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

Merge pull request #3946 from pipecat-ai/mb/tts-settings-review

Browse Source 
Review TTS settings
This commit is contained in:
Mark Backman
2026-03-07 07:48:26 -05:00
committed by GitHub
parent dc97ffc909 1cfaea2007
commit fdf9fb6f02
50 changed files with 284 additions and 286 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/foundational/07i-interruptible-xtts.py
View File

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

4
examples/foundational/07m-interruptible-aws-strands.py
View File

@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
# Create Strands agent processor
try:
agent = build_agent(model_id="us.anthropic.claude-3-5-haiku-20241022-v1:0", max_tokens=8000)
agent = build_agent(model_id="us.anthropic.claude-sonnet-4-6", max_tokens=8000)
llm = StrandsAgentsProcessor(agent=agent)
logger.info("Successfully created Strands agent for NAB customer service coaching")
except Exception as e:
@@ -152,7 +152,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
messages=[
{
"role": "user",
"content": f"Greet the user and introduce yourself.",
"content": f"Greet the user and introduce yourself. Don't use emojis.",
}
],
run_llm=True,

2
examples/foundational/07m-interruptible-aws.py
View File

@@ -64,7 +64,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
model="us.anthropic.claude-sonnet-4-6",
temperature=0.8,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

2
examples/foundational/07n-interruptible-gemini-image.py
View File

@@ -72,7 +72,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GoogleSTTService(
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
settings=GoogleSTTSettings(
languages=Language.EN_US,
languages=[Language.EN_US],
),
)

2
examples/foundational/07n-interruptible-gemini.py
View File

@@ -55,7 +55,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GoogleSTTService(
settings=GoogleSTTSettings(
languages=Language.EN_US,
languages=[Language.EN_US],
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
)

5
examples/foundational/07n-interruptible-google-http.py
View File

@@ -55,8 +55,9 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
stt = GoogleSTTService(
settings=GoogleSTTSettings(
languages=Language.EN_US,
model="chirp_3",
languages=[Language.EN_US],
# Add model to use a specific model
# model="chirp_3",
),
credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
location="us",

2
examples/foundational/07t-interruptible-fish.py
View File

@@ -58,7 +58,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
tts = FishAudioTTSService(
api_key=os.getenv("FISH_API_KEY"),
settings=FishAudioTTSSettings(
model="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
voice="4ce7e917cedd4bc2bb2e6ff3a46acaa1", # Barack Obama
),
)

8
examples/foundational/07z-interruptible-sarvam-http.py
View File

@@ -24,7 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import (
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.services.sarvam.stt import SarvamSTTService, SarvamSTTSettings
from pipecat.services.sarvam.tts import SarvamHttpTTSService, SarvamHttpTTSSettings
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -59,14 +59,16 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
async with aiohttp.ClientSession() as session:
stt = SarvamSTTService(
api_key=os.getenv("SARVAM_API_KEY"),
model="saarika:v2.5",
settings=SarvamSTTSettings(
model="saarika:v2.5",
),
)
tts = SarvamHttpTTSService(
api_key=os.getenv("SARVAM_API_KEY"),
aiohttp_session=session,
settings=SarvamHttpTTSSettings(
language=Language.EN,
language=Language.EN_IN,
),
)

7
examples/foundational/12b-describe-image-aws.py
View File

@@ -61,11 +61,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AWSBedrockLLMService(
aws_region="us-west-2",
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),
model="us.anthropic.claude-sonnet-4-6",
temperature=0.8,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way. You are also able to describe images.",
),
)

2
examples/foundational/14r-function-calling-aws.py
View File

@@ -76,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
model="us.anthropic.claude-sonnet-4-6",
temperature=0.8,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

8
examples/foundational/15a-switch-languages.py
View File

@@ -7,7 +7,6 @@
import os
from deepgram import LiveOptions
from dotenv import load_dotenv
from loguru import logger
@@ -28,7 +27,7 @@ from pipecat.processors.filters.function_filter import FunctionFilter
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService, CartesiaTTSSettings
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.deepgram.stt import DeepgramSTTService, DeepgramSTTSettings
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.llm import OpenAILLMService, OpenAILLMSettings
from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -102,7 +101,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
stt = DeepgramSTTService(
api_key=os.getenv("DEEPGRAM_API_KEY"), live_options=LiveOptions(language="multi")
api_key=os.getenv("DEEPGRAM_API_KEY"),
settings=DeepgramSTTSettings(
language="multi",
),
)
tts = SwitchLanguage()

3
examples/foundational/55a-update-settings-deepgram-sagemaker-stt.py
View File

@@ -7,7 +7,6 @@
import asyncio
import os
from deepgram import LiveOptions
from dotenv import load_dotenv
from loguru import logger
@@ -114,7 +113,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
STTUpdateSettingsFrame(
delta=DeepgramSageMakerSTTSettings(
language=Language.ES,
live_options=LiveOptions(punctuate=False),
punctuate=False,
)
)
)

3
examples/foundational/55a-update-settings-deepgram-stt.py
View File

@@ -7,7 +7,6 @@
import asyncio
import os
from deepgram import LiveOptions
from dotenv import load_dotenv
from loguru import logger
@@ -108,7 +107,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
STTUpdateSettingsFrame(
delta=DeepgramSTTSettings(
language=Language.ES,
live_options=LiveOptions(punctuate=False),
punctuate=False,
)
)
)

2
examples/foundational/55zp-update-settings-aws-bedrock-llm.py
View File

@@ -62,7 +62,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
llm = AWSBedrockLLMService(
aws_region="us-west-2",
settings=AWSBedrockLLMSettings(
model="us.anthropic.claude-haiku-4-5-20251001-v1:0",
model="us.anthropic.claude-sonnet-4-6",
temperature=0.8,
system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
),

2
examples/foundational/55zr-update-settings-gradium-stt.py
View File

@@ -104,7 +104,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
await asyncio.sleep(10)
logger.info("Updating Gradium STT settings: delay_in_frames=5")
await task.queue_frame(STTUpdateSettingsFrame(delta=GradiumSTTSettings(delay_in_frames=5)))
await task.queue_frame(STTUpdateSettingsFrame(delta=GradiumSTTSettings(delay_in_frames=16)))
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):