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

Merge pull request #4220 from pipecat-ai/mb/more-service-deprecations

Browse Source 
Remove more deprecated service parameters and shims
This commit is contained in:
Mark Backman
2026-04-01 22:23:39 -04:00
committed by GitHub
parent a6013ba437 5ce46df599
commit 2426f80789
19 changed files with 94 additions and 460 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4220.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Fixed `CartesiaTTSService` failing with "Context has closed" errors when switching voice, model, or language via `TTSUpdateSettingsFrame`. The service now automatically flushes the current audio context and opens a fresh one when these settings change.

13
changelog/4220.removed.md Normal file
View File

@@ -0,0 +1,13 @@
- ⚠️ Removed deprecated service parameters and shims that have been replaced by the `settings=Service.Settings(...)` pattern or direct `__init__` parameters:
- `PollyTTSService` alias (use `AWSTTSService`)
- `TTSService`: `text_aggregator`, `text_filter` init params
- `AWSNovaSonicLLMService`: `send_transcription_frames` init param
- `DeepgramSTTService`: `url` init param (use `base_url`)
- `FishAudioTTSService`: `model` init param (use `reference_id` or `settings`)
- `GladiaSTTService`: `language` and `confidence` from `GladiaInputParams`, `InputParams` class alias
- `GeminiTTSService`: `api_key` init param
- `GeminiLiveLLMService`: `base_url` init param (use `http_options`)
- `GoogleVertexLLMService`: `InputParams` class with `location`/`project_id` fields (use direct init params); `project_id` is now required, `location` defaults to `"us-east4"`
- `MiniMaxHttpTTSService`: `english_normalization` from `InputParams` (use `text_normalization`)
- `SimliVideoService`: `simli_config` init param (use `api_key`/`face_id`), `use_turn_server` init param; `api_key` and `face_id` are now required
- `AnthropicLLMService`: `enable_prompt_caching_beta` from `InputParams` (use `enable_prompt_caching`)

28
examples/features/features-pattern-pair-voice-switching.py
View File

@@ -45,7 +45,7 @@ from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
from pipecat.frames.frames import LLMRunFrame, TTSUpdateSettingsFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -54,6 +54,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.processors.aggregators.llm_text_processor import LLMTextProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
@@ -100,39 +101,43 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
# Create pattern pair aggregator for voice switching
pattern_aggregator = PatternPairAggregator()
llm_text_aggregator = PatternPairAggregator()
# Add pattern for voice switching
pattern_aggregator.add_pattern(
llm_text_aggregator.add_pattern(
type="voice",
start_pattern="<voice>",
end_pattern="</voice>",
action=MatchAction.REMOVE, # Remove tags from final text
action=MatchAction.AGGREGATE,
)
# Register handler for voice switching
async def on_voice_tag(match: PatternMatch):
voice_name = match.text.strip().lower()
if voice_name in VOICE_IDS:
# First flush any existing audio to finish the current context
await tts.flush_audio()
# Then set the new voice
await tts.set_voice(VOICE_IDS[voice_name])
await llm_text_processor.push_frame(
TTSUpdateSettingsFrame(
delta=CartesiaTTSService.Settings(voice=VOICE_IDS[voice_name])
)
)
logger.info(f"Switched to {voice_name} voice")
else:
logger.warning(f"Unknown voice: {voice_name}")
pattern_aggregator.on_pattern_match("voice", on_voice_tag)
llm_text_aggregator.on_pattern_match("voice", on_voice_tag)
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
# Process LLM text through the pattern aggregator before TTS
llm_text_processor = LLMTextProcessor(text_aggregator=llm_text_aggregator)
# Initialize TTS with narrator voice as default
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSService.Settings(
voice=VOICE_IDS["narrator"],
),
text_aggregator=pattern_aggregator,
skip_aggregator_types=["voice"], # Skip voice tags in TTS speech
)
# System prompt for storytelling with voice switching
@@ -204,7 +209,8 @@ Remember: Use narrator voice for EVERYTHING except the actual quoted dialogue.""
stt,
user_aggregator,
llm,
tts, # TTS with pattern aggregator
llm_text_processor,
tts,
transport.output(),
assistant_aggregator,
]

