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

Merge pull request #3952 from pipecat-ai/mb/settings-alias

Browse Source 
Add Settings class attribute alias to all service classes
This commit is contained in:
Mark Backman
2026-03-09 10:45:10 -04:00
committed by GitHub
parent 1e615cd095 f7dc13c0de
commit c16e534f73
349 changed files with 1295 additions and 1160 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
COMMUNITY_INTEGRATIONS.md
View File

@@ -271,12 +271,15 @@ The rule of thumb: if a caller might send an update frame to change it at runtim
#### Wiring settings into `__init__`
Accept an **optional** `settings` parameter. Build a `default_settings` object with all fields set to real values, then merge any caller overrides with `apply_update`:
Accept an **optional** `settings` parameter. Build a `default_settings` object with all fields set to real values, then merge any caller overrides with `apply_update`.
Add a `Settings` **class attribute** that points to your settings dataclass. This lets callers access the settings class through the service itself (e.g. `MyTTSService.Settings(...)`) without a separate import:
```python
from typing import Optional
class MyTTSService(TTSService):
Settings = MyTTSSettings
_settings: MyTTSSettings
def __init__(
@@ -311,10 +314,10 @@ This pattern lets callers override only what they care about:
# Uses all defaults
svc = MyTTSService(api_key="sk-xxx")
# Overrides just the voice
# Overrides just the voice — access Settings through the service class
svc = MyTTSService(
api_key="sk-xxx",
settings=MyTTSSettings(voice="custom-voice"),
settings=MyTTSService.Settings(voice="custom-voice"),
)
```

4
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, RimeTTSSettings
from pipecat.services.rime.tts import RimeHttpTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -40,7 +40,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
aiohttp_session=session,
settings=RimeTTSSettings(
settings=RimeHttpTTSService.Settings(
voice="rex",
),
)

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

4
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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
load_dotenv(override=True)
@@ -29,7 +29,7 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)

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

8
examples/foundational/02-llm-say-one-thing.py
View File

@@ -16,8 +16,8 @@ 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, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -39,14 +39,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
),
)

4
examples/foundational/03-still-frame.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.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.fal.image import FalImageGenService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -45,7 +45,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
imagegen = FalImageGenService(
settings=FalImageGenSettings(
settings=FalImageGenService.Settings(
image_size="square_hd",
),
aiohttp_session=session,

4
examples/foundational/03a-local-still-frame.py
View File

@@ -17,7 +17,7 @@ from pipecat.frames.frames import TextFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.fal.image import FalImageGenService
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
load_dotenv(override=True)
@@ -37,7 +37,7 @@ async def main():
)
imagegen = FalImageGenService(
settings=FalImageGenSettings(
settings=FalImageGenService.Settings(
image_size="square_hd",
),
aiohttp_session=session,

8
examples/foundational/04-transports-small-webrtc.py
View File

@@ -27,9 +27,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
@@ -67,14 +67,14 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
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, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.daily.transport import DailyParams, DailyTransport
load_dotenv(override=True)
@@ -50,14 +50,14 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),

8
examples/foundational/04b-transports-livekit.py
View File

@@ -29,9 +29,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMUserAggregatorParams,
)
from pipecat.runner.livekit import configure
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
load_dotenv(override=True)
@@ -57,14 +57,14 @@ async def main():
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)

8
examples/foundational/05-sync-speech-and-image.py
View File

@@ -27,8 +27,8 @@ 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, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -98,13 +98,13 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaHttpTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(
settings=FalImageGenSettings(
settings=FalImageGenService.Settings(
image_size="square_hd",
),
aiohttp_session=session,

8
examples/foundational/05a-local-sync-speech-and-image.py
View File

@@ -28,8 +28,8 @@ 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, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
@@ -98,13 +98,13 @@ async def main():
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaHttpTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(
settings=FalImageGenSettings(
settings=FalImageGenService.Settings(
image_size="square_hd",
),
aiohttp_session=session,

8
examples/foundational/06-listen-and-respond.py
View File

@@ -28,9 +28,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -83,14 +83,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/06a-image-sync.py
View File

