wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update examples

Browse Source
This commit is contained in:
Mark Backman
2026-03-04 22:55:51 -05:00
parent 197885773f
commit 039a8f6c7d
207 changed files with 1241 additions and 852 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/foundational/01-say-one-thing-piper.py
View File

@@ -39,7 +39,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
tts = PiperHttpTTSService(
base_url=os.getenv("PIPER_BASE_URL"), aiohttp_session=session, sample_rate=24000
base_url=os.getenv("PIPER_BASE_URL"),
aiohttp_session=session,
sample_rate=24000,
)
task = PipelineTask(

6
examples/foundational/01-say-one-thing-rime.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.rime.tts import RimeHttpTTSService
from pipecat.services.rime.tts import RimeHttpTTSService, RimeTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -39,8 +39,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
voice_id="rex",
aiohttp_session=session,
settings=RimeTTSSettings(
voice="rex",
),
)
task = PipelineTask(

6
examples/foundational/01-say-one-thing.py
View File

@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -37,7 +37,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
task = PipelineTask(

6
examples/foundational/01a-local-audio.py
View File

@@ -15,7 +15,7 @@ from pipecat.frames.frames import EndFrame, TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
load_dotenv(override=True)
@@ -29,7 +29,9 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
pipeline = Pipeline([tts, transport.output()])

6
examples/foundational/01b-livekit-audio.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.runner.livekit import configure
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
load_dotenv(override=True)
@@ -37,7 +37,9 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
runner = PipelineRunner()

6
examples/foundational/02-llm-say-one-thing.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -39,7 +39,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/04-transports-small-webrtc.py
View File

@@ -27,7 +27,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import TransportParams
@@ -67,7 +67,9 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

12
examples/foundational/04a-transports-daily.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMUserAggregatorParams,
)
from pipecat.runner.daily import configure
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.daily.transport import DailyParams, DailyTransport
load_dotenv(override=True)
@@ -50,12 +50,16 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o",
settings=OpenAILLMSettings(
model="gpt-4o",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

6
examples/foundational/04b-transports-livekit.py
View File

@@ -29,7 +29,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMUserAggregatorParams,
)
from pipecat.runner.livekit import configure
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
@@ -62,7 +62,9 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
context = LLMContext()

6
examples/foundational/05-sync-speech-and-image.py
View File

@@ -27,7 +27,7 @@ from pipecat.processors.aggregators.sentence import SentenceAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -98,7 +98,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(

6
examples/foundational/05a-local-sync-speech-and-image.py
View File

@@ -28,7 +28,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.sentence import SentenceAggregator
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
@@ -98,7 +98,9 @@ async def main():
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(

6
examples/foundational/06-listen-and-respond.py
View File

@@ -28,7 +28,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -83,7 +83,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/06a-image-sync.py
View File

@@ -29,7 +29,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -100,7 +100,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/07-interruptible-cartesia-http.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.stt import CartesiaSTTService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

37
examples/foundational/07a-interruptible-speechmatics-vad.py
View File

@@ -21,10 +21,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.base_llm import BaseOpenAILLMService
from pipecat.services.openai.base_llm import OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService, SpeechmaticsSTTSettings
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService, SpeechmaticsTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -93,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
settings=SpeechmaticsSTTSettings(
language=Language.EN,
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
# focus_speakers=["S1"],
@@ -104,32 +104,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
voice_id="sarah",
settings=SpeechmaticsTTSSettings(
voice="sarah",
),
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
params=BaseOpenAILLMService.InputParams(temperature=0.75),
settings=OpenAILLMSettings(
temperature=0.75,
),
system_instruction="You are a helpful British assistant called Sarah. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
)
messages = [
{
"role": "system",
"content": (
"You are a helpful British assistant called Sarah. "
"Your goal is to demonstrate your capabilities in a succinct way. "
"Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
"Always include punctuation in your responses. "
"Give very short replies - do not give longer replies unless strictly necessary. "
"Respond to what the user said in a concise, funny, creative and helpful way. "
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. "
"Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to. "
),
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
@@ -160,7 +149,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Say a short hello to the user."})
context.add_message({"role": "system", "content": "Say a short hello to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

