HeyGen implementation for Pipecat - HeyGenVideoService

This commit is contained in:
Filipi Fuchter
2025-07-30 09:07:15 -03:00
parent c145a9ef13
commit 6e921cdf45
10 changed files with 1383 additions and 0 deletions

View File

@@ -0,0 +1,123 @@
#
# Copyright (c) 20242025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
import argparse
import os
import aiohttp
from dotenv import load_dotenv
from loguru import logger
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.heygen.video import HeyGenVideoService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.services.daily import DailyParams
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,
video_out_enabled=True,
video_out_is_live=True,
video_out_width=1280,
video_out_height=720,
vad_analyzer=SileroVADAnalyzer(),
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
video_out_enabled=True,
video_out_is_live=True,
video_out_width=1280,
video_out_height=720,
vad_analyzer=SileroVADAnalyzer(),
),
}
async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
logger.info(f"Starting bot")
async with aiohttp.ClientSession() as session:
stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
tts = CartesiaTTSService(
api_key=os.getenv("CARTESIA_API_KEY"),
voice_id="00967b2f-88a6-4a31-8153-110a92134b9f",
)
llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
heyGen = HeyGenVideoService(api_key=os.getenv("HEYGEN_API_KEY"), session=session)
messages = [
{
"role": "system",
"content": "You are a helpful assistant. Your output will be converted to audio so don't include special characters in your answers. Be succinct and respond to what the user said in a creative and helpful way.",
},
]
context = OpenAILLMContext(messages)
context_aggregator = llm.create_context_aggregator(context)
pipeline = Pipeline(
[
transport.input(), # Transport user input
stt, # STT
context_aggregator.user(), # User responses
llm, # LLM
tts, # TTS
heyGen, # Avatar
transport.output(), # Transport bot output
context_aggregator.assistant(), # Assistant spoken responses
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
# Kick off the conversation.
messages.append(
{
"role": "system",
"content": "Start by saying 'Hello' and then a short greeting.",
}
)
await task.queue_frames([context_aggregator.user().get_context_frame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=handle_sigint)
await runner.run(task)
if __name__ == "__main__":
from pipecat.examples.run import main
main(run_example, transport_params=transport_params)