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

Merge pull request #3877 from pipecat-ai/pk/service-init-cleanup

Browse Source 
Add `settings` as canonical init arg for all AIService descendants, d…
This commit is contained in:
kompfner
2026-03-06 10:01:50 -05:00
committed by GitHub
parent 3199168d3e 5b270fec8e
commit ac80b787bf
337 changed files with 8180 additions and 3560 deletions
Download Patch File Download Diff File Expand all files Collapse all files

95
COMMUNITY_INTEGRATIONS.md
View File

@@ -231,49 +231,102 @@ def can_generate_metrics(self) -> bool:
return True
```
### Dynamic Settings Updates
### Service Settings
STT, LLM, and TTS services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
Every STT, LLM, TTS, and image-generation service exposes a **Settings dataclass** that serves two roles:
Each service declares a settings dataclass that extends the appropriate base (`STTSettings`, `TTSSettings`, `LLMSettings`). Fields default to `NOT_GIVEN` so that update objects can represent sparse deltas:
1. **Store mode** — the service's `self._settings` holds the current value of every runtime-updatable field.
2. **Delta mode** — an update frame carries only the fields that changed; unset fields remain `NOT_GIVEN`.
#### Defining your Settings class
Extend `STTSettings`, `TTSSettings`, `LLMSettings`, or `ImageGenSettings`. The base classes already provide common fields (e.g. `model`, `voice`, `language`). You only need to add **service-specific knobs that should be runtime-updatable**:
```python
from dataclasses import dataclass, field
from pipecat.services.settings import STTSettings, NOT_GIVEN
from pipecat.services.settings import TTSSettings, NOT_GIVEN
@dataclass
class MySTTSettings(STTSettings):
"""Settings for my STT service.
class MyTTSSettings(TTSSettings):
"""Settings for MyTTS service.
Parameters:
region: Cloud region for the service.
speaking_rate: Speed multiplier (0.5–2.0).
"""
region: str = field(default_factory=lambda: NOT_GIVEN)
speaking_rate: float | None = field(default_factory=lambda: NOT_GIVEN)
```
The service stores its current settings in `self._settings` and declares the type with a class-level annotation for editor support:
**What goes in Settings vs. `__init__` params:**
| Belongs in Settings | Stays as `__init__` params |
| -------------------------------------------------------- | ----------------------------------------- |
| Model name, voice, language | API keys, auth tokens |
| Service-specific tuning knobs (rate, pitch, temperature) | Base URLs, endpoint overrides |
| Anything users may want to change mid-session | Audio encoding, sample format |
| | Connection parameters (timeouts, retries) |
The rule of thumb: if a caller might send an update frame to change it at runtime, it belongs in Settings. Everything else is init-only config stored as `self._xxx`.
#### 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`:
```python
class MySTTService(STTService):
_settings: MySTTSettings
from typing import Optional
def __init__(self, *, model: str, language: str, region: str, **kwargs):
# An initial value should be provided for every settings field.
# This will be validated at service start.
# (If you track sample_rate, it can be a placeholder value like 0; see
# "Sample Rate Handling").
super().__init__(
settings=MySTTSettings(model=model, language=language, region=region), **kwargs
class MyTTSService(TTSService):
_settings: MyTTSSettings
def __init__(
self,
*,
api_key: str,
settings: Optional[MyTTSSettings] = None,
**kwargs,
):
# 1. Defaults — every field has a real value (store mode).
default_settings = MyTTSSettings(
model="my-model-v1",
voice="default-voice",
language="en",
speaking_rate=1.0,
)
# 2. Merge caller overrides (only given fields win).
if settings is not None:
default_settings.apply_update(settings)
# 3. Pass the fully-populated settings to the base class.
super().__init__(settings=default_settings, **kwargs)
# 4. Init-only config stored separately.
self._api_key = api_key
```
This pattern lets callers override only what they care about:
```python
# Uses all defaults
svc = MyTTSService(api_key="sk-xxx")
# Overrides just the voice
svc = MyTTSService(
api_key="sk-xxx",
settings=MyTTSSettings(voice="custom-voice"),
)
```
#### Reacting to runtime changes
STT, LLM, and TTS services support runtime configuration changes via `*UpdateSettingsFrame`s (e.g. `STTUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, `LLMUpdateSettingsFrame`).