36
examples/foundational/07a-interruptible-speechmatics.py
View File

@@ -22,10 +22,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.base_llm import BaseOpenAILLMService
from pipecat.services.openai.base_llm import OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService, SpeechmaticsSTTSettings
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService, SpeechmaticsTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
settings=SpeechmaticsSTTSettings(
language=Language.EN,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),
@@ -84,31 +84,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
voice_id="sarah",
settings=SpeechmaticsTTSSettings(
voice="sarah",
),
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
params=BaseOpenAILLMService.InputParams(temperature=0.75),
settings=OpenAILLMSettings(
temperature=0.75,
),
system_instruction="You are a helpful British assistant called Sarah. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Always include punctuation in your responses. Give very short replies - do not give longer replies unless strictly necessary. Respond to what the user said in a concise, funny, creative and helpful way. Use `<Sn/>` tags to identify different speakers - do not use tags in your replies. Do not respond to speakers within `<PASSIVE/>` tags unless explicitly asked to.",
)
messages = [
{
"role": "system",
"content": (
"You are a helpful British assistant called Sarah. "
"Your goal is to demonstrate your capabilities in a succinct way. "
"Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. "
"Always include punctuation in your responses. "
"Give very short replies - do not give longer replies unless strictly necessary. "
"Respond to what the user said in a concise, funny, creative and helpful way. "
"Use `<Sn/>` tags to identify different speakers - do not use tags in your replies."
),
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -139,7 +129,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Say a short hello to the user."})
context.add_message({"role": "system", "content": "Say a short hello to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

6
examples/foundational/07b-interruptible-langchain.py
View File

@@ -28,7 +28,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.frameworks.langchain import LangchainProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -71,7 +71,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
prompt = ChatPromptTemplate.from_messages(

15
examples/foundational/07c-interruptible-deepgram-flux.py
View File

@@ -22,8 +22,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.flux.stt import DeepgramFluxSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.deepgram.flux.stt import DeepgramFluxSTTService, DeepgramFluxSTTSettings
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,10 +56,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramFluxSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
settings=DeepgramFluxSTTSettings(
min_confidence=0.3,
),
)
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

10
examples/foundational/07c-interruptible-deepgram-http.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramHttpTTSService
from pipecat.services.deepgram.tts import DeepgramHttpTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramHttpTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
voice="aura-2-andromeda-en",
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
aiohttp_session=session,
)
@@ -68,9 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
messages = []
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

17
examples/foundational/07c-interruptible-deepgram-vad.py
View File

@@ -7,7 +7,6 @@
import os
from deepgram import LiveOptions
from dotenv import load_dotenv
from loguru import logger
@@ -22,8 +21,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,10 +55,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
settings=DeepgramSTTSettings(
vad_events=True,
utterance_end_ms="1000",
),
)
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

9
examples/foundational/07c-interruptible-deepgram.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,7 +55,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

6
examples/foundational/07d-interruptible-elevenlabs-http.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService, ElevenLabsHttpTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -63,8 +63,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsHttpTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
aiohttp_session=session,
settings=ElevenLabsHttpTTSSettings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(

6
examples/foundational/07d-interruptible-elevenlabs.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.elevenlabs.stt import ElevenLabsRealtimeSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService, ElevenLabsTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -57,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
settings=ElevenLabsTTSSettings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(

23
examples/foundational/07g-interruptible-openai.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
from pipecat.services.openai.tts import OpenAITTSService
from pipecat.services.openai.stt import OpenAIRealtimeSTTService, OpenAIRealtimeSTTSettings
from pipecat.services.openai.tts import OpenAITTSService, OpenAITTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,16 +55,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
language=Language.EN,
# Uses local VAD by default.
# To enable server-side VAD, set turn_detection=None or
# a dict with server_vad settings.
# turn_detection={"type": "server_vad", "threshold": 0.5},
settings=OpenAIRealtimeSTTSettings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
language=Language.EN,
),
)
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAITTSSettings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

6
examples/foundational/07h-interruptible-openpipe.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openpipe.llm import OpenPipeLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -57,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
timestamp = int(time.time())

6
examples/foundational/07i-interruptible-xtts.py
View File

@@ -25,7 +25,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.xtts.tts import XTTSService
from pipecat.services.xtts.tts import XTTSService, XTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = XTTSService(
aiohttp_session=session,
voice_id="Claribel Dervla",
settings=XTTSSettings(
voice="Claribel Dervla",
),
base_url="http://localhost:8000",
)

28
examples/foundational/07j-interruptible-gladia-vad.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY", ""),
region=os.getenv("GLADIA_REGION"),
params=GladiaInputParams(
settings=GladiaSTTSettings(
language_config=LanguageConfig(
languages=[Language.EN],
),
@@ -68,19 +68,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
messages = [
{
"role": "system",
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(
@@ -114,7 +112,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

