diff --git a/examples/foundational/07c-interruptible-deepgram.py b/examples/foundational/07c-interruptible-deepgram.py
index 4ca7dfeac..25be49a1c 100644
--- a/examples/foundational/07c-interruptible-deepgram.py
+++ b/examples/foundational/07c-interruptible-deepgram.py
@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.llm_response import (
     LLMAssistantResponseAggregator, LLMUserResponseAggregator)
-from pipecat.services.deepgram import DeepgramTTSService
+from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 from pipecat.vad.silero import SileroVADAnalyzer
@@ -39,23 +39,23 @@ async def main(room_url: str, token):
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                transcription_enabled=True,
                 vad_enabled=True,
-                vad_analyzer=SileroVADAnalyzer()
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True
             )
         )
 
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
         tts = DeepgramTTSService(
             aiohttp_session=session,
             api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-helios-en"
         )
 
         llm = OpenAILLMService(
-            # api_key=os.getenv("OPENAI_API_KEY"),
-            # model="gpt-4o"
-            model="meta-llama/Meta-Llama-3-8B-Instruct",
-            base_url="http://0.0.0.0:8000/v1"
-        )
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o")
 
         messages = [
             {
@@ -69,6 +69,7 @@ async def main(room_url: str, token):
 
         pipeline = Pipeline([
             transport.input(),   # Transport user input
+            stt,                 # STT
             tma_in,              # User responses
             llm,                 # LLM
             tts,                 # TTS
@@ -76,7 +77,7 @@ async def main(room_url: str, token):
             tma_out              # Assistant spoken responses
         ])
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
diff --git a/examples/foundational/16-gpu-container-local-bot.py b/examples/foundational/16-gpu-container-local-bot.py
new file mode 100644
index 000000000..0da208ae4
--- /dev/null
+++ b/examples/foundational/16-gpu-container-local-bot.py
@@ -0,0 +1,130 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+import json
+
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator, LLMUserResponseAggregator)
+from pipecat.services.deepgram import DeepgramTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyTransportMessageFrame
+from pipecat.vad.silero import SileroVADAnalyzer
+
+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(room_url: str, token):
+    async with aiohttp.ClientSession() as session:
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer()
+            )
+        )
+
+        tts = DeepgramTTSService(
+            aiohttp_session=session,
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            voice="aura-asteria-en",
+            base_url="http://0.0.0.0:8080/v1/speak"
+        )
+
+        llm = OpenAILLMService(
+            # To use OpenAI
+            # api_key=os.getenv("OPENAI_API_KEY"),
+            # model="gpt-4o"
+            # Or, to use a local vLLM (or similar) api server
+            model="meta-llama/Meta-Llama-3-8B-Instruct",
+            base_url="http://0.0.0.0:8000/v1"
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline([
+            transport.input(),   # Transport user input
+            tma_in,              # User responses
+            llm,                 # LLM
+            tts,                 # TTS
+            transport.output(),  # Transport bot output
+            tma_out              # Assistant spoken responses
+        ])
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True, enable_metrics=True))
+
+        # When a participant joins, start transcription for that participant so the
+        # bot can "hear" and respond to them.
+        @transport.event_handler("on_participant_joined")
+        async def on_participant_joined(transport, participant):
+            transport.capture_participant_transcription(participant["id"])
+
+        # When the first participant joins, the bot should introduce itself.
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            messages.append(
+                {"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        # Handle "latency-ping" messages. The client will send app messages that look like
+        # this:
+        #   { "latency-ping": { ts: <client-side timestamp> }}
+        #
+        # We want to send an immediate pong back to the client from this handler function.
+        # Also, we will push a frame into the top of the pipeline and send it after the
+        #
+        @transport.event_handler("on_app_message")
+        async def on_app_message(transport, message, sender):
+            try:
+                if "latency-ping" in message:
+                    logger.debug(f"Received latency ping app message: {message}")
+                    ts = message["latency-ping"]["ts"]
+                    # Send immediately
+                    transport.output().send_message(DailyTransportMessageFrame(
+                        message={"latency-pong-msg-handler": {"ts": ts}},
+                        participant_id=sender))
+                    # And push to the pipeline for the Daily transport.output to send
+                    await tma_in.push_frame(
+                        DailyTransportMessageFrame(
+                            message={"latency-pong-pipeline-delivery": {"ts": ts}},
+                            participant_id=sender))
+            except Exception as e:
+                logger.debug(f"message handling error: {e} - {message}")
+
+        runner = PipelineRunner()
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    (url, token) = configure()
+    asyncio.run(main(url, token))