@@ -29,9 +29,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -100,14 +100,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07-interruptible-cartesia-http.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.cartesia.stt import CartesiaSTTService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,14 +59,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
aiohttp_session=session,
settings=CartesiaTTSSettings(
settings=CartesiaHttpTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

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

@@ -21,9 +21,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.tts_service import TextAggregationMode
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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/07a-interruptible-speechmatics-vad.py
View File

@@ -21,10 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.base_llm import OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService, SpeechmaticsSTTSettings
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService, SpeechmaticsTTSSettings
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -93,7 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
settings=SpeechmaticsSTTSettings(
settings=SpeechmaticsSTTService.Settings(
language=Language.EN,
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
# focus_speakers=["S1"],
@@ -104,7 +103,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
settings=SpeechmaticsTTSSettings(
settings=SpeechmaticsTTSService.Settings(
voice="sarah",
),
aiohttp_session=session,
@@ -112,7 +111,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),

11
examples/foundational/07a-interruptible-speechmatics.py
View File

@@ -22,10 +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.openai.base_llm import OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService, SpeechmaticsSTTSettings
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService, SpeechmaticsTTSSettings
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
from pipecat.services.speechmatics.tts import SpeechmaticsTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -76,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SpeechmaticsSTTService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
settings=SpeechmaticsSTTSettings(
settings=SpeechmaticsSTTService.Settings(
language=Language.EN,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),
@@ -84,7 +83,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SpeechmaticsTTSService(
api_key=os.getenv("SPEECHMATICS_API_KEY"),
settings=SpeechmaticsTTSSettings(
settings=SpeechmaticsTTSService.Settings(
voice="sarah",
),
aiohttp_session=session,
@@ -92,7 +91,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),

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

12
examples/foundational/07c-interruptible-deepgram-flux.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.deepgram.flux.stt import DeepgramFluxSTTService, DeepgramFluxSTTSettings
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.deepgram.flux.stt import DeepgramFluxSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,21 +56,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramFluxSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramFluxSTTSettings(
settings=DeepgramFluxSTTService.Settings(
min_confidence=0.3,
),
)
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07c-interruptible-deepgram-http.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.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramHttpTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.deepgram.tts import DeepgramHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramHttpTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
settings=DeepgramHttpTTSService.Settings(
voice="aura-2-andromeda-en",
),
aiohttp_session=session,
@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

7
examples/foundational/07c-interruptible-deepgram-sagemaker.py
View File

@@ -24,10 +24,7 @@ from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTService
from pipecat.services.deepgram.sagemaker.tts import (
DeepgramSageMakerTTSService,
DeepgramSageMakerTTSSettings,
)
from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -72,7 +69,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramSageMakerTTSService(
endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
settings=DeepgramSageMakerTTSSettings(
settings=DeepgramSageMakerTTSService.Settings(
voice="aura-2-andromeda-en",
),
)

12
examples/foundational/07c-interruptible-deepgram-vad.py
View File

@@ -21,9 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -55,7 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramSTTSettings(
settings=DeepgramSTTService.Settings(
vad_events=True,
utterance_end_ms="1000",
),
@@ -63,14 +63,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07c-interruptible-deepgram.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.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,14 +57,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
settings=DeepgramTTSService.Settings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07d-interruptible-elevenlabs-http.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.elevenlabs.stt import ElevenLabsSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService, ElevenLabsHttpTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsHttpTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
aiohttp_session=session,
settings=ElevenLabsHttpTTSSettings(
settings=ElevenLabsHttpTTSService.Settings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07d-interruptible-elevenlabs.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.elevenlabs.stt import ElevenLabsRealtimeSTTService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService, ElevenLabsTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,14 +57,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
settings=ElevenLabsTTSSettings(
settings=ElevenLabsTTSService.Settings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

4
examples/foundational/07f-interruptible-azure-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.azure.llm import AzureLLMService, AzureLLMSettings
from pipecat.services.azure.llm import AzureLLMService
from pipecat.services.azure.stt import AzureSTTService
from pipecat.services.azure.tts import AzureHttpTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
settings=AzureLLMSettings(
settings=AzureLLMService.Settings(
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.",
),

