From bea9e4b3ba0a1615036bad5f750009b7a0de7377 Mon Sep 17 00:00:00 2001
From: filipi87 <filipi87@gmail.com>
Date: Tue, 12 May 2026 17:44:11 -0300
Subject: [PATCH] New example voice-nvidia-sagemaker.py

---
 env.example                              |   4 +
 examples/voice/voice-nvidia-sagemaker.py | 129 +++++++++++++++++++++++
 2 files changed, 133 insertions(+)
 create mode 100644 examples/voice/voice-nvidia-sagemaker.py

diff --git a/env.example b/env.example
index d449db6b2..6d69cc0e9 100644
--- a/env.example
+++ b/env.example
@@ -132,6 +132,10 @@ NOVITA_API_KEY=...
 
 # NVIDIA
 NVIDIA_API_KEY=...
+# For a full example of how to deploy to SageMaker, see:
+# https://github.com/pipecat-ai/pipecat-examples/tree/main/nvidia_sagemaker_example/deployment/aws-sagemaker-nvidia
+SAGEMAKER_ASR_ENDPOINT_NAME=...
+SAGEMAKER_MAGPIE_ENDPOINT_NAME=...
 
 # OpenAI
 OPENAI_API_KEY=...
diff --git a/examples/voice/voice-nvidia-sagemaker.py b/examples/voice/voice-nvidia-sagemaker.py
new file mode 100644
index 000000000..403dcfafb
--- /dev/null
+++ b/examples/voice/voice-nvidia-sagemaker.py
@@ -0,0 +1,129 @@
+#
+# Copyright (c) 2024-2026, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+# For a full example of how to deploy to SageMaker, see:
+# https://github.com/pipecat-ai/pipecat-examples/tree/main/nvidia_sagemaker_example/deployment/aws-sagemaker-nvidia
+
+import os
+
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMRunFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_context import LLMContext
+from pipecat.processors.aggregators.llm_response_universal import (
+    LLMContextAggregatorPair,
+    LLMUserAggregatorParams,
+)
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.nvidia.llm import NvidiaLLMService
+from pipecat.services.nvidia.sagemaker.stt import NvidiaSageMakerSTTService
+from pipecat.services.nvidia.sagemaker.tts import NvidiaSageMakerTTSService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+# We use lambdas to defer transport parameter creation until the transport
+# type is selected at runtime.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+    ),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    stt = NvidiaSageMakerSTTService(
+        endpoint_name=os.getenv("SAGEMAKER_ASR_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION", "us-west-2"),
+    )
+
+    llm = NvidiaLLMService(
+        api_key=os.environ["NVIDIA_API_KEY"],
+        settings=NvidiaLLMService.Settings(
+            model="meta/llama-3.3-70b-instruct",
+            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
+        ),
+    )
+
+    tts = NvidiaSageMakerTTSService(
+        endpoint_name=os.getenv("SAGEMAKER_MAGPIE_ENDPOINT_NAME"),
+        region=os.getenv("AWS_REGION", "us-west-2"),
+    )
+
+    context = LLMContext()
+    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
+        context,
+        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
+    )
+
+    pipeline = Pipeline(
+        [
+            transport.input(),  # Transport user input
+            stt,  # STT
+            user_aggregator,  # User responses
+            llm,  # LLM
+            tts,  # TTS
+            transport.output(),  # Transport bot output
+            assistant_aggregator,  # Assistant spoken responses
+        ]
+    )
+
+    task = PipelineTask(
+        pipeline,
+        params=PipelineParams(
+            enable_metrics=True,
+            enable_usage_metrics=True,
+        ),
+        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+    )
+
+    @transport.event_handler("on_client_connected")
+    async def on_client_connected(transport, client):
+        logger.info(f"Client connected")
+        # Kick off the conversation.
+        context.add_message(
+            {"role": "developer", "content": "Please introduce yourself to the user."}
+        )
+        await task.queue_frames([LLMRunFrame()])
+
+    @transport.event_handler("on_client_disconnected")
+    async def on_client_disconnected(transport, client):
+        logger.info(f"Client disconnected")
+        await task.cancel()
+
+    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+    await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()