TranscriptionMessage: add user_id field

CHANGELOG.md

@@ -9,6 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added `user_id` field to `TranscriptionMessage`. This allows identifying the
+  user in a multi-user scenario. Note that this requires that
+  `TranscriptionFrame` has the `user_id` properly set.
+
 - Added new `PipelineTask` event handlers `on_pipeline_started`,
   `on_pipeline_stopped`, `on_pipeline_ended` and `on_pipeline_cancelled`, which
   correspond to the `StartFrame`, `StopFrame`, `EndFrame` and `CancelFrame`

src/pipecat/frames/frames.py

@@ -288,6 +288,7 @@ class TranscriptionMessage:
 
     role: Literal["user", "assistant"]
     content: str
+    user_id: Optional[str] = None
     timestamp: Optional[str] = None
 
 

src/pipecat/processors/transcript_processor.py

@@ -62,7 +62,7 @@ class UserTranscriptProcessor(BaseTranscriptProcessor):
 
         if isinstance(frame, TranscriptionFrame):
             message = TranscriptionMessage(
-                role="user", content=frame.text, timestamp=frame.timestamp
+                role="user", user_id=frame.user_id, content=frame.text, timestamp=frame.timestamp
             )
             await self._emit_update([message])
 

tests/test_transcript_processor.py

@@ -64,6 +64,7 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
         message = update_frame.messages[0]
         self.assertEqual(message.role, "user")
         self.assertEqual(message.content, "Hello, world!")
+        self.assertEqual(message.user_id, "test_user")
         self.assertEqual(message.timestamp, timestamp)
 
     async def test_event_handler(self):