dv-pipecat-ai 0.0.85.dev699__py3-none-any.whl → 0.0.85.dev814__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,
         *,
@@ -65,6 +77,7 @@ class OpenAITTSService(TTSService):
         sample_rate: Optional[int] = None,
         instructions: Optional[str] = None,
         speed: Optional[float] = None,
+        params: Optional[InputParams] = None,
         **kwargs,
     ):
         """Initialize OpenAI TTS service.
@@ -77,7 +90,11 @@ class OpenAITTSService(TTSService):
             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(
@@ -86,12 +103,26 @@ class OpenAITTSService(TTSService):
             )
         super().__init__(sample_rate=sample_rate, **kwargs)
 
-        self._speed = speed
         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.
 
@@ -144,11 +175,11 @@ class OpenAITTSService(TTSService):
                 "response_format": "pcm",
             }
 
-            if self._instructions:
-                create_params["instructions"] = self._instructions
+            if self._settings["instructions"]:
+                create_params["instructions"] = self._settings["instructions"]
 
-            if self._speed:
-                create_params["speed"] = self._speed
+            if self._settings["speed"]:
+                create_params["speed"] = self._settings["speed"]
 
             async with self._client.audio.speech.with_streaming_response.create(
                 **create_params

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

@@ -269,6 +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
@@ -291,6 +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."""

pipecat/services/rime/tts.py

@@ -255,6 +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
@@ -272,6 +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."""
@@ -553,15 +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/sarvam/tts.py

@@ -77,17 +77,29 @@ class SarvamHttpTTSService(TTSService):
 
     Example::
 
-        tts = SarvamTTSService(
+        tts = SarvamHttpTTSService(
             api_key="your-api-key",
             voice_id="anushka",
             model="bulbul:v2",
             aiohttp_session=session,
-            params=SarvamTTSService.InputParams(
+            params=SarvamHttpTTSService.InputParams(
                 language=Language.HI,
                 pitch=0.1,
                 pace=1.2
             )
         )
+
+        # For bulbul v3 beta with any speaker:
+        tts_v3 = SarvamHttpTTSService(
+            api_key="your-api-key",
+            voice_id="speaker_name",
+            model="bulbul:v3,
+            aiohttp_session=session,
+            params=SarvamHttpTTSService.InputParams(
+                language=Language.HI,
+                temperature=0.8
+            )
+        )
     """
 
     class InputParams(BaseModel):
@@ -106,6 +118,14 @@ class SarvamHttpTTSService(TTSService):
         pace: Optional[float] = Field(default=1.0, ge=0.3, le=3.0)
         loudness: Optional[float] = Field(default=1.0, ge=0.1, le=3.0)
         enable_preprocessing: Optional[bool] = False
+        temperature: Optional[float] = Field(
+            default=0.6,
+            ge=0.01,
+            le=1.0,
+            description="Controls the randomness of the output for bulbul v3 beta. "
+            "Lower values make the output more focused and deterministic, while "
+            "higher values make it more random. Range: 0.01 to 1.0. Default: 0.6.",
+        )
 
     def __init__(
         self,
@@ -125,7 +145,7 @@ class SarvamHttpTTSService(TTSService):
             api_key: Sarvam AI API subscription key.
             aiohttp_session: Shared aiohttp session for making requests.
             voice_id: Speaker voice ID (e.g., "anushka", "meera"). Defaults to "anushka".
-            model: TTS model to use ("bulbul:v1" or "bulbul:v2"). Defaults to "bulbul:v2".
+            model: TTS model to use ("bulbul:v2" or "bulbul:v3-beta" or "bulbul:v3"). Defaults to "bulbul:v2".
             base_url: Sarvam AI API base URL. Defaults to "https://api.sarvam.ai".
             sample_rate: Audio sample rate in Hz (8000, 16000, 22050, 24000). If None, uses default.
             params: Additional voice and preprocessing parameters. If None, uses defaults.
@@ -139,16 +159,32 @@ class SarvamHttpTTSService(TTSService):
         self._base_url = base_url
         self._session = aiohttp_session
 