4
examples/foundational/07f-interruptible-azure.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.azure.llm import AzureLLMService, AzureLLMSettings
from pipecat.services.azure.llm import AzureLLMService
from pipecat.services.azure.stt import AzureSTTService
from pipecat.services.azure.tts import AzureTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -65,7 +65,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
settings=AzureLLMSettings(
settings=AzureLLMService.Settings(
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.",
),

12
examples/foundational/07g-interruptible-openai-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.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.stt import OpenAISTTService, OpenAISTTSettings
from pipecat.services.openai.tts import OpenAITTSService, OpenAITTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import OpenAISTTService
from pipecat.services.openai.tts import OpenAITTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAISTTService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAISTTSettings(
settings=OpenAISTTService.Settings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
),
@@ -62,14 +62,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAITTSSettings(
settings=OpenAITTSService.Settings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are very knowledgable about dogs. 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.",
),
)

12
examples/foundational/07g-interruptible-openai.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.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.stt import OpenAIRealtimeSTTService, OpenAIRealtimeSTTSettings
from pipecat.services.openai.tts import OpenAITTSService, OpenAITTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
from pipecat.services.openai.tts import OpenAITTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,7 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAIRealtimeSTTSettings(
settings=OpenAIRealtimeSTTService.Settings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
language=Language.EN,
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAITTSSettings(
settings=OpenAITTSService.Settings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are very knowledgable about dogs. 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.",
),
)

8
examples/foundational/07h-interruptible-openpipe.py
View File

@@ -23,9 +23,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openpipe.llm import OpenPipeLLMService, OpenPipeLLMSettings
from pipecat.services.openpipe.llm import OpenPipeLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,7 +57,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("OPENAI_API_KEY"),
openpipe_api_key=os.getenv("OPENPIPE_API_KEY"),
tags={"conversation_id": f"pipecat-{timestamp}"},
settings=OpenPipeLLMSettings(
settings=OpenPipeLLMService.Settings(
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.",
),
)

8
examples/foundational/07i-interruptible-xtts.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.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.xtts.tts import XTTSService, XTTSTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.xtts.tts import XTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = XTTSService(
aiohttp_session=session,
settings=XTTSTTSSettings(
settings=XTTSService.Settings(
voice="Claribel Dervla",
),
base_url="http://localhost:8000",
@@ -67,7 +67,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
examples/foundational/07j-interruptible-gladia-vad.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.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -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"),
settings=GladiaSTTSettings(
settings=GladiaSTTService.Settings(
language_config=LanguageConfig(
languages=[Language.EN],
),
@@ -68,14 +68,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
examples/foundational/07j-interruptible-gladia.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.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -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"),
settings=GladiaSTTSettings(
settings=GladiaSTTService.Settings(
language_config=LanguageConfig(
languages=[Language.EN],
)
@@ -66,14 +66,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07k-interruptible-lmnt.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.deepgram.stt import DeepgramSTTService
from pipecat.services.lmnt.tts import LmntTTSService, LmntTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.lmnt.tts import LmntTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = LmntTTSService(
api_key=os.getenv("LMNT_API_KEY"),
settings=LmntTTSSettings(
settings=LmntTTSService.Settings(
voice="morgan",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

4
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, GroqLLMSettings
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.groq.tts import GroqTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
settings=GroqLLMSettings(
settings=GroqLLMService.Settings(
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.",
),

4
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, AWSPollyTTSSettings
from pipecat.services.aws.tts import AWSPollyTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -95,7 +95,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AWSPollyTTSService(
region="us-west-2", # only specific regions support generative TTS
settings=AWSPollyTTSSettings(
settings=AWSPollyTTSService.Settings(
voice="Joanna",
engine="generative",
rate="1.1",

8
examples/foundational/07m-interruptible-aws.py
View File

@@ -20,9 +20,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.aws.stt import AWSTranscribeSTTService
from pipecat.services.aws.tts import AWSPollyTTSService, AWSPollyTTSSettings
from pipecat.services.aws.tts import AWSPollyTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AWSPollyTTSService(
region="us-west-2", # only specific regions support generative TTS
settings=AWSPollyTTSSettings(
settings=AWSPollyTTSService.Settings(
voice="Joanna",
engine="generative",
rate="1.1",
@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
settings=AWSBedrockLLMService.Settings(
model="us.anthropic.claude-sonnet-4-6",
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.",