36
src/pipecat/services/anthropic/llm.py
View File

@@ -130,11 +130,6 @@ class AnthropicLLMService(LLMService):
Parameters:
enable_prompt_caching: Whether to enable the prompt caching feature.
enable_prompt_caching_beta (deprecated): Whether to enable the beta prompt caching feature.
.. deprecated:: 0.0.84
Use the `enable_prompt_caching` parameter instead.
max_tokens: Maximum tokens to generate. Must be at least 1.
temperature: Sampling temperature between 0.0 and 1.0.
top_k: Top-k sampling parameter.
@@ -147,7 +142,6 @@ class AnthropicLLMService(LLMService):
"""
enable_prompt_caching: Optional[bool] = None
enable_prompt_caching_beta: Optional[bool] = None
max_tokens: Optional[int] = Field(default_factory=lambda: 4096, ge=1)
temperature: Optional[float] = Field(default_factory=lambda: NOT_GIVEN, ge=0.0, le=1.0)
top_k: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=0)
@@ -157,18 +151,6 @@ class AnthropicLLMService(LLMService):
)
extra: Optional[Dict[str, Any]] = Field(default_factory=dict)
def model_post_init(self, __context):
"""Post-initialization to handle deprecated parameters."""
if self.enable_prompt_caching_beta is not None:
import warnings
warnings.simplefilter("always")
warnings.warn(
"enable_prompt_caching_beta is deprecated. Use enable_prompt_caching instead.",
DeprecationWarning,
stacklevel=2,
)
def __init__(
self,
*,
@@ -237,22 +219,8 @@ class AnthropicLLMService(LLMService):
default_settings.thinking = params.thinking
if isinstance(params.extra, dict):
default_settings.extra = params.extra
# Handle enable_prompt_caching / enable_prompt_caching_beta
enable_prompt_caching = params.enable_prompt_caching
if params.enable_prompt_caching_beta is not None:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"enable_prompt_caching_beta is deprecated. "
"Use enable_prompt_caching instead.",
DeprecationWarning,
stacklevel=2,
)
if enable_prompt_caching is None:
enable_prompt_caching = params.enable_prompt_caching_beta
default_settings.enable_prompt_caching = enable_prompt_caching or False
if params.enable_prompt_caching is not None:
default_settings.enable_prompt_caching = params.enable_prompt_caching
# 4. Apply settings delta (canonical API, always wins)
if settings is not None:

19
src/pipecat/services/aws/nova_sonic/llm.py
View File

@@ -258,7 +258,6 @@ class AWSNovaSonicLLMService(LLMService):
settings: Optional[Settings] = None,
system_instruction: Optional[str] = None,
tools: Optional[ToolsSchema] = None,
send_transcription_frames: bool = True,
**kwargs,
):
"""Initializes the AWS Nova Sonic LLM service.
@@ -302,12 +301,6 @@ class AWSNovaSonicLLMService(LLMService):
.. deprecated:: 0.0.105
Use ``settings=AWSNovaSonicLLMService.Settings(system_instruction=...)`` instead.
tools: Available tools/functions for the model to use.
send_transcription_frames: Whether to emit transcription frames.
.. deprecated:: 0.0.91
This parameter is deprecated and will be removed in a future version.
Transcription frames are always sent.
**kwargs: Additional arguments passed to the parent LLMService.
"""
# 1. Initialize default_settings with hardcoded defaults
@@ -391,18 +384,6 @@ class AWSNovaSonicLLMService(LLMService):
)
self._settings.endpointing_sensitivity = None
if not send_transcription_frames:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"`send_transcription_frames` is deprecated and will be removed in a future version. "
"Transcription frames are always sent.",
DeprecationWarning,
stacklevel=2,
)
self._context: Optional[LLMContext] = None
self._stream: Optional[
DuplexEventStream[

28
src/pipecat/services/aws/tts.py
View File

@@ -369,31 +369,3 @@ class AWSPollyTTSService(TTSService):
except (BotoCoreError, ClientError) as error:
error_message = f"AWS Polly TTS error: {str(error)}"
yield ErrorFrame(error=error_message)
class PollyTTSService(AWSPollyTTSService):
"""Deprecated alias for AWSPollyTTSService.
.. deprecated:: 0.0.67
`PollyTTSService` is deprecated, use `AWSPollyTTSService` instead.
"""
Settings = AWSPollyTTSSettings
def __init__(self, **kwargs):
"""Initialize the deprecated PollyTTSService.
Args:
**kwargs: All arguments passed to AWSPollyTTSService.
"""
super().__init__(**kwargs)
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"'PollyTTSService' is deprecated, use 'AWSPollyTTSService' instead.",
DeprecationWarning,
)

