503e5e9106
When Gemini Live was configured with local VAD (server-side VAD disabled), the service was listening for the wrong frame types and not sending ActivityStart/ActivityEnd events to the server. Now it listens for VADUserStartedSpeakingFrame/VADUserStoppedSpeakingFrame and sends the appropriate activity signals when local VAD is in use. Also removes the unnecessary local SileroVADAnalyzer from server-side VAD examples and adds a new 26a example demonstrating local VAD configuration.
131 lines
4.0 KiB
Python
131 lines
4.0 KiB
Python
#
|
|
# Copyright (c) 2024-2026, Daily
|
|
#
|
|
# SPDX-License-Identifier: BSD 2-Clause License
|
|
#
|
|
|
|
|
|
import os
|
|
|
|
from dotenv import load_dotenv
|
|
from loguru import logger
|
|
|
|
from pipecat.frames.frames import LLMRunFrame
|
|
from pipecat.pipeline.pipeline import Pipeline
|
|
from pipecat.pipeline.runner import PipelineRunner
|
|
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
|
from pipecat.processors.aggregators.llm_context import LLMContext
|
|
from pipecat.processors.aggregators.llm_response_universal import (
|
|
AssistantTurnStoppedMessage,
|
|
LLMContextAggregatorPair,
|
|
UserTurnStoppedMessage,
|
|
)
|
|
from pipecat.runner.types import RunnerArguments
|
|
from pipecat.runner.utils import create_transport
|
|
from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService
|
|
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
|
from pipecat.transports.daily.transport import DailyParams
|
|
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
|
|
|
load_dotenv(override=True)
|
|
|
|
|
|
# We use lambdas to defer transport parameter creation until the transport
|
|
# type is selected at runtime.
|
|
transport_params = {
|
|
"daily": lambda: DailyParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"twilio": lambda: FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
"webrtc": lambda: TransportParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
),
|
|
}
|
|
|
|
|
|
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
|
logger.info(f"Starting bot")
|
|
|
|
llm = GeminiLiveLLMService(
|
|
api_key=os.getenv("GOOGLE_API_KEY"),
|
|
settings=GeminiLiveLLMService.Settings(
|
|
voice="Aoede", # Puck, Charon, Kore, Fenrir, Aoede
|
|
# system_instruction="Talk like a pirate."
|
|
),
|
|
# inference_on_context_initialization=False,
|
|
)
|
|
|
|
context = LLMContext(
|
|
[
|
|
{
|
|
"role": "user",
|
|
"content": "Say hello. Then ask if I want to hear a joke.",
|
|
},
|
|
],
|
|
)
|
|
# Server-side VAD is enabled by default; no local VAD is added.
|
|
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
|
|
|
|
pipeline = Pipeline(
|
|
[
|
|
transport.input(),
|
|
user_aggregator,
|
|
llm,
|
|
transport.output(),
|
|
assistant_aggregator,
|
|
]
|
|
)
|
|
|
|
task = PipelineTask(
|
|
pipeline,
|
|
params=PipelineParams(
|
|
enable_metrics=True,
|
|
enable_usage_metrics=True,
|
|
),
|
|
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
|
)
|
|
|
|
@transport.event_handler("on_client_connected")
|
|
async def on_client_connected(transport, client):
|
|
logger.info(f"Client connected")
|
|
# Kick off the conversation.
|
|
await task.queue_frames([LLMRunFrame()])
|
|
|
|
@transport.event_handler("on_client_disconnected")
|
|
async def on_client_disconnected(transport, client):
|
|
logger.info(f"Client disconnected")
|
|
await task.cancel()
|
|
|
|
@user_aggregator.event_handler("on_user_turn_stopped")
|
|
async def on_user_turn_stopped(aggregator, strategy, message: UserTurnStoppedMessage):
|
|
timestamp = f"[{message.timestamp}] " if message.timestamp else ""
|
|
line = f"{timestamp}user: {message.content}"
|
|
logger.info(f"Transcript: {line}")
|
|
|
|
@assistant_aggregator.event_handler("on_assistant_turn_stopped")
|
|
async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMessage):
|
|
timestamp = f"[{message.timestamp}] " if message.timestamp else ""
|
|
line = f"{timestamp}assistant: {message.content}"
|
|
logger.info(f"Transcript: {line}")
|
|
|
|
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
|
|
|
await runner.run(task)
|
|
|
|
|
|
async def bot(runner_args: RunnerArguments):
|
|
"""Main bot entry point compatible with Pipecat Cloud."""
|
|
transport = await create_transport(runner_args, transport_params)
|
|
await run_bot(transport, runner_args)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
from pipecat.runner.run import main
|
|
|
|
main()
|