dv-pipecat-ai 0.0.82.dev857__py3-none-any.whl → 0.0.85.dev837__py3-none-any.whl

pipecat/services/openai/tts.py

@@ -14,6 +14,7 @@ from typing import AsyncGenerator, Dict, Literal, Optional
 
 from loguru import logger
 from openai import AsyncOpenAI, BadRequestError
+from pydantic import BaseModel
 
 from pipecat.frames.frames import (
     ErrorFrame,
@@ -55,6 +56,17 @@ class OpenAITTSService(TTSService):
 
     OPENAI_SAMPLE_RATE = 24000  # OpenAI TTS always outputs at 24kHz
 
+    class InputParams(BaseModel):
+        """Input parameters for OpenAI TTS configuration.
+
+        Parameters:
+            instructions: Instructions to guide voice synthesis behavior.
+            speed: Voice speed control (0.25 to 4.0, default 1.0).
+        """
+
+        instructions: Optional[str] = None
+        speed: Optional[float] = None
+
     def __init__(
         self,
         *,
@@ -64,6 +76,8 @@ class OpenAITTSService(TTSService):
         model: str = "gpt-4o-mini-tts",
         sample_rate: Optional[int] = None,
         instructions: Optional[str] = None,
+        speed: Optional[float] = None,
+        params: Optional[InputParams] = None,
         **kwargs,
     ):
         """Initialize OpenAI TTS service.
@@ -75,7 +89,12 @@ class OpenAITTSService(TTSService):
             model: TTS model to use. Defaults to "gpt-4o-mini-tts".
             sample_rate: Output audio sample rate in Hz. If None, uses OpenAI's default 24kHz.
             instructions: Optional instructions to guide voice synthesis behavior.
+            speed: Voice speed control (0.25 to 4.0, default 1.0).
+            params: Optional synthesis controls (acting instructions, speed, ...).
             **kwargs: Additional keyword arguments passed to TTSService.
+
+                .. deprecated:: 0.0.91
+                        The `instructions` and `speed` parameters are deprecated, use `InputParams` instead.
         """
         if sample_rate and sample_rate != self.OPENAI_SAMPLE_RATE:
             logger.warning(
@@ -86,9 +105,24 @@ class OpenAITTSService(TTSService):
 
         self.set_model_name(model)
         self.set_voice(voice)
-        self._instructions = instructions
         self._client = AsyncOpenAI(api_key=api_key, base_url=base_url)
 
+        if instructions or speed:
+            import warnings
+
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "The `instructions` and `speed` parameters are deprecated, use `InputParams` instead.",
+                    DeprecationWarning,
+                    stacklevel=2,
+                )
+
+        self._settings = {
+            "instructions": params.instructions if params else instructions,
+            "speed": params.speed if params else speed,
+        }
+
     def can_generate_metrics(self) -> bool:
         """Check if this service can generate processing metrics.
 
@@ -133,17 +167,22 @@ class OpenAITTSService(TTSService):
         try:
             await self.start_ttfb_metrics()
 
-            # Setup extra body parameters
-            extra_body = {}
-            if self._instructions:
-                extra_body["instructions"] = self._instructions
+            # Setup API parameters
+            create_params = {
+                "input": text,
+                "model": self.model_name,
+                "voice": VALID_VOICES[self._voice_id],
+                "response_format": "pcm",
+            }
+
+            if self._settings["instructions"]:
+                create_params["instructions"] = self._settings["instructions"]
+
+            if self._settings["speed"]:
+                create_params["speed"] = self._settings["speed"]
 
             async with self._client.audio.speech.with_streaming_response.create(
-                input=text,
-                model=self.model_name,
-                voice=VALID_VOICES[self._voice_id],
-                response_format="pcm",
-                extra_body=extra_body,
+                **create_params
             ) as r:
                 if r.status_code != 200:
                     error = await r.text()

pipecat/services/openai_realtime/__init__.py

@@ -0,0 +1,27 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import warnings
+
+from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
+from pipecat.services.openai.realtime.events import (
+    InputAudioNoiseReduction,
+    InputAudioTranscription,
+    SemanticTurnDetection,
+    SessionProperties,
+    TurnDetection,
+)
+from pipecat.services.openai.realtime.llm import OpenAIRealtimeLLMService
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/openai_realtime/azure.py