28
examples/foundational/07j-interruptible-gladia.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY", ""),
region=os.getenv("GLADIA_REGION"),
params=GladiaInputParams(
settings=GladiaSTTSettings(
language_config=LanguageConfig(
languages=[Language.EN],
)
@@ -66,19 +66,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
messages = [
{
"role": "system",
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -109,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

9
examples/foundational/07k-interruptible-lmnt.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.lmnt.tts import LmntTTSService
from pipecat.services.lmnt.tts import LmntTTSService, LmntTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,7 +54,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
tts = LmntTTSService(
api_key=os.getenv("LMNT_API_KEY"),
settings=LmntTTSSettings(
voice="morgan",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

6
examples/foundational/07l-interruptible-groq.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.groq.tts import GroqTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
model="meta-llama/llama-4-maverick-17b-128e-instruct",
settings=GroqLLMSettings(
model="meta-llama/llama-4-maverick-17b-128e-instruct",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

9
examples/foundational/07m-interruptible-aws-strands.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.frameworks.strands_agents import StrandsAgentsProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.stt import AWSTranscribeSTTService
from pipecat.services.aws.tts import AWSPollyTTSService
from pipecat.services.aws.tts import AWSPollyTTSService, AWSPollyTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -95,8 +95,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AWSPollyTTSService(
region="us-west-2", # only specific regions support generative TTS
voice_id="Joanna",
params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
settings=AWSPollyTTSSettings(
voice="Joanna",
engine="generative",
rate="1.1",
),
)
# Create Strands agent processor

9
examples/foundational/07m-interruptible-aws.py
View File

@@ -22,7 +22,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.aws.stt import AWSTranscribeSTTService
from pipecat.services.aws.tts import AWSPollyTTSService
from pipecat.services.aws.tts import AWSPollyTTSService, AWSPollyTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,8 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AWSPollyTTSService(
region="us-west-2", # only specific regions support generative TTS
voice_id="Joanna",
params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
settings=AWSPollyTTSSettings(
voice="Joanna",
engine="generative",
rate="1.1",
),
)
llm = AWSBedrockLLMService(

22
examples/foundational/07n-interruptible-gemini-image.py
View File

@@ -37,9 +37,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -70,20 +70,26 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
),
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleTTSService.InputParams(language=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash-image",
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,
settings=GoogleLLMSettings(
model="gemini-2.5-flash-image",
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

14
examples/foundational/07n-interruptible-gemini.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GeminiTTSService
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GeminiTTSService, GeminiTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,15 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot with Gemini TTS")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US),
settings=GoogleSTTSettings(
languages=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
tts = GeminiTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
model="gemini-2.5-flash-tts",
voice_id="Charon",
params=GeminiTTSService.InputParams(
settings=GeminiTTSSettings(
model="gemini-2.5-flash-tts",
voice="Charon",
language=Language.EN_US,
prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
),

27
examples/foundational/07n-interruptible-google-http.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleHttpTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleHttpTTSService, GoogleHttpTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,24 +54,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
location="us",
)
tts = GoogleHttpTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
settings=GoogleHttpTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# params=GoogleLLMService.InputParams(
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
# ),
settings=GoogleLLMSettings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

27
examples/foundational/07n-interruptible-google.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,24 +54,29 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
location="us",
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleTTSService.InputParams(language=Language.EN_US),
settings=GoogleTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# params=GoogleLLMService.InputParams(
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
# ),
settings=GoogleLLMSettings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

11
examples/foundational/07o-interruptible-assemblyai-turn-detection.py
View File

@@ -22,9 +22,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.assemblyai.models import AssemblyAIConnectionParams
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -94,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
vad_force_turn_endpoint=False, # Use AssemblyAI's built-in turn detection
connection_params=AssemblyAIConnectionParams(
settings=AssemblyAISTTSettings(
speech_model="u3-rt-pro",
# Optional: Tune turn detection timing (defaults shown below)
# min_turn_silence=100, # Default
@@ -108,7 +107,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/07o-interruptible-assemblyai.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

7
examples/foundational/07p-interruptible-krisp-viva.py
View File

@@ -43,7 +43,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -84,7 +84,10 @@ 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"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

9
examples/foundational/07p-interruptible-krisp.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -58,7 +58,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-helios-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

7
examples/foundational/07q-interruptible-rime-http.py
View File

@@ -25,7 +25,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.rime.tts import RimeHttpTTSService
from pipecat.services.rime.tts import RimeHttpTTSService, RimeTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,7 +60,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
voice_id="luna",
settings=RimeTTSSettings(
voice="luna",
model="arcana",
),
model="arcana",
aiohttp_session=session,
)

