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

pipecat/services/sarvam/tts.py

@@ -20,9 +20,9 @@ from pipecat.frames.frames import (
     EndFrame,
     ErrorFrame,
     Frame,
+    InterruptionFrame,
     LLMFullResponseEndFrame,
     StartFrame,
-    StartInterruptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
@@ -76,17 +76,29 @@ 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):
@@ -105,6 +117,14 @@ 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,
@@ -124,7 +144,7 @@ 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.
@@ -138,16 +158,32 @@ 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)
 
@@ -275,6 +311,18 @@ 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):
@@ -310,6 +358,14 @@ 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,
@@ -329,6 +385,7 @@ 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.
@@ -371,15 +428,12 @@ 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,
@@ -387,6 +441,24 @@ 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
@@ -455,7 +527,7 @@ class SarvamTTSService(InterruptibleTTSService):
             direction: The direction to push the frame.
         """
         await super().push_frame(frame, direction)
-        if isinstance(frame, (TTSStoppedFrame, StartInterruptionFrame)):
+        if isinstance(frame, (TTSStoppedFrame, InterruptionFrame)):
             self._started = False
 
     async def process_frame(self, frame: Frame, direction: FrameDirection):
@@ -525,6 +597,7 @@ 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
@@ -556,6 +629,10 @@ 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:
@@ -605,8 +682,15 @@ class SarvamTTSService(InterruptibleTTSService):
             logger.warning("Service is disconnecting, ignoring text send")
             return
 
+        # Validate text input
+        if not text or not isinstance(text, str) or not text.strip():
+            logger.warning(f"Invalid text input for Sarvam TTS: {repr(text)}")
+            return
+
         if self._websocket and self._websocket.state == State.OPEN:
-            msg = {"type": "text", "data": {"text": text}}
+            msg = {"type": "text", "data": {"text": text.strip()}}
+            logger.info(f"Sarvam TTS: Sending text message: {repr(text.strip())}")
+            logger.debug(f"Sarvam TTS: Full message payload: {msg}")
             await self._websocket.send(json.dumps(msg))
         else:
             logger.warning("WebSocket not ready, cannot send text")

pipecat/services/simli/video.py

@@ -15,8 +15,8 @@ from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
     Frame,
+    InterruptionFrame,
     OutputImageRawFrame,
-    StartInterruptionFrame,
     TTSAudioRawFrame,
     TTSStoppedFrame,
     UserStartedSpeakingFrame,
@@ -179,7 +179,7 @@ class SimliVideoService(FrameProcessor):
             return
         elif isinstance(frame, (EndFrame, CancelFrame)):
             await self._stop()
-        elif isinstance(frame, (StartInterruptionFrame, UserStartedSpeakingFrame)):
+        elif isinstance(frame, (InterruptionFrame, UserStartedSpeakingFrame)):
             if not self._previously_interrupted:
                 await self._simli_client.clearBuffer()
             self._previously_interrupted = self._is_trinity_avatar

pipecat/services/speechmatics/stt.py

@@ -19,7 +19,6 @@ from loguru import logger
 from pydantic import BaseModel
 
 from pipecat.frames.frames import (
-    BotInterruptionFrame,
     CancelFrame,
     EndFrame,
     ErrorFrame,
@@ -551,7 +550,7 @@ class SpeechmaticsSTTService(STTService):
 
             @self._client.on(ServerMessageType.END_OF_UTTERANCE)
             def _evt_on_end_of_utterance(message: dict[str, Any]):
-                logger.debug("End of utterance received from STT")
+                self.logger.debug("End of utterance received from STT")
                 asyncio.run_coroutine_threadsafe(
                     self._handle_end_of_utterance(), self.get_event_loop()
                 )
@@ -578,6 +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
@@ -596,6 +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.
@@ -619,7 +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
             ]
@@ -749,14 +750,13 @@ class SpeechmaticsSTTService(STTService):
             return
 
         # Frames to send
-        upstream_frames: list[Frame] = []
         downstream_frames: list[Frame] = []
 
         # If VAD is enabled, then send a speaking frame
         if self._params.enable_vad and not self._is_speaking:
             logger.debug("User started speaking")
             self._is_speaking = True
-            upstream_frames += [BotInterruptionFrame()]
+            await self.push_interruption_task_frame_and_wait()
             downstream_frames += [UserStartedSpeakingFrame()]
 