To react to runtime setting changes, override `_update_settings`. The base implementation applies the delta to `self._settings` and returns a `dict` mapping each changed field name to its **pre-update** value. Your override should call `super()` first, then act on the changed fields. A common implementation might look like:
```python
async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
"""Apply a settings update, reconfiguring the recognizer if needed."""
async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
"""Apply a settings update, reconfiguring the connection if needed."""
changed = await super()._update_settings(update)
if not changed:
@@ -292,7 +345,7 @@ Note that, in this example, the service requires a reconnect to apply the new la
If your service can't yet apply certain settings at runtime, call `self._warn_unhandled_updated_settings(changed)` with any unhandled field names so users get a clear log message:
```python
async def _update_settings(self, update: STTSettings) -> dict[str, Any]:
async def _update_settings(self, update: TTSSettings) -> dict[str, Any]:
changed = await super()._update_settings(update)
if not changed:

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

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

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

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

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

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

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

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

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

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

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -39,12 +39,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
settings=OpenAILLMSettings(
system_instruction="You are an LLM in a WebRTC session, and this is a 'hello world' demo.",
),
)
task = PipelineTask(

6
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
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -45,7 +45,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create an HTTP session
async with aiohttp.ClientSession() as session:
imagegen = FalImageGenService(
params=FalImageGenService.InputParams(image_size="square_hd"),
settings=FalImageGenSettings(
image_size="square_hd",
),
aiohttp_session=session,
key=os.getenv("FAL_KEY"),
)

6
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
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
load_dotenv(override=True)
@@ -37,7 +37,9 @@ async def main():
)
imagegen = FalImageGenService(
params=FalImageGenService.InputParams(image_size="square_hd"),
settings=FalImageGenSettings(
image_size="square_hd",
),
aiohttp_session=session,
key=os.getenv("FAL_KEY"),
)

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import TransportParams
from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
@@ -67,12 +67,16 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

14
examples/foundational/04a-transports-daily.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
LLMUserAggregatorParams,
)
from pipecat.runner.daily import configure
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.daily.transport import DailyParams, DailyTransport
load_dotenv(override=True)
@@ -50,13 +50,17 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o",
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.",
settings=OpenAILLMSettings(
model="gpt-4o",
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
load_dotenv(override=True)
@@ -57,12 +57,16 @@ async def main():
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
context = LLMContext()

12
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
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -98,11 +98,15 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(
params=FalImageGenService.InputParams(image_size="square_hd"),
settings=FalImageGenSettings(
image_size="square_hd",
),
aiohttp_session=session,
key=os.getenv("FAL_KEY"),
)

12
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
from pipecat.services.fal.image import FalImageGenService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.fal.image import FalImageGenService, FalImageGenSettings
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.tk import TkLocalTransport, TkTransportParams
@@ -98,11 +98,15 @@ async def main():
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
imagegen = FalImageGenService(
params=FalImageGenService.InputParams(image_size="square_hd"),
settings=FalImageGenSettings(
image_size="square_hd",
),
aiohttp_session=session,
key=os.getenv("FAL_KEY"),
)

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -83,12 +83,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
ml = MetricsLogger()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -100,12 +100,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaHttpTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -58,13 +58,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaHttpTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
aiohttp_session=session,
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

15
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.tts_service import TextAggregationMode
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,15 +56,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