6
examples/foundational/07q-interruptible-rime.py
View File

@@ -24,7 +24,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.rime.tts import RimeTTSService
from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
voice_id="luna",
settings=RimeTTSSettings(
voice="luna",
),
)
llm = OpenAILLMService(

6
examples/foundational/07r-interruptible-nvidia.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.nvidia.llm import NvidiaLLMService
from pipecat.services.nvidia.llm import NvidiaLLMService, NvidiaLLMSettings
from pipecat.services.nvidia.stt import NvidiaSTTService
from pipecat.services.nvidia.tts import NvidiaTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = NvidiaLLMService(
api_key=os.getenv("NVIDIA_API_KEY"),
model="meta/llama-3.3-70b-instruct",
settings=NvidiaLLMSettings(
model="meta/llama-3.3-70b-instruct",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)

13
examples/foundational/07s-interruptible-google-audio-in.py
View File

@@ -36,8 +36,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.frame_processor import FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -216,7 +216,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
settings=GoogleLLMSettings(
model="gemini-2.5-flash",
),
# force a certain amount of thinking if you want it
# params=GoogleLLMService.InputParams(
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
@@ -224,7 +226,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
settings=GoogleTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
params=GoogleTTSService.InputParams(language=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)

6
examples/foundational/07t-interruptible-fish.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.fish.tts import FishAudioTTSService
from pipecat.services.fish.tts import FishAudioTTSService, FishAudioTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -57,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = FishAudioTTSService(
api_key=os.getenv("FISH_API_KEY"),
model="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
settings=FishAudioTTSSettings(
model="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
),
)
llm = OpenAILLMService(

6
examples/foundational/07v-interruptible-neuphonic-http.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -60,7 +60,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicHttpTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
settings=NeuphonicTTSSettings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
aiohttp_session=session,
)

6
examples/foundational/07v-interruptible-neuphonic.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.neuphonic.tts import NeuphonicTTSService
from pipecat.services.neuphonic.tts import NeuphonicTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
settings=NeuphonicTTSSettings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
)
llm = OpenAILLMService(

6
examples/foundational/07w-interruptible-fal.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.fal.stt import FalSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/07x-interruptible-local.py
View File

@@ -21,7 +21,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
@@ -44,7 +44,9 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/07y-interruptible-minimax.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.minimax.tts import MiniMaxHttpTTSService
from pipecat.services.minimax.tts import MiniMaxHttpTTSService, MiniMaxTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -63,7 +63,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("MINIMAX_API_KEY", ""),
group_id=os.getenv("MINIMAX_GROUP_ID", ""),
aiohttp_session=session,
params=MiniMaxHttpTTSService.InputParams(language=Language.EN),
settings=MiniMaxTTSSettings(
language=Language.EN,
),
)
llm = OpenAILLMService(

6
examples/foundational/07z-interruptible-sarvam-http.py
View File

@@ -25,7 +25,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamHttpTTSService
from pipecat.services.sarvam.tts import SarvamHttpTTSService, SarvamHttpTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -65,7 +65,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SarvamHttpTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
aiohttp_session=session,
params=SarvamHttpTTSService.InputParams(language=Language.EN),
settings=SarvamHttpTTSSettings(
language=Language.EN,
),
)
llm = OpenAILLMService(

14
examples/foundational/07z-interruptible-sarvam.py
View File

@@ -22,8 +22,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamTTSService
from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
from pipecat.services.sarvam.tts import SarvamTTSService, SarvamTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,13 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
model="saarika:v2.5",
settings=SarvamSTTSettings(
model="saarika:v2.5",
),
)
tts = SarvamTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
model="bulbul:v2",
voice_id="manisha",
settings=SarvamTTSSettings(
model="bulbul:v2",
voice="manisha",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

20
examples/foundational/07za-interruptible-soniox.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.soniox.stt import SonioxInputParams, SonioxSTTService
from pipecat.services.soniox.stt import SonioxSTTService, SonioxSTTSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -51,17 +51,21 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
params=SonioxInputParams(
language_hints=[Language.EN],
language_hints_strict=True,
stt = (
SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
settings=SonioxSTTSettings(
language_hints=[Language.EN],
language_hints_strict=True,
),
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

10
examples/foundational/07zb-interruptible-inworld-http.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.inworld.tts import InworldHttpTTSService
from pipecat.services.inworld.tts import InworldHttpTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -58,10 +58,12 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = InworldHttpTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
aiohttp_session=session,
voice_id="Ashley",
model="inworld-tts-1",
# Set to False for non-streaming mode or True for streaming mode.
streaming=True,
settings=InworldTTSSettings(
voice="Ashley",
model="inworld-tts-1",
),
# Set to False for non-streaming mode or True for streaming mode.
)
llm = OpenAILLMService(