+        # Build base settings common to all models
         self._settings = {
             "language": (
                 self.language_to_service_language(params.language) if params.language else "en-IN"
             ),
-            "pitch": params.pitch,
-            "pace": params.pace,
-            "loudness": params.loudness,
             "enable_preprocessing": params.enable_preprocessing,
         }
 
+        # Add model-specific parameters
+        if model in ("bulbul:v3-beta", "bulbul:v3"):
+            self._settings.update(
+                {
+                    "temperature": getattr(params, "temperature", 0.6),
+                    "model": model,
+                }
+            )
+        else:
+            self._settings.update(
+                {
+                    "pitch": params.pitch,
+                    "pace": params.pace,
+                    "loudness": params.loudness,
+                    "model": model,
+                }
+            )
+
         self.set_model_name(model)
         self.set_voice(voice_id)
 
@@ -276,6 +312,18 @@ class SarvamTTSService(InterruptibleTTSService):
                 pace=1.2
             )
         )
+
+        # For bulbul v3 beta with any speaker and temperature:
+        # Note: pace and loudness are not supported for bulbul v3 and bulbul v3 beta
+        tts_v3 = SarvamTTSService(
+            api_key="your-api-key",
+            voice_id="speaker_name",
+            model="bulbul:v3",
+            params=SarvamTTSService.InputParams(
+                language=Language.HI,
+                temperature=0.8
+            )
+        )
     """
 
     class InputParams(BaseModel):
@@ -311,6 +359,14 @@ class SarvamTTSService(InterruptibleTTSService):
         output_audio_codec: Optional[str] = "linear16"
         output_audio_bitrate: Optional[str] = "128k"
         language: Optional[Language] = Language.EN
+        temperature: Optional[float] = Field(
+            default=0.6,
+            ge=0.01,
+            le=1.0,
+            description="Controls the randomness of the output for bulbul v3 beta. "
+            "Lower values make the output more focused and deterministic, while "
+            "higher values make it more random. Range: 0.01 to 1.0. Default: 0.6.",
+        )
 
     def __init__(
         self,
@@ -330,6 +386,7 @@ class SarvamTTSService(InterruptibleTTSService):
         Args:
             api_key: Sarvam API key for authenticating TTS requests.
             model: Identifier of the Sarvam speech model (default "bulbul:v2").
+                Supports "bulbul:v2", "bulbul:v3-beta" and "bulbul:v3".
             voice_id: Voice identifier for synthesis (default "anushka").
             url: WebSocket URL for connecting to the TTS backend (default production URL).
             aiohttp_session: Optional shared aiohttp session. To maintain backward compatibility.
@@ -372,15 +429,12 @@ class SarvamTTSService(InterruptibleTTSService):
         self._api_key = api_key
         self.set_model_name(model)
         self.set_voice(voice_id)
-        # Configuration parameters
+        # Build base settings common to all models
         self._settings = {
             "target_language_code": (
                 self.language_to_service_language(params.language) if params.language else "en-IN"
             ),
-            "pitch": params.pitch,
-            "pace": params.pace,
             "speaker": voice_id,
-            "loudness": params.loudness,
             "speech_sample_rate": 0,
             "enable_preprocessing": params.enable_preprocessing,
             "min_buffer_size": params.min_buffer_size,
@@ -388,6 +442,24 @@ class SarvamTTSService(InterruptibleTTSService):
             "output_audio_codec": params.output_audio_codec,
             "output_audio_bitrate": params.output_audio_bitrate,
         }
+
+        # Add model-specific parameters
+        if model in ("bulbul:v3-beta", "bulbul:v3"):
+            self._settings.update(
+                {
+                    "temperature": getattr(params, "temperature", 0.6),
+                    "model": model,
+                }
+            )
+        else:
+            self._settings.update(
+                {
+                    "pitch": params.pitch,
+                    "pace": params.pace,
+                    "loudness": params.loudness,
+                    "model": model,
+                }
+            )
         self._started = False
 
         self._receive_task = None
@@ -526,6 +598,7 @@ class SarvamTTSService(InterruptibleTTSService):
             logger.debug("Connected to Sarvam TTS Websocket")
             await self._send_config()
 
