Integration into Livekit Agent

I am using livekit voice agent pipeline. How can I replace the tts with HeyGen to give my agent a "face"?

BTW its really beneficial to have a heygen plugin like other model service

from livekit.agents import llm  
from livekit.agents.pipeline import VoicePipelineAgent  
from livekit.plugins import cartesia, deepgram, openai, silero

agent = VoicePipelineAgent(  
    vad=silero.VAD.load(),
  	stt=deepgram_stt,
  	llm=openai.LLM(),
  	tts=cartesia.TTS()
)