Add TranscriptionProcessor

src/pipecat/frames/frames.py

@@ -5,7 +5,7 @@
 #
 
 from dataclasses import dataclass, field
-from typing import Any, List, Mapping, Optional, Tuple
+from typing import Any, List, Literal, Mapping, Optional, Tuple, TypeAlias
 
 from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.clocks.base_clock import BaseClock
@@ -195,7 +195,8 @@ class TranscriptionFrame(TextFrame):
 @dataclass
 class InterimTranscriptionFrame(TextFrame):
     """A text frame with interim transcription-specific data. Will be placed in
-    the transport's receive queue when a participant speaks."""
+    the transport's receive queue when a participant speaks.
+    """
 
     text: str
     user_id: str
@@ -206,6 +207,34 @@ class InterimTranscriptionFrame(TextFrame):
         return f"{self.name}(user: {self.user_id}, text: [{self.text}], language: {self.language}, timestamp: {self.timestamp})"
 
 
+@dataclass
+class TranscriptionMessage:
+    """A message in a conversation transcript containing the role and content.
+
+    Messages are in standard format with roles normalized to user/assistant.
+    """
+
+    role: Literal["user", "assistant"]
+    content: str
+    timestamp: str | None = None
+
+
+@dataclass
+class TranscriptionUpdateFrame(DataFrame):
+    """A frame containing new messages added to the conversation transcript.
+
+    This frame is emitted when new messages are added to the conversation history,
+    containing only the newly added messages rather than the full transcript.
+    Messages have normalized roles (user/assistant) regardless of the LLM service used.
+    """
+
+    messages: List[TranscriptionMessage]
+
+    def __str__(self):
+        pts = format_pts(self.pts)
+        return f"{self.name}(pts: {pts}, messages: {len(self.messages)})"
+
+
 @dataclass
 class LLMMessagesFrame(DataFrame):
     """A frame containing a list of LLM messages. Used to signal that an LLM
@@ -546,7 +575,8 @@ class EndFrame(ControlFrame):
 @dataclass
 class LLMFullResponseStartFrame(ControlFrame):
     """Used to indicate the beginning of an LLM response. Following by one or
-    more TextFrame and a final LLMFullResponseEndFrame."""
+    more TextFrame and a final LLMFullResponseEndFrame.
+    """
 
     pass