||
|
||||
Settings = SarvamHttpTTSSettings
|
||||
_settings: SarvamHttpTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
@@ -717,6 +718,7 @@ class SarvamTTSService(InterruptibleTTSService):
|
||||
See https://docs.sarvam.ai/api-reference-docs/text-to-speech/stream for API details.
|
||||
"""
|
||||
|
||||
Settings = SarvamTTSSettings
|
||||
_settings: SarvamTTSSettings
|
||||
|
||||
class InputParams(BaseModel):
|
||||
|
||||
@@ -174,6 +174,7 @@ class SonioxSTTService(WebsocketSTTService):
|
||||
For complete API documentation, see: https://soniox.com/docs/speech-to-text/api-reference/websocket-api
|
||||
"""
|
||||
|
||||
Settings = SonioxSTTSettings
|
||||
_settings: SonioxSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -175,6 +175,7 @@ class SpeechmaticsSTTService(STTService):
|
||||
...
|
||||
"""
|
||||
|
||||
Settings = SpeechmaticsSTTSettings
|
||||
_settings: SpeechmaticsSTTSettings
|
||||
|
||||
# Export related classes as class attributes
|
||||
|
||||
@@ -53,6 +53,7 @@ class SpeechmaticsTTSService(TTSService):
|
||||
It converts text to speech and returns raw PCM audio data for real-time playback.
|
||||
"""
|
||||
|
||||
Settings = SpeechmaticsTTSSettings
|
||||
_settings: SpeechmaticsTTSSettings
|
||||
|
||||
SPEECHMATICS_SAMPLE_RATE = 16000
|
||||
|
||||
@@ -59,6 +59,9 @@ class TavusVideoService(AIService):
|
||||
- User room: Contains the Pipecat Bot and the user
|
||||
"""
|
||||
|
||||
Settings = TavusVideoSettings
|
||||
_settings: TavusVideoSettings
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
|
||||
@@ -30,6 +30,7 @@ class TogetherLLMService(OpenAILLMService):
|
||||
maintaining full compatibility with OpenAI's interface and functionality.
|
||||
"""
|
||||
|
||||
Settings = TogetherLLMSettings
|
||||
_settings: TogetherLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -166,6 +166,7 @@ class UltravoxRealtimeLLMService(LLMService):
|
||||
by the model and may not always align with its understanding of user input.
|
||||
"""
|
||||
|
||||
Settings = UltravoxRealtimeLLMSettings
|
||||
_settings: UltravoxRealtimeLLMSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -122,6 +122,7 @@ class BaseWhisperSTTService(SegmentedSTTService):
|
||||
including metrics generation and error handling.
|
||||
"""
|
||||
|
||||
Settings = BaseWhisperSTTSettings
|
||||
_settings: BaseWhisperSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -207,6 +207,7 @@ class WhisperSTTService(SegmentedSTTService):
|
||||
segments. It supports multiple languages and various model sizes.
|
||||
"""
|
||||
|
||||
Settings = WhisperSTTSettings
|
||||
_settings: WhisperSTTSettings
|
||||
|
||||
def __init__(
|
||||
@@ -380,6 +381,7 @@ class WhisperSTTServiceMLX(WhisperSTTService):
|
||||
segments. It's optimized for Apple Silicon and supports multiple languages and quantizations.
|
||||
"""
|
||||
|
||||
Settings = WhisperMLXSTTSettings
|
||||
_settings: WhisperMLXSTTSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
@@ -83,6 +83,7 @@ class XTTSService(TTSService):
|
||||
studio speakers configuration.
|
||||
"""
|
||||
|
||||
Settings = XTTSTTSSettings
|
||||
_settings: XTTSTTSSettings
|
||||
|
||||
def __init__(
|
||||
|
||||
Reference in New Issue
Block a user