@@ -0,0 +1,21 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Azure OpenAI Realtime LLM service implementation."""
+
+import warnings
+
+from pipecat.services.azure.realtime.llm import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.azure are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.azure.realtime.llm instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/openai_realtime/context.py

@@ -0,0 +1,21 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""OpenAI Realtime LLM context and aggregator implementations."""
+
+import warnings
+
+from pipecat.services.openai.realtime.context import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.context are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime.context instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/openai_realtime/events.py

@@ -0,0 +1,21 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Event models and data structures for OpenAI Realtime API communication."""
+
+import warnings
+
+from pipecat.services.openai.realtime.events import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.events are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime.events instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/openai_realtime/frames.py

@@ -0,0 +1,21 @@
+#
+# Copyright (c) 2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Custom frame types for OpenAI Realtime API integration."""
+
+import warnings
+
+from pipecat.services.openai.realtime.frames import *
+
+with warnings.catch_warnings():
+    warnings.simplefilter("always")
+    warnings.warn(
+        "Types in pipecat.services.openai_realtime.frames are deprecated. "
+        "Please use the equivalent types from "
+        "pipecat.services.openai.realtime.frames instead.",
+        DeprecationWarning,
+        stacklevel=2,
+    )

pipecat/services/openai_realtime_beta/azure.py

@@ -6,6 +6,8 @@
 
 """Azure OpenAI Realtime Beta LLM service implementation."""
 
+import warnings
+
 from loguru import logger
 
 from .openai import OpenAIRealtimeBetaLLMService
@@ -23,6 +25,10 @@ except ModuleNotFoundError as e:
 class AzureRealtimeBetaLLMService(OpenAIRealtimeBetaLLMService):
     """Azure OpenAI Realtime Beta LLM service with Azure-specific authentication.
 
+    .. deprecated:: 0.0.84
+        `AzureRealtimeBetaLLMService` is deprecated, use `AzureRealtimeLLMService` instead.
+        This class will be removed in version 1.0.0.
+
     Extends the OpenAI Realtime service to work with Azure OpenAI endpoints,
     using Azure's authentication headers and endpoint format. Provides the same
     real-time audio and text communication capabilities as the base OpenAI service.
@@ -44,6 +50,16 @@ class AzureRealtimeBetaLLMService(OpenAIRealtimeBetaLLMService):
             **kwargs: Additional arguments passed to parent OpenAIRealtimeBetaLLMService.
         """
         super().__init__(base_url=base_url, api_key=api_key, **kwargs)
+
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "AzureRealtimeBetaLLMService is deprecated and will be removed in version 1.0.0. "
+                "Use AzureRealtimeLLMService instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         self.api_key = api_key
         self.base_url = base_url
 

pipecat/services/openai_realtime_beta/openai.py

@@ -9,6 +9,7 @@
 import base64
 import json
 import time
+import warnings
 from dataclasses import dataclass
 from typing import Optional
 
@@ -23,6 +24,7 @@ from pipecat.frames.frames import (
     Frame,
     InputAudioRawFrame,
     InterimTranscriptionFrame,
+    InterruptionFrame,
     LLMContextFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
@@ -31,7 +33,6 @@ from pipecat.frames.frames import (
     LLMTextFrame,
     LLMUpdateSettingsFrame,
     StartFrame,
-    StartInterruptionFrame,
     TranscriptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
@@ -92,6 +93,10 @@ class CurrentAudioResponse:
 class OpenAIRealtimeBetaLLMService(LLMService):
     """OpenAI Realtime Beta LLM service providing real-time audio and text communication.
 
+    .. deprecated:: 0.0.84
+        `OpenAIRealtimeBetaLLMService` is deprecated, use `OpenAIRealtimeLLMService` instead.
+        This class will be removed in version 1.0.0.
+
     Implements the OpenAI Realtime API Beta with WebSocket communication for low-latency
     bidirectional audio and text interactions. Supports function calling, conversation
     management, and real-time transcription.
@@ -124,6 +129,15 @@ class OpenAIRealtimeBetaLLMService(LLMService):
             send_transcription_frames: Whether to emit transcription frames. Defaults to True.
             **kwargs: Additional arguments passed to parent LLMService.
         """
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "OpenAIRealtimeBetaLLMService is deprecated and will be removed in version 1.0.0. "
+                "Use OpenAIRealtimeLLMService instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         full_url = f"{base_url}?model={model}"
         super().__init__(base_url=full_url, **kwargs)
 
