From a9ef5ca95d1d36e8d6ed09a0ec72ca821ab6d683 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Thu, 31 Oct 2024 15:47:32 -0700
Subject: [PATCH] examples: add bot background sound example

---
 CHANGELOG.md                                  |   4 +-
 .../foundational/23-bot-background-sound.py   | 121 ++++++++++++++++++
 2 files changed, 124 insertions(+), 1 deletion(-)
 create mode 100644 examples/foundational/23-bot-background-sound.py

diff --git a/CHANGELOG.md b/CHANGELOG.md
index dd56eb011..eb344aa45 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -61,7 +61,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Other
 
-- Added a new foundational example 22-natural-conversation.py. This examples
+- Add `23-bot-background-sound.py` foundational example.
+
+- Added a new foundational example `22-natural-conversation.py`. This example
   shows how to achieve a more natural conversation detecting when the user ends
   statement.
 
diff --git a/examples/foundational/23-bot-background-sound.py b/examples/foundational/23-bot-background-sound.py
new file mode 100644
index 000000000..68dd700d5
--- /dev/null
+++ b/examples/foundational/23-bot-background-sound.py
@@ -0,0 +1,121 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import argparse
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.audio.mixers.soundfile_mixer import SoundfileMixer
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMMessagesFrame, MixerUpdateSettingsFrame, MixerEnableFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure_with_args
+
+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():
+    async with aiohttp.ClientSession() as session:
+        parser = argparse.ArgumentParser(description="Bot Background Sound")
+        parser.add_argument("-i", "--input", type=str, required=True, help="Input audio file")
+
+        (room_url, token, args) = await configure_with_args(session, parser)
+
+        soundfile_mixer = SoundfileMixer(
+            sound_files={"office": args.input},
+            default_sound="office",
+            volume=2.0,
+        )
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                audio_out_mixer=soundfile_mixer,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        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.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Show how to use mixer control frames.
+            await asyncio.sleep(10.0)
+            await task.queue_frame(MixerUpdateSettingsFrame({"volume": 0.5}))
+            await asyncio.sleep(5.0)
+            await task.queue_frame(MixerEnableFrame(False))
+            await asyncio.sleep(5.0)
+            await task.queue_frame(MixerEnableFrame(True))
+            await asyncio.sleep(5.0)
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())