10
examples/foundational/07zb-interruptible-inworld.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.inworld.tts import InworldTTSService
from pipecat.services.inworld.tts import InworldTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,9 +56,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = InworldTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
voice_id="Ashley",
model="inworld-tts-1",
temperature=1.1,
settings=InworldTTSSettings(
voice="Ashley",
model="inworld-tts-1",
temperature=1.1,
),
)
llm = OpenAILLMService(

6
examples/foundational/07zc-interruptible-asyncai-http.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService, AsyncAITTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -60,7 +60,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAIHttpTTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
settings=AsyncAITTSSettings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
aiohttp_session=session,
)

6
examples/foundational/07zc-interruptible-asyncai.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.asyncai.tts import AsyncAITTSService
from pipecat.services.asyncai.tts import AsyncAITTSService, AsyncAITTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -57,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAITTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
settings=AsyncAITTSSettings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
)
llm = OpenAILLMService(

6
examples/foundational/07zd-interruptible-aicoustics.py
View File

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
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.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -77,7 +77,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/07ze-interruptible-hume.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService, HumeTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = HumeTTSService(
api_key=os.getenv("HUME_API_KEY"),
# Replace with your Hume voice ID
voice_id="f898a92e-685f-43fa-985b-a46920f0650b",
settings=HumeTTSSettings(
voice="f898a92e-685f-43fa-985b-a46920f0650b",
),
)
llm = OpenAILLMService(

10
examples/foundational/07zf-interruptible-gradium.py
View File

@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.gradium.stt import GradiumSTTService
from pipecat.services.gradium.tts import GradiumTTSService
from pipecat.services.gradium.stt import GradiumSTTService, GradiumSTTSettings
from pipecat.services.gradium.tts import GradiumTTSService, GradiumTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -55,15 +55,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GradiumSTTService(
api_key=os.getenv("GRADIUM_API_KEY"),
api_endpoint_base_url="wss://us.api.gradium.ai/api/speech/asr",
params=GradiumSTTService.InputParams(
settings=GradiumSTTSettings(
language=Language.EN,
),
)
tts = GradiumTTSService(
api_key=os.getenv("GRADIUM_API_KEY"),
voice_id="YTpq7expH9539ERJ",
url="wss://us.api.gradium.ai/api/speech/tts",
settings=GradiumTTSSettings(
voice="YTpq7expH9539ERJ",
),
)
llm = OpenAILLMService(

6
examples/foundational/07zg-interruptible-camb.py
View File

@@ -21,7 +21,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.camb.tts import CambTTSService
from pipecat.services.camb.tts import CambTTSService, CambTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CambTTSService(
api_key=os.getenv("CAMB_API_KEY"),
model="mars-flash",
settings=CambTTSSettings(
model="mars-flash",
),
)
llm = OpenAILLMService(

8
examples/foundational/07zi-interruptible-piper.py
View File

@@ -23,7 +23,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.piper.tts import PiperTTSService
from pipecat.services.piper.tts import PiperTTSService, PiperTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,7 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = PiperTTSService(voice_id="en_US-ryan-high")
tts = PiperTTSService(
settings=PiperTTSSettings(
voice="en_US-ryan-high",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

8
examples/foundational/07zj-interruptible-kokoro.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.kokoro.tts import KokoroTTSService
from pipecat.services.kokoro.tts import KokoroTTSService, KokoroTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,7 +54,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = KokoroTTSService(voice_id="af_heart")
tts = KokoroTTSService(
settings=KokoroTTSSettings(
voice="af_heart",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),

6
examples/foundational/07zk-interruptible-resemble.py
View File

@@ -23,7 +23,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.resembleai.tts import ResembleAITTSService
from pipecat.services.resembleai.tts import ResembleAITTSService, ResembleAITTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,7 +59,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ResembleAITTSService(
api_key=os.getenv("RESEMBLE_API_KEY"),
voice_id=os.getenv("RESEMBLE_VOICE_UUID"),
settings=ResembleAITTSSettings(
voice=os.getenv("RESEMBLE_VOICE_UUID"),
),
)
llm = OpenAILLMService(

6
examples/foundational/08-custom-frame-processor.py
View File

@@ -26,7 +26,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -95,7 +95,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/10-wake-phrase.py
View File

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/11-sound-effects.py
View File