55
src/pipecat/services/cartesia/tts.py
View File

@@ -10,7 +10,7 @@ import base64
import json
from dataclasses import dataclass, field
from enum import Enum
from typing import AsyncGenerator, List, Optional
from typing import Any, AsyncGenerator, List, Optional
import aiohttp
from loguru import logger
@@ -28,7 +28,6 @@ from pipecat.frames.frames import (
from pipecat.services.settings import NOT_GIVEN, TTSSettings, _NotGiven
from pipecat.services.tts_service import TextAggregationMode, TTSService, WebsocketTTSService
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.skip_tags_aggregator import SkipTagsAggregator
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -240,7 +239,6 @@ class CartesiaTTSService(WebsocketTTSService):
container: str = "raw",
params: Optional[InputParams] = None,
settings: Optional[Settings] = None,
text_aggregator: Optional[BaseTextAggregator] = None,
text_aggregation_mode: Optional[TextAggregationMode] = None,
aggregate_sentences: Optional[bool] = None,
**kwargs,
@@ -271,11 +269,6 @@ class CartesiaTTSService(WebsocketTTSService):
settings: Runtime-updatable settings. When provided alongside deprecated
parameters, ``settings`` values take precedence.
text_aggregator: Custom text aggregator for processing input text.
.. deprecated:: 0.0.95
Use an LLMTextProcessor before the TTSService for custom text aggregation.
text_aggregation_mode: How to aggregate incoming text before synthesis.
aggregate_sentences: Whether to aggregate sentences within the TTSService.
@@ -337,20 +330,18 @@ class CartesiaTTSService(WebsocketTTSService):
pause_frame_processing=False,
sample_rate=sample_rate,
push_start_frame=True,
text_aggregator=text_aggregator,
settings=default_settings,
**kwargs,
)
if not text_aggregator:
# Always skip tags added for spelled-out text
# Note: This is primarily to support backwards compatibility.
# The preferred way of taking advantage of Cartesia SSML Tags is
# to use an LLMTextProcessor and/or a text_transformer to identify
# and insert these tags for the purpose of the TTS service alone.
self._text_aggregator = SkipTagsAggregator(
[("<spell>", "</spell>")], aggregation_type=self._text_aggregation_mode
)
# Always skip tags added for spelled-out text
# Note: This is primarily to support backwards compatibility.
# The preferred way of taking advantage of Cartesia SSML Tags is
# to use an LLMTextProcessor and/or a text_transformer to identify
# and insert these tags for the purpose of the TTS service alone.
self._text_aggregator = SkipTagsAggregator(
[("<spell>", "</spell>")], aggregation_type=self._text_aggregation_mode
)
self._api_key = api_key
self._cartesia_version = cartesia_version
@@ -599,6 +590,34 @@ class CartesiaTTSService(WebsocketTTSService):
msg = self._build_msg(text="", continue_transcript=False, context_id=flush_id)
await self._websocket.send(msg)
async def _update_settings(self, delta: CartesiaTTSSettings) -> dict[str, Any]:
"""Apply a TTS settings delta, flushing the context if needed.
Voice, model, and language are locked per Cartesia context. If any of
these change, the current context is flushed so the next sentence opens
a fresh one with the updated settings.
Args:
delta: A TTS settings delta.
Returns:
Dict mapping changed field names to their previous values.
"""
changed = await super()._update_settings(delta)
if not changed:
return changed
if changed.keys() & {"voice", "model", "language"}:
if self._turn_context_id and self.audio_context_available(self._turn_context_id):
await self.flush_audio(context_id=self._turn_context_id)
# Assign a new turn context ID so subsequent sentences in this
# turn open a new Cartesia context with the updated settings.
if self._turn_context_id:
self._turn_context_id = None
self._turn_context_id = self.create_context_id()
return changed
async def _process_messages(self):
async for message in self._get_websocket():
msg = json.loads(message)

17
src/pipecat/services/deepgram/stt.py
View File

@@ -314,7 +314,6 @@ class DeepgramSTTService(STTService):
self,
*,
api_key: str,
url: str = "",
base_url: str = "",
encoding: str = "linear16",
channels: int = 1,
@@ -335,11 +334,6 @@ class DeepgramSTTService(STTService):
Args:
api_key: Deepgram API key for authentication.
url: Custom Deepgram API base URL.
.. deprecated:: 0.0.64
Parameter `url` is deprecated, use `base_url` instead.
base_url: Custom Deepgram API base URL.
encoding: Audio encoding format. Defaults to "linear16".
channels: Number of audio channels. Defaults to 1.
@@ -374,17 +368,6 @@ class DeepgramSTTService(STTService):
Note:
The `vad_events` option in LiveOptions is deprecated as of version 0.0.99 and will be removed in a future version. Please use the Silero VAD instead.
"""
if url:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'url' is deprecated, use 'base_url' instead.",
DeprecationWarning,
)
base_url = url
# 1. Initialize default_settings with hardcoded defaults
default_settings = self.Settings(
model="nova-3-general",