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} initialization error: {e}")
             self._websocket = None
@@ -557,6 +630,10 @@ class SarvamTTSService(InterruptibleTTSService):
                 await self._websocket.close()
         except Exception as e:
             logger.error(f"{self} error closing websocket: {e}")
+        finally:
+            self._started = False
+            self._websocket = None
+            await self._call_event_handler("on_disconnected")
 
     def _get_websocket(self):
         if self._websocket:

pipecat/services/speechmatics/stt.py

@@ -577,6 +577,7 @@ class SpeechmaticsSTTService(STTService):
                 ),
             )
             logger.debug(f"{self} Connected to Speechmatics STT service")
+            await self._call_event_handler("on_connected")
         except Exception as e:
             logger.error(f"{self} Error connecting to Speechmatics: {e}")
             self._client = None
@@ -595,6 +596,7 @@ class SpeechmaticsSTTService(STTService):
             logger.error(f"{self} Error closing Speechmatics client: {e}")
         finally:
             self._client = None
+            await self._call_event_handler("on_disconnected")
 
     def _process_config(self) -> None:
         """Create a formatted STT transcription config.
@@ -618,7 +620,7 @@ class SpeechmaticsSTTService(STTService):
             transcription_config.additional_vocab = [
                 {
                     "content": e.content,
-                    "sounds_like": e.sounds_like,
+                    **({"sounds_like": e.sounds_like} if e.sounds_like else {}),
                 }
                 for e in self._params.additional_vocab
             ]

pipecat/services/stt_service.py

@@ -36,6 +36,25 @@ class STTService(AIService):
     Provides common functionality for STT services including audio passthrough,
     muting, settings management, and audio processing. Subclasses must implement
     the run_stt method to provide actual speech recognition.
+
+    Event handlers:
+        on_connected: Called when connected to the STT service.
+        on_connected: Called when disconnected from the STT service.
+        on_connection_error: Called when a connection to the STT service error occurs.
+
+    Example::
+
+        @stt.event_handler("on_connected")
+        async def on_connected(stt: STTService):
+            logger.debug(f"STT connected")
+
+        @stt.event_handler("on_disconnected")
+        async def on_disconnected(stt: STTService):
+            logger.debug(f"STT disconnected")
+
+        @stt.event_handler("on_connection_error")
+        async def on_connection_error(stt: STTService, error: str):
+            logger.error(f"STT connection error: {error}")
     """
 
     def __init__(
@@ -66,6 +85,10 @@ class STTService(AIService):
         self._voicemail_detect: bool = False
         self._user_id: str = ""
 
+        self._register_event_handler("on_connected")
+        self._register_event_handler("on_disconnected")
+        self._register_event_handler("on_connection_error")
+
     @property
     def is_muted(self) -> bool:
         """Check if the STT service is currently muted.
@@ -307,15 +330,6 @@ class WebsocketSTTService(STTService, WebsocketService):
 
     Combines STT functionality with websocket connectivity, providing automatic
     error handling and reconnection capabilities.
-
-    Event handlers:
-        on_connection_error: Called when a websocket connection error occurs.
-
-    Example::
-
-        @stt.event_handler("on_connection_error")
-        async def on_connection_error(stt: STTService, error: str):
-            logger.error(f"STT connection error: {error}")
     """
 
     def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
@@ -327,7 +341,6 @@ class WebsocketSTTService(STTService, WebsocketService):
         """
         STTService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)

pipecat/services/tts_service.py

@@ -8,7 +8,17 @@
 
 import asyncio
 from abc import abstractmethod
-from typing import Any, AsyncGenerator, Callable, Dict, List, Mapping, Optional, Sequence, Tuple
+from typing import (
+    Any,
+    AsyncGenerator,
+    AsyncIterator,
+    Dict,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
 from loguru import logger
 
