dv-pipecat-ai 0.0.82.dev41__tar.gz → 0.0.82.dev45__tar.gz

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.82.dev41
+Version: 0.0.82.dev45
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/src/dv_pipecat_ai.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.82.dev41
+Version: 0.0.82.dev45
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/src/pipecat/frames/frames.py

@@ -1473,6 +1473,17 @@ class STTUpdateSettingsFrame(ServiceUpdateSettingsFrame):
     pass
 
 
+@dataclass
+class DTMFUpdateSettingsFrame(ServiceUpdateSettingsFrame):
+    """Frame for updating DTMF aggregator settings.
+    
+    Updates DTMF configuration dynamically during conversation flow.
+    Settings can include: timeout, digits, end, reset parameters.
+    """
+
+    pass
+
+
 @dataclass
 class VADParamsUpdateFrame(SystemFrame):
     """Frame for updating VAD parameters.

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/src/pipecat/processors/aggregators/dtmf_aggregator.py

@@ -4,13 +4,6 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
-"""DTMF aggregation processor for converting keypad input to transcription.
-
-This module provides a frame processor that aggregates DTMF (Dual-Tone Multi-Frequency)
-keypad inputs into meaningful sequences and converts them to transcription frames
-for downstream processing by LLM context aggregators.
-"""
-
 import asyncio
 from typing import Optional
 
@@ -24,7 +17,7 @@ from pipecat.frames.frames import (
     StartFrame,
     TranscriptionFrame,
 )
-from pipecat.processors.frame_processor import FrameDirection, FrameProcessor, FrameProcessorSetup
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.utils.time import time_now_iso8601
 
 
@@ -33,12 +26,16 @@ class DTMFAggregator(FrameProcessor):
 
     The aggregator accumulates digits from InputDTMFFrame instances and flushes
     when:
-
     - Timeout occurs (configurable idle period)
     - Termination digit is received (default: '#')
     - EndFrame or CancelFrame is received
 
     Emits TranscriptionFrame for compatibility with existing LLM context aggregators.
+
+    Args:
+        timeout: Idle timeout in seconds before flushing
+        termination_digit: Digit that triggers immediate flush
+        prefix: Prefix added to DTMF sequence in transcription
     """
 
     def __init__(
@@ -48,14 +45,6 @@ class DTMFAggregator(FrameProcessor):
         prefix: str = "DTMF: ",
         **kwargs,
     ):
-        """Initialize the DTMF aggregator.
-
-        Args:
-            timeout: Idle timeout in seconds before flushing
-            termination_digit: Digit that triggers immediate flush
-            prefix: Prefix added to DTMF sequence in transcription
-            **kwargs: Additional arguments passed to FrameProcessor
-        """
         super().__init__(**kwargs)
         self._aggregation = ""
         self._idle_timeout = timeout
@@ -65,18 +54,7 @@ class DTMFAggregator(FrameProcessor):
         self._digit_event = asyncio.Event()
         self._aggregation_task: Optional[asyncio.Task] = None
 
-    async def cleanup(self) -> None:
-        """Clean up resources."""
-        await super().cleanup()
-        await self._stop_aggregation_task()
-
     async def process_frame(self, frame: Frame, direction: FrameDirection) -> None:
-        """Process incoming frames and handle DTMF aggregation.
-
-        Args:
-            frame: The frame to process.
-            direction: The direction of frame flow in the pipeline.
-        """
         await super().process_frame(frame, direction)
 
         if isinstance(frame, StartFrame):
@@ -105,7 +83,7 @@ class DTMFAggregator(FrameProcessor):
 
         # For first digit, schedule interruption.
         if is_first_digit:
-            await self.push_frame(BotInterruptionFrame(), FrameDirection.UPSTREAM)
+            asyncio.create_task(self._send_interruption_task())
 
         # Check for immediate flush conditions
         if frame.button == self._termination_digit:
@@ -114,6 +92,15 @@ class DTMFAggregator(FrameProcessor):
             # Signal digit received for timeout handling
             self._digit_event.set()
 
+    async def _send_interruption_task(self):
+        """Send interruption frame safely in a separate task."""
+        try:
+            # Send the interruption frame
+            await self.push_frame(BotInterruptionFrame(), FrameDirection.UPSTREAM)
+        except Exception as e:
+            # Log error but don't propagate
+            print(f"Error sending interruption: {e}")
+
     def _create_aggregation_task(self) -> None:
         """Creates the aggregation task if it hasn't been created yet."""
         if not self._aggregation_task:
@@ -132,6 +119,7 @@ class DTMFAggregator(FrameProcessor):
                 await asyncio.wait_for(self._digit_event.wait(), timeout=self._idle_timeout)
                 self._digit_event.clear()
             except asyncio.TimeoutError:
+                self.reset_watchdog()
                 if self._aggregation:
                     await self._flush_aggregation()
 