# Alternatively, you can use TextAggregationMode.TOKEN to stream tokens instead of
# sentencesfor faster response times.
# text_aggregation_mode=TextAggregationMode.TOKEN,
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

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

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

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

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

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

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

21
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
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +56,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramFluxSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
params=DeepgramFluxSTTService.InputParams(min_confidence=0.3),
settings=DeepgramFluxSTTSettings(
min_confidence=0.3,
),
)
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

16
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.deepgram.tts import DeepgramHttpTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,18 +59,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramHttpTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
voice="aura-2-andromeda-en",
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
messages = []
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

19
examples/foundational/07c-interruptible-deepgram-sagemaker.py
View File

@@ -22,9 +22,12 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.deepgram.sagemaker.stt import DeepgramSageMakerSTTService
from pipecat.services.deepgram.sagemaker.tts import DeepgramSageMakerTTSService
from pipecat.services.deepgram.sagemaker.tts import (
DeepgramSageMakerTTSService,
DeepgramSageMakerTTSSettings,
)
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -69,14 +72,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = DeepgramSageMakerTTSService(
endpoint_name=os.getenv("SAGEMAKER_TTS_ENDPOINT_NAME"),
region=os.getenv("AWS_REGION"),
voice="aura-2-andromeda-en",
settings=DeepgramSageMakerTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = AWSBedrockLLMService(
aws_region=os.getenv("AWS_REGION"),
model="us.amazon.nova-pro-v1:0",
params=AWSBedrockLLMService.InputParams(temperature=0.8),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=AWSBedrockLLMSettings(
model="us.amazon.nova-pro-v1:0",
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.",
),
)
context = LLMContext()

23
examples/foundational/07c-interruptible-deepgram-vad.py
View File

@@ -7,7 +7,6 @@
import os
from deepgram import LiveOptions
from dotenv import load_dotenv
from loguru import logger
@@ -22,9 +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
from pipecat.services.deepgram.tts import DeepgramTTSService
from pipecat.services.openai.llm import OpenAILLMService
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,14 +55,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
live_options=LiveOptions(vad_events=True, utterance_end_ms="1000"),
settings=DeepgramSTTSettings(
vad_events=True,
utterance_end_ms="1000",
),
)
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

15
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -55,11 +55,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-2-andromeda-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-2-andromeda-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService, ElevenLabsHttpTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -63,13 +63,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsHttpTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
aiohttp_session=session,
settings=ElevenLabsHttpTTSSettings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.elevenlabs.tts import ElevenLabsTTSService, ElevenLabsTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,12 +57,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ElevenLabsTTSService(
api_key=os.getenv("ELEVENLABS_API_KEY", ""),
voice_id=os.getenv("ELEVENLABS_VOICE_ID", ""),
settings=ElevenLabsTTSSettings(
voice=os.getenv("ELEVENLABS_VOICE_ID", ""),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

6
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
from pipecat.services.azure.llm import AzureLLMService, AzureLLMSettings
from pipecat.services.azure.stt import AzureSTTService
from pipecat.services.azure.tts import AzureHttpTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -66,7 +66,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
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.",
settings=AzureLLMSettings(
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.",
),
)
context = LLMContext()

6
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
from pipecat.services.azure.llm import AzureLLMService, AzureLLMSettings
from pipecat.services.azure.stt import AzureSTTService
from pipecat.services.azure.tts import AzureTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -66,7 +66,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("AZURE_CHATGPT_API_KEY"),
endpoint=os.getenv("AZURE_CHATGPT_ENDPOINT"),
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.",
settings=AzureLLMSettings(
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.",
),
)
context = LLMContext()

23
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
from pipecat.services.openai.stt import OpenAISTTService
from pipecat.services.openai.tts import OpenAITTSService
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,15 +54,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAISTTService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
settings=OpenAISTTSettings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
),
)
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAITTSSettings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

29
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
from pipecat.services.openai.stt import OpenAIRealtimeSTTService
from pipecat.services.openai.tts import OpenAITTSService
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.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,20 +55,25 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = OpenAIRealtimeSTTService(