@@ -49,6 +59,25 @@ class TTSService(AIService):
     Provides common functionality for TTS services including text aggregation,
     filtering, audio generation, and frame management. Supports configurable
     sentence aggregation, silence insertion, and frame processing control.
+
+    Event handlers:
+        on_connected: Called when connected to the STT service.
+        on_connected: Called when disconnected from the STT service.
+        on_connection_error: Called when a connection to the STT service error occurs.
+
+    Example::
+
+        @tts.event_handler("on_connected")
+        async def on_connected(tts: TTSService):
+            logger.debug(f"TTS connected")
+
+        @tts.event_handler("on_disconnected")
+        async def on_disconnected(tts: TTSService):
+            logger.debug(f"TTS disconnected")
+
+        @tts.event_handler("on_connection_error")
+        async def on_connection_error(stt: TTSService, error: str):
+            logger.error(f"TTS connection error: {error}")
     """
 
     def __init__(
@@ -124,7 +153,6 @@ class TTSService(AIService):
 
         self._tracing_enabled: bool = False
 
-
         if text_filter:
             import warnings
 
@@ -143,6 +171,10 @@ class TTSService(AIService):
 
         self._processing_text: bool = False
 
+        self._register_event_handler("on_connected")
+        self._register_event_handler("on_disconnected")
+        self._register_event_handler("on_connection_error")
+
     @property
     def sample_rate(self) -> int:
         """Get the current sample rate for audio output.
@@ -384,6 +416,36 @@ class TTSService(AIService):
         ):
             await self._stop_frame_queue.put(frame)
 
+    async def _stream_audio_frames_from_iterator(
+        self, iterator: AsyncIterator[bytes], *, strip_wav_header: bool
+    ) -> AsyncGenerator[Frame, None]:
+        buffer = bytearray()
+        need_to_strip_wav_header = strip_wav_header
+        async for chunk in iterator:
+            if need_to_strip_wav_header and chunk.startswith(b"RIFF"):
+                chunk = chunk[44:]
+                need_to_strip_wav_header = False
+
+            # Append to current buffer.
+            buffer.extend(chunk)
+
+            # Round to nearest even number.
+            aligned_length = len(buffer) & ~1  # 111111111...11110
+            if aligned_length > 0:
+                aligned_chunk = buffer[:aligned_length]
+                buffer = buffer[aligned_length:]  # keep any leftover byte
+
+                if len(aligned_chunk) > 0:
+                    frame = TTSAudioRawFrame(bytes(aligned_chunk), self.sample_rate, 1)
+                    yield frame
+
+        if len(buffer) > 0:
+            # Make sure we don't need an extra padding byte.
+            if len(buffer) % 2 == 1:
+                buffer.extend(b"\x00")
+            frame = TTSAudioRawFrame(bytes(buffer), self.sample_rate, 1)
+            yield frame
+
     async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         self._processing_text = False
         await self._text_aggregator.handle_interruption()
@@ -613,7 +675,6 @@ class WebsocketTTSService(TTSService, WebsocketService):
         """
         TTSService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)
@@ -665,15 +726,6 @@ class WebsocketWordTTSService(WordTTSService, WebsocketService):
     """Base class for websocket-based TTS services that support word timestamps.
 
     Combines word timestamp functionality with websocket connectivity.
-
-    Event handlers:
-        on_connection_error: Called when a websocket connection error occurs.
-
-    Example::
-
-        @tts.event_handler("on_connection_error")
-        async def on_connection_error(tts: TTSService, error: str):
-            logger.error(f"TTS connection error: {error}")
     """
 
     def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
@@ -685,7 +737,6 @@ class WebsocketWordTTSService(WordTTSService, WebsocketService):
         """
         WordTTSService.__init__(self, **kwargs)
         WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
-        self._register_event_handler("on_connection_error")
 
     async def _report_error(self, error: ErrorFrame):
         await self._call_event_handler("on_connection_error", error.error)

pipecat/transports/base_input.py

@@ -232,6 +232,9 @@ class BaseInputTransport(FrameProcessor):
         """
         # Cancel and wait for the audio input task to finish.
         await self._cancel_audio_task()
+        # Stop audio filter.
+        if self._params.audio_in_filter:
+            await self._params.audio_in_filter.stop()
 
     async def set_transport_ready(self, frame: StartFrame):
         """Called when the transport is ready to stream.