playback started call for DataStreamAudioOutput and QueueAudioOutput

livekit-agents/livekit/agents/voice/avatar/_datastream_io.py

@@ -3,6 +3,7 @@
 import asyncio
 import json
 import math
+import time
 from collections.abc import AsyncIterator
 from dataclasses import asdict
 from typing import Any, Callable, Union
@@ -134,6 +135,10 @@ async def capture_frame(self, frame: rtc.AudioFrame) -> None:
                 },
             )
             self._pushed_duration = 0.0
+            # Not ideal since frame isn't actually playing yet
+            # potentially we need another RPC for this
+            self.on_playback_started(created_at=time.time())
+
         await self._stream_writer.write(bytes(frame.data))
         self._pushed_duration += frame.duration
 

livekit-agents/livekit/agents/voice/avatar/_queue_io.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import logging
+import time
 from collections.abc import AsyncIterator
 from typing import Literal, Union
 
@@ -16,7 +17,7 @@
 class QueueAudioOutput(
     AudioOutput,
     AudioReceiver,
-    rtc.EventEmitter[Literal["playback_finished", "clear_buffer"]],
+    rtc.EventEmitter[Literal["clear_buffer"]],
 ):
     """
     AudioOutput implementation that sends audio frames through a queue.
@@ -37,6 +38,9 @@ async def capture_frame(self, frame: rtc.AudioFrame) -> None:
         await super().capture_frame(frame)
         if not self._capturing:
             self._capturing = True
+            # Not ideal since frame isn't actually playing yet
+            # potentially we need another RPC/hook for this
+            self.on_playback_started(created_at=time.time())
 
         await self._data_ch.send(frame)