api_key=os.getenv("OPENAI_API_KEY"),
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
language=Language.EN,
# Uses local VAD by default.
# To enable server-side VAD, set turn_detection=None or
# a dict with server_vad settings.
# turn_detection={"type": "server_vad", "threshold": 0.5},
settings=OpenAIRealtimeSTTSettings(
model="gpt-4o-transcribe",
prompt="Expect words related to dogs, such as breed names.",
language=Language.EN,
),
)
tts = OpenAITTSService(api_key=os.getenv("OPENAI_API_KEY"), voice="ballad")
tts = OpenAITTSService(
api_key=os.getenv("OPENAI_API_KEY"),
settings=OpenAITTSSettings(
voice="ballad",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openpipe.llm import OpenPipeLLMService
from pipecat.services.openpipe.llm import OpenPipeLLMService, OpenPipeLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,7 +57,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
timestamp = int(time.time())
@@ -65,7 +67,9 @@ 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}"},
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.",
settings=OpenPipeLLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.xtts.tts import XTTSService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.xtts.tts import XTTSService, XTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,13 +59,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = XTTSService(
aiohttp_session=session,
voice_id="Claribel Dervla",
settings=XTTSSettings(
voice="Claribel Dervla",
),
base_url="http://localhost:8000",
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

32
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
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
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"),
params=GladiaInputParams(
settings=GladiaSTTSettings(
language_config=LanguageConfig(
languages=[Language.EN],
),
@@ -68,19 +68,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
messages = [
{
"role": "system",
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(
@@ -114,7 +114,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

32
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
from pipecat.services.gladia.config import GladiaInputParams, LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.gladia.config import LanguageConfig
from pipecat.services.gladia.stt import GladiaSTTService, GladiaSTTSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
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"),
params=GladiaInputParams(
settings=GladiaSTTSettings(
language_config=LanguageConfig(
languages=[Language.EN],
)
@@ -66,19 +66,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY", ""),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY", ""))
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY", ""),
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
messages = [
{
"role": "system",
"content": f"You are a helpful LLM. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
},
]
context = LLMContext(messages)
context = LLMContext()
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -109,7 +109,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append({"role": "system", "content": "Please introduce yourself to the user."})
context.add_message({"role": "system", "content": "Please introduce yourself to the user."})
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")

15
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.lmnt.tts import LmntTTSService, LmntTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,11 +54,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = LmntTTSService(api_key=os.getenv("LMNT_API_KEY"), voice_id="morgan")
tts = LmntTTSService(
api_key=os.getenv("LMNT_API_KEY"),
settings=LmntTTSSettings(
voice="morgan",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

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

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.groq.tts import GroqTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,8 +56,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
model="meta-llama/llama-4-maverick-17b-128e-instruct",
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.",
settings=GroqLLMSettings(
model="meta-llama/llama-4-maverick-17b-128e-instruct",
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
tts = GroqTTSService(api_key=os.getenv("GROQ_API_KEY"))

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

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

15
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
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.aws.stt import AWSTranscribeSTTService
from pipecat.services.aws.tts import AWSPollyTTSService
from pipecat.services.aws.tts import AWSPollyTTSService, AWSPollyTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,15 +54,20 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AWSPollyTTSService(
region="us-west-2", # only specific regions support generative TTS
voice_id="Joanna",
params=AWSPollyTTSService.InputParams(engine="generative", rate="1.1"),
settings=AWSPollyTTSSettings(
voice="Joanna",
engine="generative",
rate="1.1",
),
)
llm = AWSBedrockLLMService(
aws_region="us-west-2",
model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
params=AWSBedrockLLMService.InputParams(temperature=0.8),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=AWSBedrockLLMSettings(
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.",
),
)
context = LLMContext()

24
examples/foundational/07n-interruptible-gemini-image.py
View File

@@ -37,9 +37,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -70,21 +70,27 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
),
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleTTSService.InputParams(language=Language.EN_US),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash-image",
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,
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.",
settings=GoogleLLMSettings(
model="gemini-2.5-flash-image",
# model="gemini-3-pro-image-preview", # A more powerful model, but slower,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
context = LLMContext()

20
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
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GeminiTTSService
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.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,15 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot with Gemini TTS")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US),
settings=GoogleSTTSettings(
languages=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
tts = GeminiTTSService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
model="gemini-2.5-flash-tts",
voice_id="Charon",
params=GeminiTTSService.InputParams(
settings=GeminiTTSSettings(
model="gemini-2.5-flash-tts",
voice="Charon",
language=Language.EN_US,
prompt="You are a helpful AI assistant. Speak in a natural, conversational tone.",
),
@@ -71,7 +73,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
system_instruction="""You are a helpful AI assistant in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way.
settings=GoogleLLMSettings(
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:
- [sigh] - Insert a sigh sound
@@ -89,6 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
- "The answer is... [long pause] ...42!"
Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.""",
),
)
context = LLMContext()

29
examples/foundational/07n-interruptible-google-http.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleHttpTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleHttpTTSService, GoogleHttpTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,25 +54,30 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
location="us",
)
tts = GoogleHttpTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleHttpTTSService.InputParams(language=Language.EN_US),
settings=GoogleHttpTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# params=GoogleLLMService.InputParams(
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
# ),
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.",
settings=GoogleLLMSettings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
context = LLMContext()

29
examples/foundational/07n-interruptible-google.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.google.stt import GoogleSTTService, GoogleSTTSettings
from pipecat.services.google.tts import GoogleTTSService, GoogleTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -54,25 +54,30 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = GoogleSTTService(
params=GoogleSTTService.InputParams(languages=Language.EN_US, model="chirp_3"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
location="us",
)
tts = GoogleTTSService(
voice_id="en-US-Chirp3-HD-Charon",
params=GoogleTTSService.InputParams(language=Language.EN_US),
settings=GoogleTTSSettings(
voice="en-US-Chirp3-HD-Charon",
language=Language.EN_US,
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# params=GoogleLLMService.InputParams(
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096)
# ),
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.",
settings=GoogleLLMSettings(
model="gemini-2.5-flash",
# force a certain amount of thinking if you want it
# thinking=GoogleLLMService.ThinkingConfig(thinking_budget=4096),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
context = LLMContext()

17
examples/foundational/07o-interruptible-assemblyai-turn-detection.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.assemblyai.models import AssemblyAIConnectionParams
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -94,7 +93,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = AssemblyAISTTService(
api_key=os.getenv("ASSEMBLYAI_API_KEY"),
vad_force_turn_endpoint=False, # Use AssemblyAI's built-in turn detection
connection_params=AssemblyAIConnectionParams(
settings=AssemblyAISTTSettings(
speech_model="u3-rt-pro",
# Optional: Tune turn detection timing (defaults shown below)
# min_turn_silence=100, # Default
@@ -108,12 +107,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,12 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

13
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -84,12 +84,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121"
api_key=os.getenv("CARTESIA_API_KEY"),
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

15
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.deepgram.tts import DeepgramTTSService, DeepgramTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -58,11 +58,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")
tts = DeepgramTTSService(
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramTTSSettings(
voice="aura-helios-en",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

13
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
from pipecat.services.rime.tts import RimeHttpTTSService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.rime.tts import RimeHttpTTSService, RimeTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,14 +60,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeHttpTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
voice_id="luna",
settings=RimeTTSSettings(
voice="luna",
model="arcana",
),
model="arcana",
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.rime.tts import RimeTTSService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.rime.tts import RimeTTSService, RimeTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,12 +56,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = RimeTTSService(
api_key=os.getenv("RIME_API_KEY", ""),
voice_id="luna",
settings=RimeTTSSettings(
voice="luna",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

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

@@ -22,7 +22,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.nvidia.llm import NvidiaLLMService
from pipecat.services.nvidia.llm import NvidiaLLMService, NvidiaLLMSettings
from pipecat.services.nvidia.stt import NvidiaSTTService
from pipecat.services.nvidia.tts import NvidiaTTSService
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -56,8 +56,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = NvidiaLLMService(
api_key=os.getenv("NVIDIA_API_KEY"),
model="meta/llama-3.3-70b-instruct",
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.",
settings=NvidiaLLMSettings(
model="meta/llama-3.3-70b-instruct",
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))

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

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

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.fish.tts import FishAudioTTSService, FishAudioTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,12 +57,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = FishAudioTTSService(
api_key=os.getenv("FISH_API_KEY"),
model="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
settings=FishAudioTTSSettings(
model="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.neuphonic.tts import NeuphonicHttpTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,13 +60,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicHttpTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
settings=NeuphonicTTSSettings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.neuphonic.tts import NeuphonicTTSService, NeuphonicTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,12 +56,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = NeuphonicTTSService(
api_key=os.getenv("NEUPHONIC_API_KEY"),
voice_id="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
settings=NeuphonicTTSSettings(
voice="fc854436-2dac-4d21-aa69-ae17b54e98eb", # Emily