         # If final, then re-parse into TranscriptionFrame
@@ -775,7 +775,7 @@ class SpeechmaticsSTTService(STTService):
             ]
 
             # Log transcript(s)
-            logger.debug(f"Finalized transcript: {[f.text for f in downstream_frames]}")
+            self.logger.debug(f"Finalized transcript: {[f.text for f in downstream_frames]}")
 
         # Return as interim results (unformatted)
         else:
@@ -794,10 +794,6 @@ class SpeechmaticsSTTService(STTService):
             self._is_speaking = False
             downstream_frames += [UserStoppedSpeakingFrame()]
 
-        # Send UPSTREAM frames
-        for frame in upstream_frames:
-            await self.push_frame(frame, FrameDirection.UPSTREAM)
-
         # Send the DOWNSTREAM frames
         for frame in downstream_frames:
             await self.push_frame(frame, FrameDirection.DOWNSTREAM)
@@ -996,6 +992,22 @@ def _language_to_speechmatics_language(language: Language) -> str:
     # List of supported input languages
     BASE_LANGUAGES = {
         Language.AR: "ar",
+        Language.AR_AE: "ar",
+        Language.AR_BH: "ar",
+        Language.AR_DZ: "ar",
+        Language.AR_EG: "ar",
+        Language.AR_IQ: "ar",
+        Language.AR_JO: "ar",
+        Language.AR_KW: "ar",
+        Language.AR_LB: "ar",
+        Language.AR_LY: "ar",
+        Language.AR_MA: "ar",
+        Language.AR_OM: "ar",
+        Language.AR_QA: "ar",
+        Language.AR_SA: "ar",
+        Language.AR_SY: "ar",
+        Language.AR_TN: "ar",
+        Language.AR_YE: "ar",
         Language.BA: "ba",
         Language.EU: "eu",
         Language.BE: "be",

pipecat/services/stt_service.py

@@ -16,6 +16,7 @@ from loguru import logger
 from pipecat.frames.frames import (
     AudioRawFrame,
     BotStoppedSpeakingFrame,
+    ErrorFrame,
     Frame,
     StartFrame,
     STTMuteFrame,
@@ -25,6 +26,7 @@ from pipecat.frames.frames import (
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.ai_service import AIService
+from pipecat.services.websocket_service import WebsocketService
 from pipecat.transcriptions.language import Language
 
 
@@ -34,6 +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__(
@@ -64,6 +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.
@@ -298,3 +323,25 @@ class SegmentedSTTService(STTService):
         if not self._user_speaking and len(self._audio_buffer) > self._audio_buffer_size_1s:
             discarded = len(self._audio_buffer) - self._audio_buffer_size_1s
             self._audio_buffer = self._audio_buffer[discarded:]
+
+
+class WebsocketSTTService(STTService, WebsocketService):
+    """Base class for websocket-based STT services.
+
+    Combines STT functionality with websocket connectivity, providing automatic
+    error handling and reconnection capabilities.
+    """
+
+    def __init__(self, *, reconnect_on_error: bool = True, **kwargs):
+        """Initialize the Websocket STT service.
+
+        Args:
+            reconnect_on_error: Whether to automatically reconnect on websocket errors.
+            **kwargs: Additional arguments passed to parent classes.
+        """
+        STTService.__init__(self, **kwargs)
+        WebsocketService.__init__(self, reconnect_on_error=reconnect_on_error, **kwargs)
+
+    async def _report_error(self, error: ErrorFrame):
+        await self._call_event_handler("on_connection_error", error.error)
+        await self.push_error(error)

pipecat/services/tavus/video.py

@@ -23,12 +23,12 @@ from pipecat.frames.frames import (
     CancelFrame,
     EndFrame,
     Frame,
+    InterruptionFrame,
     OutputAudioRawFrame,
     OutputImageRawFrame,
     OutputTransportReadyFrame,
     SpeechOutputAudioRawFrame,
     StartFrame,
-    StartInterruptionFrame,
     TTSAudioRawFrame,
     TTSStartedFrame,
 )
@@ -222,7 +222,7 @@ class TavusVideoService(AIService):
         """
         await super().process_frame(frame, direction)
 
