realtime_video_restyler.py

import logging

from dotenv import load_dotenv

from vision_agents.core import User, Agent, cli
from vision_agents.core.agents import AgentLauncher
from vision_agents.plugins import decart, getstream, gemini, elevenlabs, deepgram

logger = logging.getLogger(__name__)

load_dotenv()


async def create_agent(**kwargs) -> Agent:
    processor = decart.RestylingProcessor(
        initial_prompt="Change my video to studio Ghibli", model="mirage_v2"
    )
    llm = gemini.LLM(model="gemini-3-pro-preview")

    agent = Agent(
        edge=getstream.Edge(),
        agent_user=User(name="Story teller", id="agent"),
        instructions="You are a live video effects generator and restyling AI agent: [EXCITED], [NERVOUS], [FRUSTRATED], [TIRED] Reactions: [GASP], [SIGH], [LAUGHS], [GULPS] Volume & energy: [WHISPERING], [SHOUTING], [QUIETLY], [LOUDLY] Pacing & rhythm: [PAUSES], [STAMMERS], [RUSHED]",
        llm=llm,
        tts=elevenlabs.TTS(voice_id="N2lVS1w4EtoT3dr4eOWO"),
        stt=deepgram.STT(),
        processors=[processor],
    )

    @llm.register_function(
        description="This function changes the prompt of the Decart processor which in turn changes the style of the video and user's background"
    )
    async def change_prompt(prompt: str) -> str:
        await processor.update_prompt(prompt)
        return f"Prompt changed to {prompt}"

    return agent


async def join_call(agent: Agent, call_type: str, call_id: str, **kwargs) -> None:
    """Join the call and start the agent."""
    # Ensure the agent user is created
    await agent.create_user()
    # Create a call
    call = await agent.create_call(call_type, call_id)

    logger.info("🤖 Starting Agent...")

    # Have the agent join the call/room
    with await agent.join(call):
        logger.info("Joining call")
        logger.info("LLM ready")

        await agent.finish()  # Run till the call ends


if __name__ == "__main__":
    cli(AgentLauncher(create_agent=create_agent, join_call=join_call))