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

@@ -110,7 +110,6 @@ class FishAudioTTSService(InterruptibleTTSService):
*,
api_key: str,
reference_id: Optional[str] = None, # This is the voice ID
model: Optional[str] = None, # Deprecated
model_id: Optional[str] = None,
output_format: FishAudioOutputFormat = "pcm",
sample_rate: Optional[int] = None,
@@ -127,12 +126,6 @@ class FishAudioTTSService(InterruptibleTTSService):
.. deprecated:: 0.0.105
Use ``settings=FishAudioTTSService.Settings(voice=...)`` instead.
model: Deprecated. Reference ID of the voice model to use for synthesis.
.. deprecated:: 0.0.74
The ``model`` parameter is deprecated and will be removed in version 0.1.0.
Use ``reference_id`` instead to specify the voice model.
model_id: Specify which Fish Audio TTS model to use (e.g. "s1").
.. deprecated:: 0.0.105
@@ -149,25 +142,6 @@ class FishAudioTTSService(InterruptibleTTSService):
parameters, ``settings`` values take precedence.
**kwargs: Additional arguments passed to the parent service.
"""
# Validation for model and reference_id parameters
if model and reference_id:
raise ValueError(
"Cannot specify both 'model' and 'reference_id'. Use 'reference_id' only."
)
if model:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'model' is deprecated and will be removed in a future version. "
"Use 'reference_id' instead.",
DeprecationWarning,
stacklevel=2,
)
reference_id = model
# 1. Initialize default_settings with hardcoded defaults
default_settings = self.Settings(
model="s2-pro",

9
src/pipecat/services/gladia/config.py
View File

@@ -10,8 +10,6 @@ from typing import Any, Dict, List, Optional, Union
from pydantic import BaseModel
from pipecat.transcriptions.language import Language
class LanguageConfig(BaseModel):
"""Configuration for language detection and handling.
@@ -163,12 +161,6 @@ class GladiaInputParams(BaseModel):
custom_metadata: Additional metadata to include with requests
endpointing: Silence duration in seconds to mark end of speech
maximum_duration_without_endpointing: Maximum utterance duration without silence
language: Language code for transcription
.. deprecated:: 0.0.62
The 'language' parameter is deprecated and will be removed in a future version.
Use 'language_config' instead.
language_config: Detailed language configuration
pre_processing: Audio pre-processing options
realtime_processing: Real-time processing features
@@ -184,7 +176,6 @@ class GladiaInputParams(BaseModel):
custom_metadata: Optional[Dict[str, Any]] = None
endpointing: Optional[float] = None
maximum_duration_without_endpointing: Optional[int] = 5
language: Optional[Language] = None # Deprecated
language_config: Optional[LanguageConfig] = None
pre_processing: Optional[PreProcessingConfig] = None
realtime_processing: Optional[RealtimeProcessingConfig] = None

55
src/pipecat/services/gladia/stt.py
View File

@@ -13,7 +13,6 @@ supporting multiple languages, custom vocabulary, and various audio processing o
import asyncio
import base64
import json
import warnings
from dataclasses import dataclass, field
from typing import Any, AsyncGenerator, Literal, Optional
@@ -171,21 +170,6 @@ def language_to_gladia_language(language: Language) -> Optional[str]:
# Deprecation warning for nested InputParams
class _InputParamsDescriptor:
"""Descriptor for backward compatibility with deprecation warning."""
def __get__(self, obj, objtype=None):
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"GladiaSTTService.InputParams is deprecated and will be removed in a future version. "
"Import and use GladiaInputParams directly instead.",
DeprecationWarning,
stacklevel=2,
)
return GladiaInputParams
@dataclass
class GladiaSTTSettings(STTSettings):
"""Settings for GladiaSTTService.
@@ -225,17 +209,11 @@ class GladiaSTTService(WebsocketSTTService):
Provides automatic reconnection, audio buffering, and comprehensive error handling.
For complete API documentation, see: https://docs.gladia.io/api-reference/v2/live/init
.. deprecated:: 0.0.62
Use :class:`~pipecat.services.gladia.config.GladiaInputParams` directly instead.
"""
Settings = GladiaSTTSettings
_settings: Settings
# Maintain backward compatibility
InputParams = _InputParamsDescriptor()
def __init__(
self,
*,
@@ -245,7 +223,6 @@ class GladiaSTTService(WebsocketSTTService):
encoding: str = "wav/pcm",
bit_depth: int = 16,
channels: int = 1,
confidence: Optional[float] = None,
sample_rate: Optional[int] = None,
model: Optional[str] = None,
params: Optional[GladiaInputParams] = None,
@@ -264,12 +241,6 @@ class GladiaSTTService(WebsocketSTTService):
encoding: Audio encoding format. Defaults to ``"wav/pcm"``.
bit_depth: Audio bit depth. Defaults to 16.
channels: Number of audio channels. Defaults to 1.
confidence: Minimum confidence threshold for transcriptions (0.0-1.0).
.. deprecated:: 0.0.86
The 'confidence' parameter is deprecated and will be removed in a future version.
No confidence threshold is applied.
sample_rate: Audio sample rate in Hz. If None, uses service default.
model: Model to use for transcription.
@@ -291,16 +262,6 @@ class GladiaSTTService(WebsocketSTTService):
Override for your deployment. See https://github.com/pipecat-ai/stt-benchmark
**kwargs: Additional arguments passed to the STTService parent class.
"""
if confidence:
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"The 'confidence' parameter is deprecated and will be removed in a future version. "
"No confidence threshold is applied.",
DeprecationWarning,
stacklevel=2,
)
# 1. Initialize default_settings with hardcoded defaults
default_settings = self.Settings(
model="solaria-1",
@@ -323,15 +284,6 @@ class GladiaSTTService(WebsocketSTTService):
# 3. Apply params overrides — only if settings not provided
if params is not None:
self._warn_init_param_moved_to_settings("params")
if params.language is not None:
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"The 'language' parameter is deprecated and will be removed in a future "
"version. Use 'language_config' instead.",
DeprecationWarning,
stacklevel=2,
)
if not settings:
# Extract init-only fields from params
if params.encoding is not None:
@@ -349,15 +301,8 @@ class GladiaSTTService(WebsocketSTTService):
default_settings.realtime_processing = params.realtime_processing
default_settings.messages_config = params.messages_config
default_settings.enable_vad = params.enable_vad
# Resolve deprecated language → language_config at init time
if params.language_config:
default_settings.language_config = params.language_config
elif params.language:
language_code = self.language_to_service_language(params.language)
if language_code:
default_settings.language_config = LanguageConfig(
languages=[language_code], code_switching=False
)
# 4. Apply settings delta (canonical API, always wins)
if settings is not None:

22
src/pipecat/services/google/gemini_live/llm.py
View File

@@ -380,7 +380,6 @@ class GeminiLiveLLMService(LLMService):
self,
*,
api_key: str,
base_url: Optional[str] = None,
model: Optional[str] = None,
voice_id: str = "Charon",
start_audio_paused: bool = False,
@@ -398,13 +397,6 @@ class GeminiLiveLLMService(LLMService):
Args:
api_key: Google AI API key for authentication.
base_url: API endpoint base URL. Defaults to the official Gemini Live endpoint.
.. deprecated:: 0.0.90
This parameter is deprecated and no longer has any effect.
Please use `http_options` to customize requests made by the
API client.
model: Model identifier to use.
.. deprecated:: 0.0.105
@@ -431,18 +423,6 @@ class GeminiLiveLLMService(LLMService):
http_options: HTTP options for the client.
**kwargs: Additional arguments passed to parent LLMService.
"""
# Check for deprecated parameter usage
if base_url is not None:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'base_url' is deprecated and no longer has any effect. Please use 'http_options' to customize requests made by the API client.",
DeprecationWarning,
stacklevel=2,
)
# 1. Initialize default_settings with hardcoded defaults
default_settings = self.Settings(
model="models/gemini-2.5-flash-native-audio-preview-12-2025",
@@ -515,13 +495,11 @@ class GeminiLiveLLMService(LLMService):
)
super().__init__(
base_url=base_url,
settings=default_settings,
**kwargs,
)
self._last_sent_time = 0
self._base_url = base_url
self._system_instruction_from_init = self._settings.system_instruction
self._tools_from_init = tools

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

@@ -755,7 +755,7 @@ class GoogleSTTService(STTService):
) -> None:
"""Update service options dynamically.
.. deprecated::
.. deprecated:: 0.0.104
Use ``STTUpdateSettingsFrame`` with ``GoogleSTTService.Settings(...)``
instead.

17
src/pipecat/services/google/tts.py
View File

@@ -16,7 +16,6 @@ for natural voice control and multi-speaker conversations.
import json
import os
import warnings
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -1259,7 +1258,6 @@ class GeminiTTSService(GoogleBaseTTSService):
def __init__(
self,
*,
api_key: Optional[str] = None,
model: Optional[str] = None,
credentials: Optional[str] = None,
credentials_path: Optional[str] = None,
@@ -1273,12 +1271,6 @@ class GeminiTTSService(GoogleBaseTTSService):
"""Initializes the Gemini TTS service.
Args:
api_key:
.. deprecated:: 0.0.95
The `api_key` parameter is deprecated. Use `credentials` or
`credentials_path` instead for Google Cloud authentication.
model: Gemini TTS model to use. Must be a TTS model like
"gemini-2.5-flash-tts" or "gemini-2.5-pro-tts".
@@ -1303,15 +1295,6 @@ class GeminiTTSService(GoogleBaseTTSService):
parameters, ``settings`` values take precedence.
**kwargs: Additional arguments passed to parent TTSService.
"""
# Handle deprecated api_key parameter
if api_key is not None:
warnings.warn(
"The 'api_key' parameter is deprecated and will be removed in a future version. "
"Use 'credentials' or 'credentials_path' instead for Google Cloud authentication.",
DeprecationWarning,
stacklevel=2,
)
if sample_rate and sample_rate != self.GOOGLE_SAMPLE_RATE:
logger.warning(
f"Google TTS only supports {self.GOOGLE_SAMPLE_RATE}Hz sample rate. "