-        if isinstance(frame, StartInterruptionFrame):
+        if isinstance(frame, InterruptionFrame):
             await self._handle_interruptions()
             await self.push_frame(frame, direction)
         elif isinstance(frame, TTSAudioRawFrame):

pipecat/services/tts_service.py

@@ -8,7 +8,18 @@
 
 import asyncio
 from abc import abstractmethod
-from typing import Any, AsyncGenerator, Callable, Dict, List, Mapping, Optional, Sequence, Tuple
+from typing import (
+    Any,
+    AsyncGenerator,
+    AsyncIterator,
+    Callable,
+    Dict,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
 from loguru import logger
 
@@ -20,10 +31,10 @@ from pipecat.frames.frames import (
     ErrorFrame,
     Frame,
     InterimTranscriptionFrame,
+    InterruptionFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
     StartFrame,
-    StartInterruptionFrame,
     TextFrame,
     TranscriptionFrame,
     TTSAudioRawFrame,
@@ -49,6 +60,25 @@ 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__(
@@ -98,6 +128,7 @@ class TTSService(AIService):
 
                 .. deprecated:: 0.0.59
                     Use `text_filters` instead, which allows multiple filters.
+            text_formatter: Optional callable receiving text and language code, returning formatted text.
 
             transport_destination: Destination for generated audio frames.
             **kwargs: Additional arguments passed to the parent AIService.
@@ -124,7 +155,6 @@ class TTSService(AIService):
 
         self._tracing_enabled: bool = False
 
-
         if text_filter:
             import warnings
 
@@ -143,6 +173,10 @@ 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.
@@ -319,7 +353,7 @@ class TTSService(AIService):
             and not isinstance(frame, TranscriptionFrame)
         ):
             await self._process_text_frame(frame)
-        elif isinstance(frame, StartInterruptionFrame):
+        elif isinstance(frame, InterruptionFrame):
             await self._handle_interruption(frame, direction)
             await self.push_frame(frame, direction)
         elif isinstance(frame, (LLMFullResponseEndFrame, EndFrame)):
@@ -377,14 +411,44 @@ class TTSService(AIService):
         await super().push_frame(frame, direction)
 
         if self._push_stop_frames and (
-            isinstance(frame, StartInterruptionFrame)
+            isinstance(frame, InterruptionFrame)
             or isinstance(frame, TTSStartedFrame)
             or isinstance(frame, TTSAudioRawFrame)
             or isinstance(frame, TTSStoppedFrame)
         ):
             await self._stop_frame_queue.put(frame)
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    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()
         for filter in self._text_filters:
@@ -465,7 +529,7 @@ class TTSService(AIService):
                 )
                 if isinstance(frame, TTSStartedFrame):
                     has_started = True
-                elif isinstance(frame, (TTSStoppedFrame, StartInterruptionFrame)):
+                elif isinstance(frame, (TTSStoppedFrame, InterruptionFrame)):
                     has_started = False
             except asyncio.TimeoutError:
                 if has_started:
@@ -550,7 +614,7 @@ class WordTTSService(TTSService):
         elif isinstance(frame, (LLMFullResponseEndFrame, EndFrame)):
             await self.flush_audio()
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         await super()._handle_interruption(frame, direction)
         self._llm_response_started = False
         self.reset_word_timestamps()
@@ -613,7 +677,6 @@ 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)
@@ -640,7 +703,7 @@ class InterruptibleTTSService(WebsocketTTSService):
         # user interrupts we need to reconnect.
         self._bot_speaking = False
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         await super()._handle_interruption(frame, direction)
         if self._bot_speaking:
             await self._disconnect()
@@ -665,15 +728,6 @@ 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 +739,6 @@ 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)
@@ -712,7 +765,7 @@ class InterruptibleWordTTSService(WebsocketWordTTSService):
         # user interrupts we need to reconnect.
         self._bot_speaking = False
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         await super()._handle_interruption(frame, direction)
         if self._bot_speaking:
             await self._disconnect()
@@ -840,7 +893,7 @@ class AudioContextWordTTSService(WebsocketWordTTSService):
         await super().cancel(frame)
         await self._stop_audio_context_task()
 
-    async def _handle_interruption(self, frame: StartInterruptionFrame, direction: FrameDirection):
+    async def _handle_interruption(self, frame: InterruptionFrame, direction: FrameDirection):
         await super()._handle_interruption(frame, direction)
         await self._stop_audio_context_task()
         self._create_audio_context_task()