frames: indicate if UserStartedSpeakingFrame/UserStoppedSpeakingFrame are emulated

CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- It is now possible to tell whether `UserStartedSpeakingFrame` or
+  `UserStoppedSpeakingFrame` have been generated because of emulation frames.
+
 ## [0.0.61] - 2025-03-26
 
 ### Added
@@ -21,9 +28,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - ElevenLabs TTS services now support a sample rate of 8000.
 
-- Added support for `instructions` in `OpenAITTSService`
+- Added support for `instructions` in `OpenAITTSService`.
 
-- Added support for `base_url` in `OpenAIImageGenService` and `OpenAITTSService`
+- Added support for `base_url` in `OpenAIImageGenService` and
+  `OpenAITTSService`.
 
 ### Fixed
 

src/pipecat/frames/frames.py

@@ -562,14 +562,14 @@ class UserStartedSpeakingFrame(SystemFrame):
 
     """
 
-    pass
+    emulated: bool = False
 
 
 @dataclass
 class UserStoppedSpeakingFrame(SystemFrame):
     """Emitted by the VAD to indicate that a user stopped speaking."""
 
-    pass
+    emulated: bool = False
 
 
 @dataclass

src/pipecat/transports/base_input.py

@@ -117,10 +117,10 @@ class BaseInputTransport(FrameProcessor):
             await self._handle_bot_interruption(frame)
         elif isinstance(frame, EmulateUserStartedSpeakingFrame):
             logger.debug("Emulating user started speaking")
-            await self._handle_user_interruption(UserStartedSpeakingFrame())
+            await self._handle_user_interruption(UserStartedSpeakingFrame(emulated=True))
         elif isinstance(frame, EmulateUserStoppedSpeakingFrame):
             logger.debug("Emulating user stopped speaking")
-            await self._handle_user_interruption(UserStoppedSpeakingFrame())
+            await self._handle_user_interruption(UserStoppedSpeakingFrame(emulated=True))
         # All other system frames
         elif isinstance(frame, SystemFrame):
             await self.push_frame(frame, direction)