@@ -30,7 +30,7 @@ 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.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -111,7 +111,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
context = LLMContext()

6
examples/foundational/12-describe-image-openai.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -53,7 +53,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/12a-describe-image-anthropic.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,7 +53,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(

20
examples/foundational/12b-describe-image-aws.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,16 +53,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AWSBedrockLLMService(
aws_region="us-west-2",
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
)

6
examples/foundational/12c-describe-image-gemini-flash.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -53,7 +53,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GoogleLLMService(

6
examples/foundational/12d-describe-image-moondream.py
View File

@@ -17,7 +17,7 @@ from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.moondream.vision import MoondreamService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -42,7 +42,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
vision = MoondreamService()

6
examples/foundational/13b-deepgram-transcription.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService, Language, LiveOptions
from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings, Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -49,7 +49,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
live_options=LiveOptions(language=Language.EN),
settings=DeepgramSTTSettings(
language=Language.EN,
),
)
tl = TranscriptionLogger()

6
examples/foundational/13c-gladia-transcription.py
View File

@@ -50,7 +50,11 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY"),
region=os.getenv("GLADIA_REGION"),
# live_options=LiveOptions(language=Language.FR),
# settings=GladiaSTTSettings(
# language_config=LanguageConfig(
# languages=[Language.FR],
# ),
# ),
)
tl = TranscriptionLogger()

12
examples/foundational/13c-gladia-translation.py
View File

@@ -22,7 +22,7 @@ from pipecat.services.gladia.config import (
RealtimeProcessingConfig,
TranslationConfig,
)
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,16 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GladiaSTTService(
api_key=os.getenv("GLADIA_API_KEY"),
region=os.getenv("GLADIA_REGION"),
params=GladiaInputParams(
settings=GladiaSTTSettings(
language_config=LanguageConfig(
languages=[Language.EN], # Input in English
languages=[Language.EN],
code_switching=False,
),
realtime_processing=RealtimeProcessingConfig(
translation=True, # Enable translation
translation=True,
translation_config=TranslationConfig(
target_languages=[Language.ES], # Translate to Spanish
model="enhanced", # Use the enhanced translation model
target_languages=[Language.ES],
model="enhanced",
),
),
),

7
examples/foundational/13d-assemblyai-transcription.py
View File

@@ -16,8 +16,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.assemblyai.models import AssemblyAIConnectionParams
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -50,8 +49,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
connection_params=AssemblyAIConnectionParams(
speech_model="u3-rt-pro",
settings=AssemblyAISTTSettings(
model="u3-rt-pro",
),
)

8
examples/foundational/13e-whisper-mlx.py
View File

@@ -18,7 +18,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.whisper.stt import MLXModel, WhisperSTTServiceMLX
from pipecat.services.whisper.stt import MLXModel, WhisperMLXSTTSettings, WhisperSTTServiceMLX
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -77,7 +77,11 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = WhisperSTTServiceMLX(model=MLXModel.LARGE_V3_TURBO)
stt = WhisperSTTServiceMLX(
settings=WhisperMLXSTTSettings(
model=MLXModel.LARGE_V3_TURBO,
),
)
tl = TranscriptionLogger()

6
examples/foundational/13g-sambanova-transcription.py
View File

@@ -19,7 +19,7 @@ from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.services.sambanova.stt import SambaNovaSTTService, SambaNovaSTTSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -79,7 +79,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
model="Whisper-Large-v3",
settings=SambaNovaSTTSettings(
model="Whisper-Large-v3",
),
api_key=os.getenv("SAMBANOVA_API_KEY"),
)

4
examples/foundational/13h-speechmatics-transcription.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService, SpeechmaticsSTTSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
params=SpeechmaticsSTTService.InputParams(
settings=SpeechmaticsSTTSettings(
language=Language.EN,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),

7
examples/foundational/13l-gradium-transcription.py
View File

@@ -16,7 +16,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.gradium.stt import GradiumSTTService
from pipecat.services.gradium.stt import GradiumSTTService, GradiumSTTSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -52,7 +52,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GradiumSTTService(
api_key=os.getenv("GRADIUM_API_KEY"),
api_endpoint_base_url="wss://us.api.gradium.ai/api/speech/asr",
params=GradiumSTTService.InputParams(language=Language.EN, delay_in_frames=8),
settings=GradiumSTTSettings(
language=Language.EN,
delay_in_frames=8,
),
)
tl = TranscriptionLogger()