78
src/pipecat/services/google/vertex/llm.py
View File

@@ -61,58 +61,14 @@ class GoogleVertexLLMService(GoogleLLMService):
Settings = GoogleVertexLLMSettings
_settings: Settings
class InputParams(GoogleLLMService.InputParams):
"""Input parameters specific to Vertex AI.
Parameters:
location: GCP region for Vertex AI endpoint (e.g., "us-east4").
.. deprecated:: 0.0.90
Use `location` as a direct argument to
`GoogleVertexLLMService.__init__()` instead.
project_id: Google Cloud project ID.
.. deprecated:: 0.0.90
Use `project_id` as a direct argument to
`GoogleVertexLLMService.__init__()` instead.
"""
# https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations
location: Optional[str] = None
project_id: Optional[str] = None
def __init__(self, **kwargs):
"""Initializes the InputParams."""
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
if "location" in kwargs and kwargs["location"] is not None:
warnings.warn(
"GoogleVertexLLMService.InputParams.location is deprecated. "
"Please provide 'location' as a direct argument to GoogleVertexLLMService.__init__() instead.",
DeprecationWarning,
stacklevel=2,
)
if "project_id" in kwargs and kwargs["project_id"] is not None:
warnings.warn(
"GoogleVertexLLMService.InputParams.project_id is deprecated. "
"Please provide 'project_id' as a direct argument to GoogleVertexLLMService.__init__() instead.",
DeprecationWarning,
stacklevel=2,
)
super().__init__(**kwargs)
def __init__(
self,
*,
credentials: Optional[str] = None,
credentials_path: Optional[str] = None,
model: Optional[str] = None,
location: Optional[str] = None,
project_id: Optional[str] = None,
location: str = "us-east4",
project_id: str,
params: Optional[GoogleLLMService.InputParams] = None,
settings: Optional[Settings] = None,
system_instruction: Optional[str] = None,
@@ -131,7 +87,7 @@ class GoogleVertexLLMService(GoogleLLMService):
.. deprecated:: 0.0.105
Use ``settings=GoogleVertexLLMService.Settings(model=...)`` instead.
location: GCP region for Vertex AI endpoint (e.g., "us-east4").
location: GCP region for Vertex AI endpoint. Defaults to "us-east4".
project_id: Google Cloud project ID.
params: Input parameters for the model.
@@ -161,34 +117,6 @@ class GoogleVertexLLMService(GoogleLLMService):
"Invalid parameter 'api_key'. Use 'credentials' or 'credentials_path' for Vertex AI authentication."
)
# Handle deprecated InputParams fields (location/project_id extraction
# must happen before validation, regardless of settings)
if params and isinstance(params, GoogleVertexLLMService.InputParams):
if project_id is None:
project_id = params.project_id
if location is None:
location = params.location
# Convert to base InputParams
params = GoogleLLMService.InputParams(
**params.model_dump(exclude={"location", "project_id"}, exclude_unset=True)
)
# Validate project_id and location parameters
# NOTE: once we remove Vertex-specific InputParams class, we can update
# __init__() signature as follows:
# - location: str = "us-east4",
# - project_id: str,
# But for now, we need them as-is to maintain proper backward
# compatibility.
if project_id is None:
raise ValueError("project_id is required")
if location is None:
# If location is not provided, default to "us-east4".
# Note: this is legacy behavior; ideally location would be
# required.
logger.warning("location is not provided. Defaulting to 'us-east4'.")
location = "us-east4" # Default location if not provided
# These need to be set before calling super().__init__() because
# super().__init__() invokes _create_client(), which needs these.
self._credentials = self._get_credentials(credentials, credentials_path)

17
src/pipecat/services/minimax/tts.py
View File

@@ -157,12 +157,6 @@ class MiniMaxHttpTTSService(TTSService):
pitch: Pitch adjustment (range: -12 to 12).
emotion: Emotional tone (options: "happy", "sad", "angry", "fearful",
"disgusted", "surprised", "calm", "fluent").
english_normalization: Deprecated; use `text_normalization` instead
.. deprecated:: 0.0.96
The `english_normalization` parameter is deprecated and will be removed in a future version.
Use the `text_normalization` parameter instead.
text_normalization: Enable text normalization (Chinese/English).
latex_read: Enable LaTeX formula reading.
exclude_aggregated_audio: Whether to exclude aggregated audio in final chunk.
@@ -173,7 +167,6 @@ class MiniMaxHttpTTSService(TTSService):
volume: Optional[float] = 1.0
pitch: Optional[int] = 0
emotion: Optional[str] = None
english_normalization: Optional[bool] = None # Deprecated
text_normalization: Optional[bool] = None
latex_read: Optional[bool] = None
exclude_aggregated_audio: Optional[bool] = None
@@ -284,16 +277,6 @@ class MiniMaxHttpTTSService(TTSService):
)
# Resolve text_normalization
if params.english_normalization is not None:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter `english_normalization` is deprecated and will be removed in a future version. Use `text_normalization` instead.",
DeprecationWarning,
)
default_settings.text_normalization = params.english_normalization
if params.text_normalization is not None:
default_settings.text_normalization = params.text_normalization