@@ -350,7 +364,7 @@ class OpenAIRealtimeBetaLLMService(LLMService):
         elif isinstance(frame, InputAudioRawFrame):
             if not self._audio_input_paused:
                 await self._send_user_audio(frame)
-        elif isinstance(frame, StartInterruptionFrame):
+        elif isinstance(frame, InterruptionFrame):
             await self._handle_interruption()
         elif isinstance(frame, UserStartedSpeakingFrame):
             await self._handle_user_started_speaking(frame)
@@ -644,14 +658,12 @@ class OpenAIRealtimeBetaLLMService(LLMService):
 
     async def _handle_evt_speech_started(self, evt):
         await self._truncate_current_audio_response()
-        await self._start_interruption()  # cancels this processor task
-        await self.push_frame(StartInterruptionFrame())  # cancels downstream tasks
+        await self.push_interruption_task_frame_and_wait()
         await self.push_frame(UserStartedSpeakingFrame())
 
     async def _handle_evt_speech_stopped(self, evt):
         await self.start_ttfb_metrics()
         await self.start_processing_metrics()
-        await self._stop_interruption()
         await self.push_frame(UserStoppedSpeakingFrame())
 
     async def _maybe_handle_evt_retrieve_conversation_item_error(self, evt: events.ErrorEvent):

pipecat/services/piper/tts.py

@@ -14,7 +14,6 @@ from loguru import logger
 from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
-    TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
@@ -99,16 +98,15 @@ class PiperTTSService(TTSService):
 
                 await self.start_tts_usage_metrics(text)
 
+                yield TTSStartedFrame()
+
                 CHUNK_SIZE = self.chunk_size
 
-                yield TTSStartedFrame()
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    # remove wav header if present
-                    if chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        yield TTSAudioRawFrame(chunk, self.sample_rate, 1)
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE), strip_wav_header=True
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
         except Exception as e:
             logger.error(f"Error in run_tts: {e}")
             yield ErrorFrame(error=str(e))

pipecat/services/playht/tts.py

@@ -14,6 +14,7 @@ import io
 import json
 import struct
 import uuid
+import warnings
 from typing import AsyncGenerator, Optional
 
 import aiohttp
@@ -25,8 +26,8 @@ from pipecat.frames.frames import (
     EndFrame,
     ErrorFrame,
     Frame,
+    InterruptionFrame,
     StartFrame,
-    StartInterruptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
@@ -110,6 +111,11 @@ def language_to_playht_language(language: Language) -> Optional[str]:
 class PlayHTTTSService(InterruptibleTTSService):
     """PlayHT WebSocket-based text-to-speech service.
 
+    .. deprecated:: 0.0.88
+
+        This class is deprecated and will be removed in a future version.
+        PlayHT is shutting down their API on December 31st, 2025.
+
     Provides real-time text-to-speech synthesis using PlayHT's WebSocket API.
     Supports streaming audio generation with configurable voice engines and
     language settings.
@@ -158,6 +164,15 @@ class PlayHTTTSService(InterruptibleTTSService):
             **kwargs,
         )
 
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "PlayHT is shutting down their API on December 31st, 2025. "
+                "'PlayHTTTSService' is deprecated and will be removed in a future version.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         params = params or PlayHTTTSService.InputParams()
 
         self._api_key = api_key
@@ -254,6 +269,8 @@ class PlayHTTTSService(InterruptibleTTSService):
                 raise ValueError("WebSocket URL is not a string")
 
             self._websocket = await websocket_connect(self._websocket_url)
+
+            await self._call_event_handler("on_connected")
         except ValueError as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -276,6 +293,7 @@ class PlayHTTTSService(InterruptibleTTSService):
         finally:
             self._request_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     async def _get_websocket_url(self):
         """Retrieve WebSocket URL from PlayHT API."""
@@ -312,7 +330,7 @@ class PlayHTTTSService(InterruptibleTTSService):
             return self._websocket
         raise Exception("Websocket not connected")
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         """Handle interruption by stopping metrics and clearing request ID."""
         await super()._handle_interruption(frame, direction)
         await self.stop_all_metrics()
@@ -401,6 +419,11 @@ class PlayHTTTSService(InterruptibleTTSService):
 class PlayHTHttpTTSService(TTSService):
     """PlayHT HTTP-based text-to-speech service.
 