8
examples/foundational/13m-openai-transcription.py
View File

@@ -18,7 +18,7 @@ from pipecat.pipeline.task import PipelineTask
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
from pipecat.services.openai.stt import OpenAIRealtimeSTTService, OpenAIRealtimeSTTSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -53,8 +53,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
settings=OpenAIRealtimeSTTSettings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
),
)
tl = TranscriptionLogger()

6
examples/foundational/14-function-calling.py
View File

@@ -23,7 +23,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
@@ -67,7 +67,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

22
examples/foundational/14a-function-calling-anthropic.py
View File

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -69,10 +69,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
llm.register_function("get_weather", get_weather)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
@@ -100,16 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
# todo: test with very short initial user message
# messages = [{"role": "system",
# "content": "You are a helpful assistant who can report the weather in any location in the universe. Respond concisely. Your response will be turned into speech so use only simple words and punctuation."},
# {"role": "user",
# "content": " Start the conversation by introducing yourself."}]
messages = [{"role": "user", "content": "Say 'hello' to start the conversation."}]
context = LLMContext(messages, tools)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

12
examples/foundational/14c-function-calling-together.py
View File

@@ -24,10 +24,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.together.llm import TogetherLLMService
from pipecat.services.together.llm import TogetherLLMService, TogetherLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -64,12 +64,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = TogetherLLMService(
api_key=os.getenv("TOGETHER_API_KEY"),
model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
settings=TogetherLLMSettings(
model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can also register a function_name of None to get all functions

6
examples/foundational/14d-function-calling-anthropic-video.py
View File

@@ -29,7 +29,7 @@ from pipecat.runner.utils import (
maybe_capture_participant_camera,
)
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,7 +90,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# Anthropic for vision analysis

20
examples/foundational/14d-function-calling-aws-video.py
View File

@@ -28,8 +28,8 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,17 +90,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# AWS for vision analysis
llm = AWSBedrockLLMService(
aws_region="us-west-2",
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
temperature=0.8,
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
)
llm.register_function("fetch_user_image", fetch_user_image)

6
examples/foundational/14d-function-calling-gemini-flash-video.py
View File

@@ -28,7 +28,7 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.llm_service import FunctionCallParams
@@ -90,7 +90,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# Google Gemini model for vision analysis

6
examples/foundational/14d-function-calling-moondream-video.py
View File

@@ -37,7 +37,7 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.moondream.vision import MoondreamService
@@ -121,7 +121,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

6
examples/foundational/14d-function-calling-openai-video.py
View File

@@ -29,7 +29,7 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
@@ -91,7 +91,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(

58
examples/foundational/14e-function-calling-google.py
View File

@@ -29,7 +29,7 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.llm_service import FunctionCallParams
@@ -100,10 +100,34 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
system_prompt = """\
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
Your response will be turned into speech so use only simple words and punctuation.
You have access to three tools: get_weather, get_restaurant_recommendation, and get_image.
You can respond to questions about the weather using the get_weather tool.
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
indicate you should use the get_image tool are:
- What do you see?
- What's in the video?
- Can you describe the video?
- Tell me about what you see.
- Tell me something interesting about what you see.
- What's happening in the video?
"""
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction=system_prompt,
)
llm.register_function("get_weather", get_weather)
llm.register_function("get_image", get_image)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
@@ -156,29 +180,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tools = ToolsSchema(standard_tools=[weather_function, get_image_function, restaurant_function])
system_prompt = """\
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
Your response will be turned into speech so use only simple words and punctuation.
You have access to three tools: get_weather, get_restaurant_recommendation, and get_image.
You can respond to questions about the weather using the get_weather tool.
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
indicate you should use the get_image tool are:
- What do you see?
- What's in the video?
- Can you describe the video?
- Tell me about what you see.
- Tell me something interesting about what you see.
- What's happening in the video?
"""
messages = [
{"role": "system", "content": system_prompt},
]
context = LLMContext(messages, tools)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -214,9 +216,9 @@ indicate you should use the get_image tool are:
client_id = get_transport_client_id(transport, client)
# Kick off the conversation.
messages.append(
context.add_message(
{
"role": "system",
"role": "user",
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
}
)

6
examples/foundational/14f-function-calling-groq.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.llm_service import FunctionCallParams
@@ -64,7 +64,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GroqLLMService(

6
examples/foundational/14g-function-calling-grok.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.grok.llm import GrokLLMService
from pipecat.services.llm_service import FunctionCallParams
@@ -64,7 +64,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GrokLLMService(