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.fal.stt import FalSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -62,12 +62,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.local.audio import LocalAudioTransport, LocalAudioTransportParams
load_dotenv(override=True)
@@ -44,12 +44,16 @@ async def main():
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.minimax.tts import MiniMaxHttpTTSService, MiniMaxTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -63,12 +63,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
api_key=os.getenv("MINIMAX_API_KEY", ""),
group_id=os.getenv("MINIMAX_GROUP_ID", ""),
aiohttp_session=session,
params=MiniMaxHttpTTSService.InputParams(language=Language.EN),
settings=MiniMaxTTSSettings(
language=Language.EN,
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

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
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamHttpTTSService
from pipecat.services.sarvam.tts import SarvamHttpTTSService, SarvamHttpTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -65,12 +65,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = SarvamHttpTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
aiohttp_session=session,
params=SarvamHttpTTSService.InputParams(language=Language.EN),
settings=SarvamHttpTTSSettings(
language=Language.EN,
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

20
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
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.tts import SarvamTTSService
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.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,17 +54,23 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
model="saarika:v2.5",
settings=SarvamSTTSettings(
model="saarika:v2.5",
),
)
tts = SarvamTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
model="bulbul:v2",
voice_id="manisha",
settings=SarvamTTSSettings(
model="bulbul:v2",
voice="manisha",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

26
examples/foundational/07za-interruptible-soniox.py
View File

@@ -22,9 +22,9 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.soniox.stt import SonioxInputParams, SonioxSTTService
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.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -51,22 +51,28 @@ transport_params = {
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
params=SonioxInputParams(
language_hints=[Language.EN],
language_hints_strict=True,
stt = (
SonioxSTTService(
api_key=os.getenv("SONIOX_API_KEY"),
settings=SonioxSTTSettings(
language_hints=[Language.EN],
language_hints_strict=True,
),
),
)
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

16
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.inworld.tts import InworldHttpTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -58,15 +58,19 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = InworldHttpTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
aiohttp_session=session,
voice_id="Ashley",
model="inworld-tts-1",
# Set to False for non-streaming mode or True for streaming mode.
streaming=True,
settings=InworldTTSSettings(
voice="Ashley",
model="inworld-tts-1",
),
# Set to False for non-streaming mode or True for streaming mode.
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

16
examples/foundational/07zb-interruptible-inworld.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.inworld.tts import InworldTTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.inworld.tts import InworldTTSService, InworldTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -56,14 +56,18 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = InworldTTSService(
api_key=os.getenv("INWORLD_API_KEY", ""),
voice_id="Ashley",
model="inworld-tts-1",
temperature=1.1,
settings=InworldTTSSettings(
voice="Ashley",
model="inworld-tts-1",
temperature=1.1,
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.asyncai.tts import AsyncAIHttpTTSService, AsyncAITTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -60,13 +60,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAIHttpTTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
settings=AsyncAITTSSettings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
aiohttp_session=session,
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.asyncai.tts import AsyncAITTSService, AsyncAITTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -57,12 +57,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = AsyncAITTSService(
api_key=os.getenv("ASYNCAI_API_KEY", ""),
voice_id=os.getenv("ASYNCAI_VOICE_ID", "e0f39dc4-f691-4e78-bba5-5c636692cc04"),
settings=AsyncAITTSSettings(
voice="e0f39dc4-f691-4e78-bba5-5c636692cc04",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -77,12 +77,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.hume.tts import HUME_SAMPLE_RATE, HumeTTSService, HumeTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_output import BaseOutputTransport
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -59,12 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = HumeTTSService(
api_key=os.getenv("HUME_API_KEY"),
# Replace with your Hume voice ID
voice_id="f898a92e-685f-43fa-985b-a46920f0650b",
settings=HumeTTSSettings(
voice="f898a92e-685f-43fa-985b-a46920f0650b",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

16
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
from pipecat.services.gradium.tts import GradiumTTSService
from pipecat.services.openai.llm import OpenAILLMService
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.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -55,20 +55,24 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GradiumSTTService(
api_key=os.getenv("GRADIUM_API_KEY"),
api_endpoint_base_url="wss://us.api.gradium.ai/api/speech/asr",
params=GradiumSTTService.InputParams(
settings=GradiumSTTSettings(
language=Language.EN,
),
)
tts = GradiumTTSService(
api_key=os.getenv("GRADIUM_API_KEY"),
voice_id="YTpq7expH9539ERJ",
url="wss://us.api.gradium.ai/api/speech/tts",
settings=GradiumTTSSettings(
voice="YTpq7expH9539ERJ",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.camb.tts import CambTTSService, CambTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,12 +56,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CambTTSService(
api_key=os.getenv("CAMB_API_KEY"),