12
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, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -71,14 +71,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GoogleSTTService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleSTTSettings(
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
),
)
tts = GoogleTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleTTSSettings(
settings=GoogleTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
@@ -86,7 +86,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
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.",

12
examples/foundational/07n-interruptible-gemini.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, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GeminiTTSService, GeminiTTSSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GeminiTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot with Gemini TTS")
stt = GoogleSTTService(
settings=GoogleSTTSettings(
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
@@ -62,7 +62,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = GeminiTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GeminiTTSSettings(
settings=GeminiTTSService.Settings(
model="gemini-2.5-flash-tts",
voice="Charon",
language=Language.EN_US,
@@ -73,7 +73,7 @@ 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(
settings=GoogleLLMService.Settings(
system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
IMPORTANT: You're using Gemini TTS which supports expressive markup tags. You can use these tags in your responses:

12
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, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleHttpTTSService, GoogleHttpTTSSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleHttpTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
settings=GoogleSTTSettings(
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
# Add model to use a specific model
# model="chirp_3",
@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = GoogleHttpTTSService(
settings=GoogleHttpTTSSettings(
settings=GoogleHttpTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.GoogleLLMSettings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)

12
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, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
settings=GoogleSTTSettings(
settings=GoogleSTTService.Settings(
languages=[Language.EN_US],
# Add model to use a specific model
# model="chirp_3",
@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = GoogleTTSService(
settings=GoogleTTSSettings(
settings=GoogleTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
@@ -73,7 +73,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),

12
examples/foundational/07o-interruptible-assemblyai-turn-detection.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.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -93,7 +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
settings=AssemblyAISTTSettings(
settings=AssemblyAISTTService.Settings(
model="u3-rt-pro",
# Optional: Tune turn detection timing (defaults shown below)
# min_turn_silence=100, # Default
@@ -107,14 +107,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07o-interruptible-assemblyai.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.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,14 +59,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07p-interruptible-krisp-viva.py
View File

@@ -43,9 +43,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -85,14 +85,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07p-interruptible-krisp.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.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,14 +60,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
settings=DeepgramTTSService.Settings(
voice="aura-helios-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07q-interruptible-rime-http.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.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.rime.tts import RimeHttpTTSService, RimeTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.rime.tts import RimeHttpTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,7 +60,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
settings=RimeTTSSettings(
settings=RimeHttpTTSService.Settings(
voice="luna",
model="arcana",
),
@@ -70,7 +70,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07q-interruptible-rime.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.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.rime.tts import RimeTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
settings=RimeTTSSettings(
settings=RimeTTSService.Settings(
voice="luna",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

4
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, NvidiaLLMSettings
from pipecat.services.nvidia.llm import NvidiaLLMService
from pipecat.services.nvidia.stt import NvidiaSTTService
from pipecat.services.nvidia.tts import NvidiaTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,7 +56,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = NvidiaLLMService(
api_key=os.getenv("NVIDIA_API_KEY"),
settings=NvidiaLLMSettings(
settings=NvidiaLLMService.Settings(
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.",
),

8
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, GoogleLLMSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -216,7 +216,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
model="gemini-2.5-flash",
system_instruction=system_message,
# force a certain amount of thinking if you want it
@@ -225,7 +225,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tts = GoogleTTSService(
settings=GoogleTTSSettings(
settings=GoogleTTSService.Settings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),

8
examples/foundational/07t-interruptible-fish.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.deepgram.stt import DeepgramSTTService
from pipecat.services.fish.tts import FishAudioTTSService, FishAudioTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.fish.tts import FishAudioTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,14 +57,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = FishAudioTTSService(
api_key=os.getenv("FISH_API_KEY"),
settings=FishAudioTTSSettings(
settings=FishAudioTTSService.Settings(
voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07v-interruptible-neuphonic-http.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.deepgram.stt import DeepgramSTTService
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,7 +60,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicHttpTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
settings=NeuphonicTTSSettings(
settings=NeuphonicHttpTTSService.Settings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
aiohttp_session=session,
@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07v-interruptible-neuphonic.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.deepgram.stt import DeepgramSTTService
from pipecat.services.neuphonic.tts import NeuphonicTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.neuphonic.tts import NeuphonicTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
settings=NeuphonicTTSSettings(
settings=NeuphonicTTSService.Settings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07w-interruptible-fal.py
View File