+    .. deprecated:: 0.0.88
+
+        This class is deprecated and will be removed in a future version.
+        PlayHT is shutting down their API on December 31st, 2025.
+
     Provides text-to-speech synthesis using PlayHT's HTTP API for simpler,
     non-streaming synthesis. Suitable for use cases where streaming is not
     required and simpler integration is preferred.
@@ -454,8 +477,6 @@ class PlayHTHttpTTSService(TTSService):
 
         # Warn about deprecated protocol parameter if explicitly provided
         if protocol:
-            import warnings
-
             with warnings.catch_warnings():
                 warnings.simplefilter("always")
                 warnings.warn(
@@ -464,6 +485,15 @@ class PlayHTHttpTTSService(TTSService):
                     stacklevel=2,
                 )
 
+        with warnings.catch_warnings():
+            warnings.simplefilter("always")
+            warnings.warn(
+                "PlayHT is shutting down their API on December 31st, 2025. "
+                "'PlayHTHttpTTSService' is deprecated and will be removed in a future version.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
         params = params or PlayHTHttpTTSService.InputParams()
 
         self._user_id = user_id

pipecat/services/rime/tts.py

@@ -24,15 +24,14 @@ from pipecat.frames.frames import (
     EndFrame,
     ErrorFrame,
     Frame,
+    InterruptionFrame,
     StartFrame,
-    StartInterruptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.tts_service import AudioContextWordTTSService, TTSService
-from pipecat.transcriptions import language
 from pipecat.transcriptions.language import Language
 from pipecat.utils.text.base_text_aggregator import BaseTextAggregator
 from pipecat.utils.text.skip_tags_aggregator import SkipTagsAggregator
@@ -256,6 +255,8 @@ class RimeTTSService(AudioContextWordTTSService):
             url = f"{self._url}?{params}"
             headers = {"Authorization": f"Bearer {self._api_key}"}
             self._websocket = await websocket_connect(url, additional_headers=headers)
+
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -273,6 +274,7 @@ class RimeTTSService(AudioContextWordTTSService):
         finally:
             self._context_id = None
             self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         """Get active websocket connection or raise exception."""
@@ -280,7 +282,7 @@ class RimeTTSService(AudioContextWordTTSService):
             return self._websocket
         raise Exception("Websocket not connected")
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         """Handle interruption by clearing current context."""
         await super()._handle_interruption(frame, direction)
         await self.stop_all_metrics()
@@ -375,7 +377,7 @@ class RimeTTSService(AudioContextWordTTSService):
             direction: The direction to push the frame.
         """
         await super().push_frame(frame, direction)
-        if isinstance(frame, (TTSStoppedFrame, StartInterruptionFrame)):
+        if isinstance(frame, (TTSStoppedFrame, InterruptionFrame)):
             if isinstance(frame, TTSStoppedFrame):
                 await self.add_word_timestamps([("Reset", 0)])
 
@@ -554,15 +556,13 @@ class RimeHttpTTSService(TTSService):
 
                 CHUNK_SIZE = self.chunk_size
 
-                async for chunk in response.content.iter_chunked(CHUNK_SIZE):
-                    if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
-                        chunk = chunk[44:]
-                        need_to_strip_wav_header = False
+                async for frame in self._stream_audio_frames_from_iterator(
+                    response.content.iter_chunked(CHUNK_SIZE),
+                    strip_wav_header=need_to_strip_wav_header,
+                ):
+                    await self.stop_ttfb_metrics()
+                    yield frame
 
-                    if len(chunk) > 0:
-                        await self.stop_ttfb_metrics()
-                        frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)
-                        yield frame
         except Exception as e:
             logger.exception(f"Error generating TTS: {e}")
             yield ErrorFrame(error=f"Rime TTS error: {str(e)}")

pipecat/services/riva/stt.py

@@ -583,7 +583,9 @@ class RivaSegmentedSTTService(SegmentedSTTService):
             self._config.language_code = self._language
 
     @traced_stt
-    async def _handle_transcription(self, transcript: str, language: Optional[Language] = None):
+    async def _handle_transcription(
+        self, transcript: str, is_final: bool, language: Optional[Language] = None
+    ):
         """Handle a transcription result with tracing."""
         pass
 

pipecat/services/salesforce/__init__.py

@@ -0,0 +1,9 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+from .llm import SalesforceAgentLLMService
+
+__all__ = ["SalesforceAgentLLMService"]