model="mars-flash",
settings=CambTTSSettings(
model="mars-flash",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
settings=OpenAILLMSettings(
system_instruction="You are a helpful voice assistant powered by Camb AI text-to-speech. ",
),
)
context = LLMContext()

14
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
from pipecat.services.piper.tts import PiperTTSService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.piper.tts import PiperTTSService, PiperTTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,11 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = PiperTTSService(voice_id="en_US-ryan-high")
tts = PiperTTSService(
settings=PiperTTSSettings(
voice="en_US-ryan-high",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

14
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
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.kokoro.tts import KokoroTTSService, KokoroTTSSettings
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -54,11 +54,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = KokoroTTSService(voice_id="af_heart")
tts = KokoroTTSService(
settings=KokoroTTSSettings(
voice="af_heart",
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
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.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.resembleai.tts import ResembleAITTSService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.resembleai.tts import ResembleAITTSService, ResembleAITTSSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -59,12 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = ResembleAITTSService(
api_key=os.getenv("RESEMBLE_API_KEY"),
voice_id=os.getenv("RESEMBLE_VOICE_UUID"),
settings=ResembleAITTSSettings(
voice=os.getenv("RESEMBLE_VOICE_UUID"),
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -95,12 +95,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -56,12 +56,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
settings=OpenAILLMSettings(
system_instruction="You are a helpful assistant. Respond to what the user said in a creative and helpful way. Keep your responses brief.",
),
)
hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -106,12 +106,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
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"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,12 +53,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
settings=OpenAILLMSettings(
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.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,12 +53,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
settings=AnthropicLLMSettings(
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.",
),
)
context = LLMContext()

22
examples/foundational/12b-describe-image-aws.py
View File

@@ -23,8 +23,8 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,17 +53,21 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AWSBedrockLLMService(
aws_region="us-west-2",
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
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.",
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
),
)
context = LLMContext()

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -53,12 +53,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
settings=GoogleLLMSettings(
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.",
),
)
context = LLMContext()

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -67,12 +67,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
# You can also register a function_name of None to get all functions

26
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
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -69,10 +69,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = AnthropicLLMService(api_key=os.getenv("ANTHROPIC_API_KEY"))
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
settings=AnthropicLLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
llm.register_function("get_weather", get_weather)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
@@ -100,16 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tools = ToolsSchema(standard_tools=[weather_function, restaurant_function])
# todo: test with very short initial user message
# messages = [{"role": "system",
# "content": "You are a helpful assistant who can report the weather in any location in the universe. Respond concisely. Your response will be turned into speech so use only simple words and punctuation."},
# {"role": "user",
# "content": " Start the conversation by introducing yourself."}]
messages = [{"role": "user", "content": "Say 'hello' to start the conversation."}]
context = LLMContext(messages, tools)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),

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

@@ -24,10 +24,10 @@ from pipecat.processors.aggregators.llm_response_universal import (
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.together.llm import TogetherLLMService
from pipecat.services.together.llm import TogetherLLMService, TogetherLLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
@@ -64,13 +64,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = TogetherLLMService(
api_key=os.getenv("TOGETHER_API_KEY"),
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.",
settings=TogetherLLMSettings(
model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.anthropic.llm import AnthropicLLMService, AnthropicLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,13 +90,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# Anthropic for vision analysis
llm = AnthropicLLMService(
api_key=os.getenv("ANTHROPIC_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
settings=AnthropicLLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
),
)
llm.register_function("fetch_user_image", fetch_user_image)

22
examples/foundational/14d-function-calling-aws-video.py
View File

@@ -28,8 +28,8 @@ from pipecat.runner.utils import (
get_transport_client_id,
maybe_capture_participant_camera,
)
from pipecat.services.aws.llm import AWSBedrockLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.aws.llm import AWSBedrockLLMService, AWSBedrockLLMSettings
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -90,18 +90,22 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# AWS for vision analysis
