Video Generation Agent

A WhatsApp agent that generates short videos from text descriptions using Fal AI’s text-to-video models.

A WhatsApp agent that generates short videos from text descriptions using Fal AI’s text-to-video models. Demonstrates outbound video support through the WhatsApp Cloud API.

video_generation.py

"""
Video Generation Agent
=======================

A WhatsApp agent that generates short videos from text descriptions
using Fal AI's text-to-video models. Demonstrates outbound video
support through the WhatsApp Cloud API.

Requires:
  WHATSAPP_ACCESS_TOKEN, WHATSAPP_PHONE_NUMBER_ID
  FAL_KEY
  pip install fal-client
"""

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIChat
from agno.os.app import AgentOS
from agno.os.interfaces.whatsapp import Whatsapp
from agno.tools.fal import FalTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent_db = SqliteDb(db_file="tmp/video_agent.db")

video_agent = Agent(
    name="Video Generator",
    model=OpenAIChat(id="gpt-5-mini"),
    tools=[FalTools(model="fal-ai/hunyuan-video")],
    instructions=[
        "You are a video generation assistant on WhatsApp.",
        "When the user describes a scene, use the generate_media tool to create a short video.",
        "After generating, briefly describe what was created.",
        "Keep messages short and conversational.",
    ],
    db=agent_db,
    add_history_to_context=True,
    num_history_runs=3,
    send_media_to_model=False,
)

# ---------------------------------------------------------------------------
# AgentOS setup
# ---------------------------------------------------------------------------

agent_os = AgentOS(
    agents=[video_agent],
    interfaces=[Whatsapp(agent=video_agent)],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    agent_os.serve(app="video_generation:app", reload=True)

Run the Example

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[os]" fal-client openai
   
3. Export environment variables

   Mac/Linux

   export FAL_API_KEY="your_fal_api_key_here"
   export FAL_KEY="your_fal_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   export WHATSAPP_ACCESS_TOKEN="your_whatsapp_access_token_here"
   export WHATSAPP_APP_SECRET="your_whatsapp_app_secret_here"
   export WHATSAPP_PHONE_NUMBER_ID="your_whatsapp_phone_number_id_here"
   export WHATSAPP_VERIFY_TOKEN="your_whatsapp_verify_token_here"
   

   $Env:FAL_API_KEY="your_fal_api_key_here"
   $Env:FAL_KEY="your_fal_key_here"
   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   $Env:WHATSAPP_ACCESS_TOKEN="your_whatsapp_access_token_here"
   $Env:WHATSAPP_APP_SECRET="your_whatsapp_app_secret_here"
   $Env:WHATSAPP_PHONE_NUMBER_ID="your_whatsapp_phone_number_id_here"
   $Env:WHATSAPP_VERIFY_TOKEN="your_whatsapp_verify_token_here"
   
4. Run the example

   Save the code above as video_generation.py, then run:

   python video_generation.py
   

Full source: cookbook/05_agent_os/interfaces/whatsapp/video_generation.py