Twilio serializer reading dtmf websocket messages and generating InputDTMFFrame containing the corresponding value of KeypadEntry

src/pipecat/frames/frames.py

@@ -5,6 +5,7 @@
 #
 
 from dataclasses import dataclass, field
+from enum import Enum
 from typing import TYPE_CHECKING, Any, Awaitable, Callable, List, Literal, Mapping, Optional, Tuple
 
 from pipecat.audio.vad.vad_analyzer import VADParams
@@ -18,6 +19,23 @@ if TYPE_CHECKING:
     from pipecat.observers.base_observer import BaseObserver
 
 
+class KeypadEntry(str, Enum):
+    """DTMF entries."""
+
+    ONE = "1"
+    TWO = "2"
+    THREE = "3"
+    FOUR = "4"
+    FIVE = "5"
+    SIX = "6"
+    SEVEN = "7"
+    EIGHT = "8"
+    NINE = "9"
+    ZERO = "0"
+    POUND = "#"
+    STAR = "*"
+
+
 def format_pts(pts: int | None):
     return nanoseconds_to_str(pts) if pts else None
 
@@ -615,6 +633,13 @@ class VisionImageRawFrame(InputImageRawFrame):
         return f"{self.name}(pts: {pts}, text: [{self.text}], size: {self.size}, format: {self.format})"
 
 
+@dataclass
+class InputDTMFFrame(Frame):
+    """A DTMF button input"""
+
+    button: KeypadEntry
+
+
 #
 # Control frames
 #

src/pipecat/serializers/twilio.py

@@ -10,7 +10,14 @@ import json
 from pydantic import BaseModel
 
 from pipecat.audio.utils import pcm_to_ulaw, ulaw_to_pcm
-from pipecat.frames.frames import AudioRawFrame, Frame, InputAudioRawFrame, StartInterruptionFrame
+from pipecat.frames.frames import (
+    AudioRawFrame,
+    Frame,
+    InputAudioRawFrame,
+    InputDTMFFrame,
+    KeypadEntry,
+    StartInterruptionFrame,
+)
 from pipecat.serializers.base_serializer import FrameSerializer, FrameSerializerType
 
 
@@ -48,9 +55,7 @@ class TwilioFrameSerializer(FrameSerializer):
     def deserialize(self, data: str | bytes) -> Frame | None:
         message = json.loads(data)
 
-        if message["event"] != "media":
+        if message["event"] == "media":
-            return None
-        else:
             payload_base64 = message["media"]["payload"]
             payload = base64.b64decode(payload_base64)
 
@@ -61,3 +66,13 @@ class TwilioFrameSerializer(FrameSerializer):
                 audio=deserialized_data, num_channels=1, sample_rate=self._params.sample_rate
             )
             return audio_frame
+        elif message["event"] == "dtmf":
+            digit = message.get("dtmf", {}).get("digit")
+
+            try:
+                return InputDTMFFrame(KeypadEntry(digit))
+            except ValueError as e:
+                # Handle case where string doesn't match any enum value
+                return None
+        else:
+            return None