llm = AWSBedrockLLMService(
aws_region="us-west-2",
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
params=AWSBedrockLLMService.InputParams(temperature=0.8),
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.",
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-3-7-sonnet-20250219-v1:0",
# Note: usually, prefer providing latency="optimized" param.
# Here we can't because AWS Bedrock doesn't support it for Claude 3.7,
# which we need for image input.
temperature=0.8,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
),
)
llm.register_function("fetch_user_image", fetch_user_image)

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -90,13 +90,17 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
# Google Gemini model for vision analysis
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
settings=GoogleLLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
),
)
llm.register_function("fetch_user_image", fetch_user_image)

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.moondream.vision import MoondreamService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -121,12 +121,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
),
)
llm.register_function("fetch_user_image", fetch_user_image)

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -91,12 +91,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = OpenAILLMService(
api_key=os.getenv("OPENAI_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
settings=OpenAILLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are able to describe images from the user camera.",
),
)
llm.register_function("fetch_user_image", fetch_user_image)

62
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.llm import GoogleLLMService, GoogleLLMSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -100,10 +100,36 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
system_prompt = """\
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
Your response will be turned into speech so use only simple words and punctuation.
You have access to three tools: get_weather, get_restaurant_recommendation, and get_image.
You can respond to questions about the weather using the get_weather tool.
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
indicate you should use the get_image tool are:
- What do you see?
- What's in the video?
- Can you describe the video?
- Tell me about what you see.
- Tell me something interesting about what you see.
- What's happening in the video?
"""
llm = GoogleLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
settings=GoogleLLMSettings(
system_instruction=system_prompt,
),
)
llm.register_function("get_weather", get_weather)
llm.register_function("get_image", get_image)
llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)
@@ -156,29 +182,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
)
tools = ToolsSchema(standard_tools=[weather_function, get_image_function, restaurant_function])
system_prompt = """\
You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
Your response will be turned into speech so use only simple words and punctuation.
You have access to three tools: get_weather, get_restaurant_recommendation, and get_image.
You can respond to questions about the weather using the get_weather tool.
You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
indicate you should use the get_image tool are:
- What do you see?
- What's in the video?
- Can you describe the video?
- Tell me about what you see.
- Tell me something interesting about what you see.
- What's happening in the video?
"""
messages = [
{"role": "system", "content": system_prompt},
]
context = LLMContext(messages, tools)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
@@ -214,9 +218,9 @@ indicate you should use the get_image tool are:
client_id = get_transport_client_id(transport, client)
# Kick off the conversation.
messages.append(
context.add_message(
{
"role": "system",
"role": "user",
"content": f"Please introduce yourself to the user. Use '{client_id}' as the user ID during function calls.",
}
)

12
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
from pipecat.services.groq.llm import GroqLLMService
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.groq.llm import GroqLLMService, GroqLLMSettings
from pipecat.services.groq.stt import GroqSTTService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -64,12 +64,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GroqLLMService(
api_key=os.getenv("GROQ_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=GroqLLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.

12
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
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.grok.llm import GrokLLMService
from pipecat.services.grok.llm import GrokLLMService, GrokLLMSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
@@ -64,12 +64,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
settings=CartesiaTTSSettings(
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
),
)
llm = GrokLLMService(
api_key=os.getenv("GROK_API_KEY"),
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
settings=GrokLLMSettings(
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),
)
# You can also register a function_name of None to get all functions
# sent to the same callback with an additional function_name parameter.

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