@@ -23,9 +23,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.fal.stt import FalSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -62,14 +62,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07x-interruptible-local.py
View File

@@ -21,9 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
load_dotenv(override=True)
@@ -44,14 +44,14 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="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.",
),
)

8
examples/foundational/07y-interruptible-minimax.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.deepgram.stt import DeepgramSTTService
from pipecat.services.minimax.tts import MiniMaxHttpTTSService, MiniMaxTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.minimax.tts import MiniMaxHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -63,14 +63,14 @@ 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,
settings=MiniMaxTTSSettings(
settings=MiniMaxHttpTTSService.Settings(
language=Language.EN,
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
examples/foundational/07z-interruptible-sarvam-http.py
View File

@@ -23,9 +23,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
from pipecat.services.sarvam.tts import SarvamHttpTTSService, SarvamHttpTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamHttpTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
settings=SarvamSTTSettings(
settings=SarvamSTTService.Settings(
model="saarika:v2.5",
),
)
@@ -67,14 +67,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SarvamHttpTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
aiohttp_session=session,
settings=SarvamHttpTTSSettings(
settings=SarvamHttpTTSService.Settings(
language=Language.EN_IN,
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
examples/foundational/07z-interruptible-sarvam.py
View File

@@ -21,9 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
from pipecat.services.sarvam.tts import SarvamTTSService, SarvamTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,21 +54,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
settings=SarvamSTTSettings(
settings=SarvamSTTService.Settings(
model="saarika:v2.5",
),
)
tts = SarvamTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
settings=SarvamTTSSettings(
settings=SarvamTTSService.Settings(
model="bulbul:v2",
voice="manisha",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
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, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.soniox.stt import SonioxSTTService, SonioxSTTSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.soniox.stt import SonioxSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
settings=SonioxSTTSettings(
settings=SonioxSTTService.Settings(
# Add language hints to use a specific language
# Add strict mode to enforce the language hints
language_hints=[Language.EN],
@@ -63,14 +63,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zb-interruptible-inworld-http.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.deepgram.stt import DeepgramSTTService
from pipecat.services.inworld.tts import InworldHttpTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.inworld.tts import InworldHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,7 +59,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("INWORLD_API_KEY", ""),
aiohttp_session=session,
streaming=True,
settings=InworldTTSSettings(
settings=InworldHttpTTSService.Settings(
voice="Ashley",
model="inworld-tts-1",
),
@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
),
)

8
examples/foundational/07zb-interruptible-inworld.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.stt import DeepgramSTTService
from pipecat.services.inworld.tts import InworldTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.inworld.tts import InworldTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,7 +54,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = InworldTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
settings=InworldTTSSettings(
settings=InworldTTSService.Settings(
voice="Ashley",
model="inworld-tts-1",
temperature=1.1,
@@ -63,7 +63,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful AI demonstrating Inworld AI's TTS. 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 friendly and helpful way.",
),
)

8
examples/foundational/07zc-interruptible-asyncai-http.py
View File

@@ -23,9 +23,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService, AsyncAITTSSettings
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,7 +60,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAIHttpTTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
settings=AsyncAITTSSettings(
settings=AsyncAIHttpTTSService.Settings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
aiohttp_session=session,
@@ -68,7 +68,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zc-interruptible-asyncai.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.asyncai.tts import AsyncAITTSService, AsyncAITTSSettings
from pipecat.services.asyncai.tts import AsyncAITTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,14 +57,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAITTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
settings=AsyncAITTSSettings(
settings=AsyncAITTSService.Settings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zd-interruptible-aicoustics.py
View File

@@ -25,9 +25,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -77,14 +77,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07ze-interruptible-hume.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.deepgram.stt import DeepgramSTTService
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService, HumeTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,14 +59,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = HumeTTSService(
api_key=os.getenv("HUME_API_KEY"),
# Replace with your Hume voice ID
settings=HumeTTSSettings(
settings=HumeTTSService.Settings(
voice="f898a92e-685f-43fa-985b-a46920f0650b",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

