Generate Video (ReplicateTools)

Create an 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

Set up your virtual environment

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

uv venv --python 3.12
.venv\Scripts\activate

Install dependencies

uv pip install -U agno openai replicate

Export your API keys

  export OPENAI_API_KEY="your_openai_api_key_here"
  export REPLICATE_API_KEY="your_replicate_api_key_here"
  export REPLICATE_API_TOKEN="your_replicate_api_key_here"

  $Env:OPENAI_API_KEY="your_openai_api_key_here"
  $Env:REPLICATE_API_KEY="your_replicate_api_key_here"
  $Env:REPLICATE_API_TOKEN="your_replicate_api_key_here"

Set both Replicate variables to the same value. The toolkit reads REPLICATE_API_KEY while the replicate client authenticates with REPLICATE_API_TOKEN.

Run Agent

python generate_video_using_replicate.py

Shorts from Video Generate Video (ModelsLabTools)

⌘I

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Generate Video (ReplicateTools)

Code

Usage

​Code

​Usage

Code

Usage