Generate Video (ReplicateTools)

This example demonstrates how to create an AI agent that generates videos using the Replicate API with the HunyuanVideo model.

Code

generate_video_using_replicate.py

from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.replicate import ReplicateTools

"""Create an agent specialized for Replicate AI content generation"""

video_agent = Agent(
    name="Video Generator Agent",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[
        ReplicateTools(
            model="tencent/hunyuan-video:847dfa8b01e739637fc76f480ede0c1d76408e1d694b830b5dfb8e547bf98405"
        )
    ],
    description="You are an AI agent that can generate videos using the Replicate API.",
    instructions=[
        "When the user asks you to create a video, use the `generate_media` tool to create the video.",
        "Return the URL as raw to the user.",
        "Don't convert video URL to markdown or anything else.",
    ],
    markdown=True,
)

video_agent.print_response("Generate a video of a horse in the dessert.")

Usage

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno
   
3. Export your OpenAI API key

   Mac/Linux

     export OPENAI_API_KEY="your_openai_api_key_here"
   

     $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run Agent

   python cookbook/03_agents/multimodal/generate_video_using_replicate.py