12
examples/foundational/07zf-interruptible-gradium.py
View File

@@ -21,9 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.gradium.stt import GradiumSTTService, GradiumSTTSettings
from pipecat.services.gradium.tts import GradiumTTSService, GradiumTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.gradium.stt import GradiumSTTService
from pipecat.services.gradium.tts import GradiumTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,7 +55,7 @@ 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",
settings=GradiumSTTSettings(
settings=GradiumSTTService.Settings(
language=Language.EN,
),
)
@@ -63,14 +63,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = GradiumTTSService(
api_key=os.getenv("GRADIUM_API_KEY"),
url="wss://us.api.gradium.ai/api/speech/tts",
settings=GradiumTTSSettings(
settings=GradiumTTSService.Settings(
voice="YTpq7expH9539ERJ",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zg-interruptible-camb.py
View File

@@ -21,9 +21,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.camb.tts import CambTTSService, CambTTSSettings
from pipecat.services.camb.tts import CambTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CambTTSService(
api_key=os.getenv("CAMB_API_KEY"),
settings=CambTTSSettings(
settings=CambTTSService.Settings(
model="mars-flash",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
),
)

8
examples/foundational/07zi-interruptible-piper.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.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.piper.tts import PiperTTSService, PiperTTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.piper.tts import PiperTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -55,14 +55,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = PiperTTSService(
settings=PiperTTSSettings(
settings=PiperTTSService.Settings(
voice="en_US-ryan-high",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zj-interruptible-kokoro.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.stt import DeepgramSTTService
from pipecat.services.kokoro.tts import KokoroTTSService, KokoroTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.kokoro.tts import KokoroTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -55,14 +55,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = KokoroTTSService(
settings=KokoroTTSSettings(
settings=KokoroTTSService.Settings(
voice="af_heart",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/07zk-interruptible-resemble.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.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.resembleai.tts import ResembleAITTSService, ResembleAITTSSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.resembleai.tts import ResembleAITTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,14 +59,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ResembleAITTSService(
api_key=os.getenv("RESEMBLE_API_KEY"),
settings=ResembleAITTSSettings(
settings=ResembleAITTSService.Settings(
voice=os.getenv("RESEMBLE_VOICE_UUID"),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/08-custom-frame-processor.py
View File

@@ -26,9 +26,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -95,14 +95,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/10-wake-phrase.py
View File

@@ -22,9 +22,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
),
)

8
examples/foundational/11-sound-effects.py
View File

@@ -30,9 +30,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -106,14 +106,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)

8
examples/foundational/12-describe-image-openai.py
View File

@@ -23,9 +23,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,14 +53,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/12a-describe-image-anthropic.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.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,14 +53,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
settings=AnthropicLLMSettings(
settings=AnthropicLLMService.Settings(
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.",
),
)

8
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, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,14 +53,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
settings=AWSBedrockLLMService.Settings(
model="us.anthropic.claude-sonnet-4-6",
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.",

8
examples/foundational/12c-describe-image-gemini-flash.py
View File

@@ -23,9 +23,9 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,14 +53,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
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.",
),
)

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

4
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, DeepgramSTTSettings, Language
from pipecat.services.deepgram.stt import DeepgramSTTService, 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 +49,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramSTTSettings(
settings=DeepgramSTTService.Settings(
language=Language.EN,
),
)

5
examples/foundational/13c-gladia-translation.py
View File

@@ -17,12 +17,11 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.gladia.config import (
GladiaInputParams,
LanguageConfig,
RealtimeProcessingConfig,
TranslationConfig,
)
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,7 +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"),
settings=GladiaSTTSettings(
settings=GladiaSTTService.Settings(
language_config=LanguageConfig(
languages=[Language.EN],
code_switching=False,

4
examples/foundational/13d-assemblyai-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.assemblyai.stt import AssemblyAISTTService, AssemblyAISTTSettings
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -49,7 +49,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
settings=AssemblyAISTTSettings(
settings=AssemblyAISTTService.Settings(
model="u3-rt-pro",
),
)