24
src/pipecat/services/rime/tts.py
View File

@@ -37,7 +37,6 @@ from pipecat.services.tts_service import (
WebsocketTTSService,
)
from pipecat.transcriptions.language import Language, resolve_language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.skip_tags_aggregator import SkipTagsAggregator
from pipecat.utils.tracing.service_decorators import traced_tts
@@ -176,7 +175,6 @@ class RimeTTSService(WebsocketTTSService):
sample_rate: Optional[int] = None,
params: Optional[InputParams] = None,
settings: Optional[Settings] = None,
text_aggregator: Optional[BaseTextAggregator] = None,
text_aggregation_mode: Optional[TextAggregationMode] = None,
aggregate_sentences: Optional[bool] = None,
**kwargs,
@@ -204,11 +202,6 @@ class RimeTTSService(WebsocketTTSService):
settings: Runtime-updatable settings. When provided alongside deprecated
parameters, ``settings`` values take precedence.
text_aggregator: Custom text aggregator for processing input text.
.. deprecated:: 0.0.95
Use an LLMTextProcessor before the TTSService for custom text aggregation.
text_aggregation_mode: How to aggregate incoming text before synthesis.
aggregate_sentences: Deprecated. Use text_aggregation_mode instead.
@@ -282,15 +275,14 @@ class RimeTTSService(WebsocketTTSService):
self._audio_format = "pcm"
self._sampling_rate = 0 # updated in start()
if not text_aggregator:
# Always skip tags added for spelled-out text
# Note: This is primarily to support backwards compatibility.
# The preferred way of taking advantage of Rime spelling is
# to use an LLMTextProcessor and/or a text_transformer to identify
# and insert these tags for the purpose of the TTS service alone.
self._text_aggregator = SkipTagsAggregator(
[("spell(", ")")], aggregation_type=self._text_aggregation_mode
)
# Always skip tags added for spelled-out text
# Note: This is primarily to support backwards compatibility.
# The preferred way of taking advantage of Rime spelling is
# to use an LLMTextProcessor and/or a text_transformer to identify
# and insert these tags for the purpose of the TTS service alone.
self._text_aggregator = SkipTagsAggregator(
[("spell(", ")")], aggregation_type=self._text_aggregation_mode
)
# Store service configuration
self._api_key = api_key

70
src/pipecat/services/simli/video.py
View File

@@ -7,7 +7,6 @@
"""Simli video service for real-time avatar generation."""
import asyncio
import warnings
from dataclasses import dataclass
from typing import Optional
@@ -79,10 +78,8 @@ class SimliVideoService(AIService):
def __init__(
self,
*,
api_key: Optional[str] = None,
face_id: Optional[str] = None,
simli_config: Optional[SimliConfig] = None,
use_turn_server: bool = False,
api_key: str,
face_id: str,
simli_url: str = "https://api.simli.ai",
is_trinity_avatar: bool = False,
params: Optional[InputParams] = None,
@@ -98,18 +95,6 @@ class SimliVideoService(AIService):
api_key: Simli API key for authentication.
face_id: Simli Face ID. For Trinity avatars, specify "faceId/emotionId"
to use a different emotion than the default.
simli_config: Configuration object for Simli client settings.
Use api_key and face_id instead.
.. deprecated:: 0.0.92
The 'simli_config' parameter is deprecated and will be removed in a future version.
Please use 'api_key' and 'face_id' parameters instead.
use_turn_server: Whether to use TURN server for connection. Defaults to False.
.. deprecated:: 0.0.95
The 'use_turn_server' parameter is deprecated and will be removed in a future version.
simli_url: URL of the simli servers. Can be changed for custom deployments
of enterprise users.
is_trinity_avatar: Boolean to tell simli client that this is a Trinity avatar
@@ -147,49 +132,16 @@ class SimliVideoService(AIService):
# 4. Call super
super().__init__(settings=default_settings, **kwargs)
# Handle deprecated simli_config parameter
if simli_config is not None:
if api_key is not None or face_id is not None:
raise ValueError(
"Cannot specify both simli_config and api_key/face_id. "
"Please use api_key and face_id (simli_config is deprecated)."
)
# Build SimliConfig from parameters
config_kwargs = {
"faceId": face_id,
}
if max_session_length is not None:
config_kwargs["maxSessionLength"] = max_session_length
if max_idle_time is not None:
config_kwargs["maxIdleTime"] = max_idle_time
warnings.warn(
"The 'simli_config' parameter is deprecated and will be removed in a future version. "
"Please use 'api_key' and 'face_id' parameters instead, with optional 'params' for "
"max_session_length and max_idle_time configuration.",
DeprecationWarning,
stacklevel=2,
)
# Use the provided simli_config
config = simli_config
else:
# Validate new parameters
if api_key is None:
raise ValueError("api_key is required")
if face_id is None:
raise ValueError("face_id is required")
# Build SimliConfig from new parameters
# Only pass optional parameters if explicitly provided to use SimliConfig defaults
config_kwargs = {
"faceId": face_id,
}
if max_session_length is not None:
config_kwargs["maxSessionLength"] = max_session_length
if max_idle_time is not None:
config_kwargs["maxIdleTime"] = max_idle_time
config = SimliConfig(**config_kwargs)
if use_turn_server:
warnings.warn(
"The 'use_turn_server' parameter is deprecated and will be removed in a future version.",
DeprecationWarning,
stacklevel=2,
)
config = SimliConfig(**config_kwargs)
self._initialized = False
# Add buffer time to session limits

