Add on_start support to VoiceWorkflowBase and VoicePipeline

Author: vrtnis

src/agents/voice/pipeline.py

@@ -125,6 +125,13 @@ async def _run_multi_turn(self, audio_input: StreamedAudioInput) -> StreamedAudi
                 self._get_tts_model(), self.config.tts_settings, self.config
             )
 
+            if hasattr(self.workflow, "on_start"):
+                try:
+                    async for intro_text in self.workflow.on_start():
+                        await output._add_text(intro_text)
+                except Exception as e:
+                    logger.warning(f"on_start() failed: {e}")
+
             transcription_session = await self._get_stt_model().create_session(
                 audio_input,
                 self.config.stt_settings,

src/agents/voice/workflow.py

@@ -32,6 +32,14 @@ def run(self, transcription: str) -> AsyncIterator[str]:
         """
         pass
 
+    async def on_start(self) -> AsyncIterator[str]:
+        """
+        Optional method that runs before any user input is received. Can be used
+        to deliver a greeting or instruction via TTS. Defaults to doing nothing.
+        """
+        return
+        yield
+
 
 class VoiceWorkflowHelper:
     @classmethod