added BotSpeakingFrame

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added new frame `BotSpeakingFrame`. This frame will be continuously pushed
+  upstream while the bot is talking.
+
 - Added `XTTSService`. This is a local Text-To-Speech service.
   See https://github.com/coqui-ai/TTS
 

src/pipecat/frames/frames.py

@@ -240,6 +240,17 @@ class StopInterruptionFrame(SystemFrame):
     pass
 
 
+@dataclass
+class BotSpeakingFrame(SystemFrame):
+    """Emitted by transport outputs while the bot is still speaking. This can be
+    used, for example, to detect when a user is idle. That is, while the bot is
+    speaking we don't want to trigger any user idle timeout since the user might
+    be listening.
+
+    """
+    pass
+
+
 @dataclass
 class MetricsFrame(SystemFrame):
     """Emitted by processor that can compute metrics like latencies.

src/pipecat/transports/base_output.py

@@ -14,6 +14,7 @@ from typing import List
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.frames.frames import (
     AudioRawFrame,
+    BotSpeakingFrame,
     CancelFrame,
     MetricsFrame,
     SpriteFrame,
@@ -263,4 +264,5 @@ class BaseOutputTransport(FrameProcessor):
         if len(buffer) >= self._audio_chunk_size:
             await self.write_raw_audio_frames(bytes(buffer[:self._audio_chunk_size]))
             buffer = buffer[self._audio_chunk_size:]
+            await self.push_frame(BotSpeakingFrame(), FrameDirection.UPSTREAM)
         return buffer