37
src/pipecat/services/tts_service.py
View File

@@ -58,7 +58,6 @@ from pipecat.services.ai_service import AIService
from pipecat.services.settings import TTSSettings, is_given
from pipecat.services.websocket_service import WebsocketService
from pipecat.transcriptions.language import Language
from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
from pipecat.utils.text.base_text_filter import BaseTextFilter
from pipecat.utils.text.simple_text_aggregator import SimpleTextAggregator
from pipecat.utils.time import seconds_to_nanoseconds
@@ -168,8 +167,6 @@ class TTSService(AIService):
append_trailing_space: bool = False,
# TTS output sample rate
sample_rate: Optional[int] = None,
# Text aggregator to aggregate incoming tokens and decide when to push to the TTS.
text_aggregator: Optional[BaseTextAggregator] = None,
# Types of text aggregations that should not be spoken.
skip_aggregator_types: Optional[List[str]] = [],
# A list of callables to transform text before just before sending it to TTS.
@@ -182,7 +179,6 @@ class TTSService(AIService):
] = None,
# Text filter executed after text has been aggregated.
text_filters: Optional[Sequence[BaseTextFilter]] = None,
text_filter: Optional[BaseTextFilter] = None,
# Audio transport destination of the generated frames.
transport_destination: Optional[str] = None,
settings: Optional[TTSSettings] = None,
@@ -215,11 +211,6 @@ class TTSService(AIService):
append_trailing_space: Whether to append a trailing space to text before sending to TTS.
This helps prevent some TTS services from vocalizing trailing punctuation (e.g., "dot").
sample_rate: Output sample rate for generated audio.
text_aggregator: Custom text aggregator for processing incoming text.
.. deprecated:: 0.0.95
Use an LLMTextProcessor before the TTSService for custom text aggregation.
skip_aggregator_types: List of aggregation types that should not be spoken.
text_transforms: A list of callables to transform text before just before sending it
to TTS. Each callable takes the aggregated text and its type, and returns the
@@ -227,11 +218,6 @@ class TTSService(AIService):
(aggregation_type | '*', transform_function).
text_filters: Sequence of text filters to apply after aggregation.
text_filter: Single text filter (deprecated, use text_filters).
.. deprecated:: 0.0.59
Use `text_filters` instead, which allows multiple filters.
transport_destination: Destination for generated audio frames.
settings: The runtime-updatable settings for the TTS service.
reuse_context_id_within_turn: Whether the service should reuse context IDs within the
@@ -300,18 +286,7 @@ class TTSService(AIService):
self._append_trailing_space: bool = append_trailing_space
self._init_sample_rate = sample_rate
self._sample_rate = 0
self._text_aggregator: BaseTextAggregator = text_aggregator or SimpleTextAggregator(
aggregation_type=self._text_aggregation_mode
)
if text_aggregator:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'text_aggregator' is deprecated. Use an LLMTextProcessor before the TTSService for custom text aggregation.",
DeprecationWarning,
)
self._text_aggregator = SimpleTextAggregator(aggregation_type=self._text_aggregation_mode)
self._skip_aggregator_types: List[str] = skip_aggregator_types or []
self._text_transforms: List[
@@ -320,16 +295,6 @@ class TTSService(AIService):
# TODO: Deprecate _text_filters when added to LLMTextProcessor
self._text_filters: Sequence[BaseTextFilter] = text_filters or []
self._transport_destination: Optional[str] = transport_destination
if text_filter:
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter 'text_filter' is deprecated, use 'text_filters' instead.",
DeprecationWarning,
)
self._text_filters = [text_filter]
self._resampler = create_stream_resampler()