examples(websocket-server): use VAD analyzer from transport

examples/foundational/15-websocket-server.py

@@ -1,39 +0,0 @@
-#
-# Copyright (c) 2024, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import asyncio
-import sys
-
-from pipecat.pipeline.pipeline import Pipeline
-from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
-from pipecat.transports.network.websocket_server import WebsocketServerTransport
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
-load_dotenv(override=True)
-
-logger.remove(0)
-logger.add(sys.stderr, level="DEBUG")
-
-
-async def main():
-    transport = WebsocketServerTransport()
-
-    pipeline = Pipeline([transport.input(), transport.output()])
-
-    task = PipelineTask(pipeline)
-
-    runner = PipelineRunner()
-
-    await runner.run(task)
-
-
-if __name__ == "__main__":
-    asyncio.run(main())

examples/websocket-server/index.html

@@ -173,6 +173,7 @@
       }
 
       function stopAudio(closeWebsocket) {
+          playTime = 0;
           isPlaying = false;
           startBtn.disabled = false;
           stopBtn.disabled = true;

examples/websocket-server/server.py

@@ -12,13 +12,16 @@ import sys
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineTask
+from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import LLMAssistantResponseAggregator, LLMUserResponseAggregator
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator
+)
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.services.whisper import WhisperSTTService
 from pipecat.transports.network.websocket_server import WebsocketServerParams, WebsocketServerTransport
-from pipecat.vad.silero import SileroVAD
+from pipecat.vad.silero import SileroVADAnalyzer
 
 from loguru import logger
 
@@ -33,13 +36,15 @@ async def main():
     async with aiohttp.ClientSession() as session:
         transport = WebsocketServerTransport(
             params=WebsocketServerParams(
+                audio_in_enabled=True,
                 audio_out_enabled=True,
-                add_wav_header=True
+                add_wav_header=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True
             )
         )
 
-        vad = SileroVAD(audio_passthrough=True)
-
         llm = OpenAILLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             model="gpt-4o")
@@ -64,7 +69,6 @@ async def main():
 
         pipeline = Pipeline([
             transport.input(),   # Websocket input from client
-            vad,                 # VAD to detect user speech
             stt,                 # Speech-To-Text
             tma_in,              # User responses
             llm,                 # LLM