Split features/ into audio/, observability/, and rag/ subfolders
Extract focused example groups from the catch-all features/ folder: - audio/: audio recording, background sound, sound effects - observability/: observer, heartbeats, sentry metrics - rag/: mem0, gemini-rag, gemini grounding metadata Update README to document the new folders.
This commit is contained in:
Mark Backman
206
examples/audio/audio-recording.py
Normal file
206
examples/audio/audio-recording.py
Normal file
@@ -0,0 +1,206 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
"""Audio Recording Example with Pipecat.
|
||||
|
||||
This example demonstrates how to record audio from a conversation between a user and an AI assistant,
|
||||
saving both merged and individual audio tracks. It showcases the AudioBufferProcessor's capabilities
|
||||
to handle both combined and separate audio streams.
|
||||
|
||||
The example:
|
||||
1. Sets up a basic conversation with an AI assistant
|
||||
2. Records the entire conversation
|
||||
3. Saves three separate WAV files:
|
||||
- A merged recording of both participants
|
||||
- Individual recording of user audio
|
||||
- Individual recording of assistant audio
|
||||
|
||||
Requirements:
|
||||
- OpenAI API key (for GPT-4)
|
||||
- Cartesia API key (for text-to-speech)
|
||||
- Daily API key (for video/audio transport)
|
||||
|
||||
Environment variables (.env file):
|
||||
OPENAI_API_KEY=your_openai_key
|
||||
CARTESIA_API_KEY=your_cartesia_key
|
||||
DAILY_API_KEY=your_daily_key
|
||||
DEEPGRAM_API_KEY=your_deepgram_key
|
||||
|
||||
The recordings will be saved in a 'recordings' directory with timestamps:
|
||||
recordings/
|
||||
merged_20240315_123456.wav (Combined audio)
|
||||
user_20240315_123456.wav (User audio only)
|
||||
bot_20240315_123456.wav (Bot audio only)
|
||||
|
||||
Note:
|
||||
This example requires the AudioBufferProcessor with track-specific audio support,
|
||||
which provides both 'on_audio_data' and 'on_track_audio_data' events for
|
||||
handling merged and separate audio tracks respectively.
|
||||
"""
|
||||
|
||||
import datetime
|
||||
import io
|
||||
import os
|
||||
import wave
|
||||
|
||||
import aiofiles
|
||||
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.processors.audio.audio_buffer_processor import AudioBufferProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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)
|
||||
|
||||
|
||||
async def save_audio_file(audio: bytes, filename: str, sample_rate: int, num_channels: int):
|
||||
"""Save audio data to a WAV file."""
|
||||
if len(audio) > 0:
|
||||
with io.BytesIO() as buffer:
|
||||
with wave.open(buffer, "wb") as wf:
|
||||
wf.setsampwidth(2)
|
||||
wf.setnchannels(num_channels)
|
||||
wf.setframerate(sample_rate)
|
||||
wf.writeframes(audio)
|
||||
async with aiofiles.open(filename, "wb") as file:
|
||||
await file.write(buffer.getvalue())
|
||||
logger.info(f"Audio saved to {filename}")
|
||||
|
||||
|
||||
# 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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"), audio_passthrough=True)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121",
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
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.",
|
||||
),
|
||||
)
|
||||
|
||||
# Create audio buffer processor
|
||||
audiobuffer = AudioBufferProcessor()
|
||||
|
||||
context = LLMContext()
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
audiobuffer, # Add audio buffer to pipeline
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
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")
|
||||
# Start recording audio
|
||||
await audiobuffer.start_recording()
|
||||
# Start conversation - empty prompt to let LLM follow system instructions
|
||||
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()
|
||||
|
||||
# Handler for merged audio
|
||||
@audiobuffer.event_handler("on_audio_data")
|
||||
async def on_audio_data(buffer, audio, sample_rate, num_channels):
|
||||
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
filename = f"recordings/merged_{timestamp}.wav"
|
||||
os.makedirs("recordings", exist_ok=True)
|
||||
await save_audio_file(audio, filename, sample_rate, num_channels)
|
||||
|
||||
# Handler for separate tracks
|
||||
@audiobuffer.event_handler("on_track_audio_data")
|
||||
async def on_track_audio_data(buffer, user_audio, bot_audio, sample_rate, num_channels):
|
||||
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||
os.makedirs("recordings", exist_ok=True)
|
||||
|
||||
# Save user audio
|
||||
user_filename = f"recordings/user_{timestamp}.wav"
|
||||
await save_audio_file(user_audio, user_filename, sample_rate, 1)
|
||||
|
||||
# Save bot audio
|
||||
bot_filename = f"recordings/bot_{timestamp}.wav"
|
||||
await save_audio_file(bot_audio, bot_filename, sample_rate, 1)
|
||||
|
||||
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()
|
||||
155
examples/audio/bot-background-sound.py
Normal file
155
examples/audio/bot-background-sound.py
Normal file
@@ -0,0 +1,155 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.mixers.soundfile_mixer import SoundfileMixer
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import LLMRunFrame, MixerEnableFrame, MixerUpdateSettingsFrame
|
||||
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.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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)
|
||||
|
||||
OFFICE_SOUND_FILE = os.path.join(
|
||||
os.path.dirname(__file__), "assets", "office-ambience-24000-mono.mp3"
|
||||
)
|
||||
|
||||
# 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,
|
||||
audio_out_mixer=SoundfileMixer(
|
||||
sound_files={"office": OFFICE_SOUND_FILE},
|
||||
default_sound="office",
|
||||
volume=2.0,
|
||||
),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
audio_out_mixer=SoundfileMixer(
|
||||
sound_files={"office": OFFICE_SOUND_FILE},
|
||||
default_sound="office",
|
||||
volume=2.0,
|
||||
),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
audio_out_mixer=SoundfileMixer(
|
||||
sound_files={"office": OFFICE_SOUND_FILE},
|
||||
default_sound="office",
|
||||
volume=2.0,
|
||||
),
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
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.",
|
||||
),
|
||||
)
|
||||
|
||||
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, participant):