4
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, WhisperMLXSTTSettings, WhisperSTTServiceMLX
from pipecat.services.whisper.stt import MLXModel, WhisperSTTServiceMLX
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -78,7 +78,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = WhisperSTTServiceMLX(
settings=WhisperMLXSTTSettings(
settings=WhisperSTTServiceMLX.Settings(
model=MLXModel.LARGE_V3_TURBO,
),
)

4
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, SambaNovaSTTSettings
from pipecat.services.sambanova.stt import SambaNovaSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -79,7 +79,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SambaNovaSTTService(
settings=SambaNovaSTTSettings(
settings=SambaNovaSTTService.Settings(
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, SpeechmaticsSTTSettings
from pipecat.services.speechmatics.stt import SpeechmaticsSTTService
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"),
settings=SpeechmaticsSTTSettings(
settings=SpeechmaticsSTTService.Settings(
language=Language.EN,
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
),

4
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, GradiumSTTSettings
from pipecat.services.gradium.stt import GradiumSTTService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -52,7 +52,7 @@ 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",
settings=GradiumSTTSettings(
settings=GradiumSTTService.Settings(
language=Language.EN,
delay_in_frames=8,
),

4
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, OpenAIRealtimeSTTSettings
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -53,7 +53,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAIRealtimeSTTSettings(
settings=OpenAIRealtimeSTTService.Settings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
),

8
examples/foundational/14-function-calling.py
View File

@@ -23,10 +23,10 @@ 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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -67,14 +67,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/14a-function-calling-anthropic.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.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -69,14 +69,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
settings=AnthropicLLMSettings(
settings=AnthropicLLMService.Settings(
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.",
),
)

8
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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.together.llm import TogetherLLMService, TogetherLLMSettings
from pipecat.services.together.llm import TogetherLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = TogetherLLMService(
api_key=os.getenv("TOGETHER_API_KEY"),
settings=TogetherLLMSettings(
settings=TogetherLLMService.Settings(
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.",
),

8
examples/foundational/14d-function-calling-anthropic-video.py
View File

@@ -28,8 +28,8 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.anthropic.llm import AnthropicLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -98,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Anthropic for vision analysis
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
settings=AnthropicLLMSettings(
settings=AnthropicLLMService.Settings(
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.",
),
)

8
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, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -98,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# AWS for vision analysis
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
settings=AWSBedrockLLMService.Settings(
model="us.anthropic.claude-sonnet-4-6",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,

8
examples/foundational/14d-function-calling-gemini-flash-video.py
View File

@@ -28,9 +28,9 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -90,7 +90,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -98,7 +98,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Google Gemini model for vision analysis
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
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.",
),
)

8
examples/foundational/14d-function-calling-moondream-video.py
View File

@@ -37,11 +37,11 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.moondream.vision import MoondreamService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -121,14 +121,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/14d-function-calling-openai-video.py
View File

@@ -29,10 +29,10 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -91,14 +91,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAILLMSettings(
settings=OpenAILLMService.Settings(
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.",
),
)

8
examples/foundational/14e-function-calling-google.py
View File

@@ -29,9 +29,9 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -100,7 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -126,7 +126,7 @@ indicate you should use the get_image tool are:
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
settings=GoogleLLMService.Settings(
system_instruction=system_prompt,
),
)

8
examples/foundational/14f-function-calling-groq.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.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
settings=GroqLLMSettings(
settings=GroqLLMService.Settings(
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.",
),
)

8
examples/foundational/14g-function-calling-grok.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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.grok.llm import GrokLLMService, GrokLLMSettings
from pipecat.services.grok.llm import GrokLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GrokLLMService(
api_key=os.getenv("GROK_API_KEY"),
settings=GrokLLMSettings(
settings=GrokLLMService.Settings(
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.",
),
)

8
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, AzureLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.azure.llm import AzureLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AzureLLMService(
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
settings=AzureLLMSettings(
settings=AzureLLMService.Settings(
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.",
),

8
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, CartesiaTTSSettings
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.fireworks.llm import FireworksLLMService, FireworksLLMSettings
from pipecat.services.fireworks.llm import FireworksLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -64,14 +64,14 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
settings=CartesiaTTSService.Settings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = FireworksLLMService(
api_key=os.getenv("FIREWORKS_API_KEY"),
settings=FireworksLLMSettings(
settings=FireworksLLMService.Settings(
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.",
),

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