FalTools enable an Agent to perform media generation tasks.

​
Prerequisites

The following example requires the fal_client library and an API key which can be obtained from Fal. 
pip install -U fal_client

export FAL_KEY=***

​
Example

The following agent will use FAL to generate any video requested by the user.
cookbook/tools/fal_tools.py
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.fal import FalTools

fal_agent = Agent(
    name="Fal Video Generator Agent",
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[FalTools("fal-ai/hunyuan-video")],
    description="You are an AI agent that can generate videos using the Fal 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,
    debug_mode=True,
    )

fal_agent.print_response("Generate video of balloon in the ocean")

​
Toolkit Params

ParameterTypeDefaultDescription
api_keystrNoneAPI key for authentication purposes.
modelstrNoneThe model to use for the media generation.
enable_generate_mediaboolTrueEnable the generate_media functionality.
enable_image_to_imageboolTrueEnable the image_to_image functionality.
allboolFalseEnable all functionality.

​
Toolkit Functions

FunctionDescription
generate_mediaGenerate either images or videos depending on the user prompt.
image_to_imageTransform an input image based on a text prompt.

​
Developer Resources