|
||||
# Show how to use mixer control frames.
|
||||
logger.info(f"Listening for background sound for a bit...")
|
||||
await asyncio.sleep(5.0)
|
||||
logger.info(f"Reducing volume...")
|
||||
await task.queue_frame(MixerUpdateSettingsFrame({"volume": 0.5}))
|
||||
await asyncio.sleep(5.0)
|
||||
logger.info(f"Disabling background sound for a bit...")
|
||||
await task.queue_frame(MixerEnableFrame(False))
|
||||
await asyncio.sleep(5.0)
|
||||
logger.info(f"Re-enabling background sound and starting bot...")
|
||||
await task.queue_frame(MixerEnableFrame(True))
|
||||
# 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()
|
||||
178
examples/audio/sound-effects.py
Normal file
178
examples/audio/sound-effects.py
Normal file
@@ -0,0 +1,178 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
import wave
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.frames.frames import (
|
||||
Frame,
|
||||
LLMContextFrame,
|
||||
LLMFullResponseEndFrame,
|
||||
OutputAudioRawFrame,
|
||||
TTSSpeakFrame,
|
||||
)
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.processors.logger import FrameLogger
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
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)
|
||||
|
||||
|
||||
sounds = {}
|
||||
sound_files = ["ding1.wav", "ding2.wav"]
|
||||
|
||||
script_dir = os.path.dirname(__file__)
|
||||
|
||||
for file in sound_files:
|
||||
# Build the full path to the image file
|
||||
full_path = os.path.join(script_dir, "assets", file)
|
||||
# Get the filename without the extension to use as the dictionary key
|
||||
filename = os.path.splitext(os.path.basename(full_path))[0]
|
||||
# Open the image and convert it to bytes
|
||||
with wave.open(full_path) as audio_file:
|
||||
sounds[file] = OutputAudioRawFrame(
|
||||
audio_file.readframes(-1), audio_file.getframerate(), audio_file.getnchannels()
|
||||
)
|
||||
|
||||
|
||||
class OutboundSoundEffectWrapper(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, LLMFullResponseEndFrame):
|
||||
await self.push_frame(sounds["ding1.wav"])
|
||||
# In case anything else downstream needs it
|
||||
await self.push_frame(frame, direction)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
class InboundSoundEffectWrapper(FrameProcessor):
|
||||
async def process_frame(self, frame: Frame, direction: FrameDirection):
|
||||
await super().process_frame(frame, direction)
|
||||
|
||||
if isinstance(frame, LLMContextFrame):
|
||||
await self.push_frame(sounds["ding2.wav"])
|
||||
# In case anything else downstream needs it
|
||||
await self.push_frame(frame, direction)
|
||||
else:
|
||||
await self.push_frame(frame, direction)
|
||||
|
||||
|
||||
# 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 = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
|
||||
|
||||
llm = OpenAILLMService(
|
||||
api_key=os.getenv("OPENAI_API_KEY"),
|
||||
settings=OpenAILLMService.Settings(
|
||||
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 = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
context = LLMContext()
|
||||
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
|
||||
)
|
||||
out_sound = OutboundSoundEffectWrapper()
|
||||
in_sound = InboundSoundEffectWrapper()
|
||||
fl = FrameLogger("LLM Out")
|
||||
fl2 = FrameLogger("Transcription In")
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
transport.input(),
|
||||
stt,
|
||||
user_aggregator,
|
||||
in_sound,
|
||||
fl2,
|
||||
llm,
|
||||
fl,
|
||||
tts,
|
||||
out_sound,
|
||||
transport.output(),
|
||||
assistant_aggregator,
|
||||
]
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
pipeline,
|
||||
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.
|
||||
await task.queue_frame(TTSSpeakFrame("Hi, I'm listening!"))
|
||||
await transport.send_audio(sounds["ding1.wav"])
|
||||
|
||||
@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()
|
||||
Reference in New Issue
Block a user