12
examples/foundational/14h-function-calling-azure.py
View File

@@ -24,8 +24,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.azure.llm import AzureLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.azure.llm import AzureLLMService, AzureLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -64,13 +64,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
model=os.getenv("AZURE_CHATGPT_MODEL"),
settings=AzureLLMSettings(
model=os.getenv("AZURE_CHATGPT_MODEL"),
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can also register a function_name of None to get all functions

12
examples/foundational/14i-function-calling-fireworks.py
View File

@@ -24,9 +24,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.fireworks.llm import FireworksLLMService
from pipecat.services.fireworks.llm import FireworksLLMService, FireworksLLMSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -64,12 +64,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = FireworksLLMService(
api_key=os.getenv("FIREWORKS_API_KEY"),
model="accounts/fireworks/models/gpt-oss-20b",
settings=FireworksLLMSettings(
model="accounts/fireworks/models/gpt-oss-20b",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can also register a function_name of None to get all functions

29
examples/foundational/14j-function-calling-nvidia.py
View File

@@ -24,10 +24,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.nvidia.llm import NvidiaLLMService
from pipecat.services.nvidia.llm import NvidiaLLMService, NvidiaLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -64,15 +64,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
# text_filters=[MarkdownTextFilter()],
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = NvidiaLLMService(
api_key=os.getenv("NVIDIA_API_KEY"),
model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
# Recommended when turning thinking off
params=NvidiaLLMService.InputParams(temperature=0.0),
settings=NvidiaLLMSettings(
model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
# Recommended when turning thinking off
temperature=0.0,
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
@@ -99,17 +103,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
required=["location", "format"],
)
tools = ToolsSchema(standard_tools=[weather_function])
messages = [
# Disable thinking by sending this message first
# Check the model for the corresponding "no thinking" message
{"role": "system", "content": "/no_think"},
{
"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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
},
]
context = LLMContext(messages, tools)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

6
examples/foundational/14k-function-calling-cerebras.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cerebras.llm import CerebrasLLMService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
@@ -64,7 +64,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = CerebrasLLMService(

12
examples/foundational/14l-function-calling-deepseek.py
View File

@@ -24,9 +24,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepseek.llm import DeepSeekLLMService
from pipecat.services.deepseek.llm import DeepSeekLLMService, DeepSeekLLMSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -64,12 +64,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = DeepSeekLLMService(
api_key=os.getenv("DEEPSEEK_API_KEY"),
model="deepseek-chat",
settings=DeepSeekLLMSettings(
model="deepseek-chat",
),
system_instruction="""You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
You have one functions available:

16
examples/foundational/14m-function-calling-openrouter.py
View File

@@ -24,10 +24,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.azure.tts import AzureTTSService
from pipecat.services.azure.tts import AzureTTSService, AzureTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openrouter.llm import OpenRouterLLMService
from pipecat.services.openrouter.llm import OpenRouterLLMService, OpenRouterLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -65,13 +65,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AzureTTSService(
api_key=os.getenv("AZURE_SPEECH_API_KEY"),
region=os.getenv("AZURE_SPEECH_REGION"),
voice="en-US-JennyNeural",
params=AzureTTSService.InputParams(language="en-US", rate="1.1", style="cheerful"),
settings=AzureTTSSettings(
voice="en-US-JennyNeural",
language="en-US",
rate="1.1",
style="cheerful",
),
)
llm = OpenRouterLLMService(
api_key=os.getenv("OPENROUTER_API_KEY"),
model="openai/gpt-4o-2024-11-20",
settings=OpenRouterLLMSettings(
model="openai/gpt-4o-2024-11-20",
),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can also register a function_name of None to get all functions

20
examples/foundational/14n-function-calling-perplexity.py
View File

@@ -28,7 +28,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.perplexity.llm import PerplexityLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -62,19 +62,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = PerplexityLLMService(api_key=os.getenv("PERPLEXITY_API_KEY"))
llm = PerplexityLLMService(
api_key=os.getenv("PERPLEXITY_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way, but try to be brief.",
)
messages = [
{
"role": "user",
"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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way, but try to be brief.",
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

11
examples/foundational/14o-function-calling-gemini-openai-format.py
View File

@@ -25,7 +25,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService, ElevenLabsTTSSettings
from pipecat.services.google.llm_openai import GoogleLLMOpenAIBetaService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -64,10 +64,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
settings=ElevenLabsTTSSettings(
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = GoogleLLMOpenAIBetaService(api_key=os.getenv("GOOGLE_API_KEY"))
llm = GoogleLLMOpenAIBetaService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
)
# You can aslo register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.
llm.register_function("get_current_weather", fetch_weather_from_api)

Some files were not shown because too many files have changed in this diff Show More