@@ -149,3 +137,8 @@ class DTMFAggregator(FrameProcessor):
         await self.push_frame(transcription_frame)
 
         self._aggregation = ""
+
+    async def cleanup(self) -> None:
+        """Clean up resources."""
+        await super().cleanup()
+        await self._stop_aggregation_task()

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/src/pipecat/processors/dtmf_aggregator.py

@@ -3,6 +3,7 @@ import asyncio
 from pipecat.frames.frames import (
     BotSpeakingFrame,
     CancelFrame,
+    DTMFUpdateSettingsFrame,
     EndFrame,
     Frame,
     InputDTMFFrame,
@@ -105,6 +106,65 @@ class DTMFAggregator(FrameProcessor):
         elif isinstance(frame, BotSpeakingFrame):
             if self._digit_aggregate_task is not None:
                 self._digit_event.set()
+        elif isinstance(frame, DTMFUpdateSettingsFrame):
+            await self._update_settings(frame.settings)
+            # Don't pass the settings frame downstream
+
+    async def _update_settings(self, settings: dict) -> None:
+        """Update DTMF aggregator settings dynamically.
+        
+        Args:
+            settings: Dictionary containing new DTMF settings
+                     Supported keys: timeout, digits, end, reset
+        """
+        settings_changed = False
+        
+        if "timeout" in settings and settings["timeout"] is not None:
+            new_timeout = float(settings["timeout"])
+            if new_timeout != self._idle_timeout:
+                self.logger.debug(f"Updating DTMF timeout from {self._idle_timeout} to {new_timeout}")
+                self._idle_timeout = new_timeout
+                settings_changed = True
+        
+        if "digits" in settings:
+            new_digits = settings["digits"]
+            if new_digits != self._digits:
+                self.logger.debug(f"Updating DTMF digits from {self._digits} to {new_digits}")
+                self._digits = new_digits
+                settings_changed = True
+        
+        if "end" in settings:
+            # Convert single string to set if needed
+            end_value = settings["end"]
+            if end_value is None:
+                new_end_on = set()
+            elif isinstance(end_value, str):
+                new_end_on = {end_value} if end_value else set()
+            else:
+                new_end_on = set(end_value)
+            
+            if new_end_on != self._end_on:
+                self.logger.debug(f"Updating DTMF end_on from {self._end_on} to {new_end_on}")
+                self._end_on = new_end_on
+                settings_changed = True
+        
+        if "reset" in settings:
+            # Convert single string to set if needed
+            reset_value = settings["reset"]
+            if reset_value is None:
+                new_reset_on = set()
+            elif isinstance(reset_value, str):
+                new_reset_on = {reset_value} if reset_value else set()
+            else:
+                new_reset_on = set(reset_value)
+            
+            if new_reset_on != self._reset_on:
+                self.logger.debug(f"Updating DTMF reset_on from {self._reset_on} to {new_reset_on}")
+                self._reset_on = new_reset_on
+                settings_changed = True
+        
+        if settings_changed:
+            self.logger.info(f"DTMF settings updated successfully")
 
     async def _digit_agg_handler(self, direction: FrameDirection, raise_timeout=False):
         """Idle task that waits for new DTMF activity. If no new digit is received within

{dv_pipecat_ai-0.0.82.dev41 → dv_pipecat_ai-0.0.82.dev45}/src/pipecat/services/elevenlabs/stt.py

@@ -223,7 +223,7 @@ class ElevenlabsSTTService(SegmentedSTTService):
         *,
         api_key: str,
         model_id: str = "scribe_v1",
-        language: Language = Language.EN,
+        language: Optional[Language] = None,
         tag_audio_events: bool = False,
         sample_rate: Optional[int] = None,
         diarize: bool = False,
@@ -293,10 +293,6 @@ class ElevenlabsSTTService(SegmentedSTTService):
             await self.start_ttfb_metrics()
 
             # Get language code for ElevenLabs API
-            language = self._settings["language"]
-            elevenlabs_lang = self.language_to_service_language(language)
-
-            # Prepare API parameters
             params = {
                 "file": audio,
                 "model_id": self._model_id,
@@ -304,9 +300,13 @@ class ElevenlabsSTTService(SegmentedSTTService):
                 "diarize": self._diarize,
             }
 
-            # Add language if specified
-            if elevenlabs_lang:
-                params["language_code"] = elevenlabs_lang
+            language = self._settings["language"]
+            if language is not None:
+                elevenlabs_lang = self.language_to_service_language(language)
+                if elevenlabs_lang:
+                    params["language_code"] = elevenlabs_lang
+            else:
+                params["language_code"] = None
 
             # Call ElevenLabs STT API in thread pool to avoid blocking
             transcription = await asyncio.to_thread(self._client.speech_to_text.convert, **params)