Files
pipecat/examples/foundational/26a-gemini-live-transcription.py
2025-12-14 12:37:05 -08:00

154 lines
5.4 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import os
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import LLMRunFrame, TranscriptionMessage
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 LLMContextAggregatorPair
from pipecat.processors.transcript_processor import TranscriptProcessor
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 store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
# set stop_secs to something roughly similar to the internal setting
# of the Multimodal Live api, just to align events. This doesn't really
# matter because we can only use the Multimodal Live API's phrase
# endpointing, for now.
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
llm = GeminiLiveLLMService(
api_key=os.getenv("GOOGLE_API_KEY"),
voice_id="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.",
},
# {"role": "assistant", "content": "Hello! Why don't scientists trust atoms?"},
# {
# "role": "user",
# "content": [
# {
# "type": "text",
# "text": "Oh, I know this one: because they make up everything.",
# }
# ],
# },
],
)
context_aggregator = LLMContextAggregatorPair(context)
transcript = TranscriptProcessor()
pipeline = Pipeline(
[
transport.input(),
context_aggregator.user(),
transcript.user(),
llm,
transport.output(),
transcript.assistant(),
context_aggregator.assistant(),
]
)
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()
# Register event handler for transcript updates
@transcript.event_handler("on_transcript_update")
async def on_transcript_update(processor, frame):
for msg in frame.messages:
if isinstance(msg, TranscriptionMessage):
timestamp = f"[{msg.timestamp}] " if msg.timestamp else ""
line = f"{timestamp}{msg.role}: {msg.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()