Merge pull request #891 from louisjoecodes/louis/flush-shorter-messag…

…es-elevenlabs

feat: set auto_mode=true - ElevenLabs tts WSS

src/pipecat/services/elevenlabs.py

@@ -312,7 +312,7 @@ async def _connect_websocket(self):
             voice_id = self._voice_id
             model = self.model_name
             output_format = self._settings["output_format"]
-            url = f"{self._url}/v1/text-to-speech/{voice_id}/stream-input?model_id={model}&output_format={output_format}"
+            url = f"{self._url}/v1/text-to-speech/{voice_id}/stream-input?model_id={model}&output_format={output_format}&auto_mode=true"
 
             if self._settings["optimize_streaming_latency"]:
                 url += f"&optimize_streaming_latency={self._settings['optimize_streaming_latency']}"