video_caption.py
"""
Video Caption
=============================
Please install dependencies using:.
"""
from agno.agent import Agent
from agno.models.openai import OpenAIResponses
from agno.tools.moviepy_video import MoviePyVideoTools
from agno.tools.openai import OpenAITools
video_tools = MoviePyVideoTools(
enable_process_video=True, enable_generate_captions=True, enable_embed_captions=True
)
openai_tools = OpenAITools()
# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
video_caption_agent = Agent(
name="Video Caption Generator Agent",
model=OpenAIResponses(
id="gpt-4o",
),
tools=[video_tools, openai_tools],
description="You are an AI agent that can generate and embed captions for videos.",
instructions=[
"When a user provides a video, process it to generate captions.",
"Use the video processing tools in this sequence:",
"1. Extract audio from the video using extract_audio",
"2. Transcribe the audio using transcribe_audio",
"3. Generate SRT captions using create_srt",
"4. Embed captions into the video using embed_captions",
],
markdown=True,
)
# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
video_caption_agent.print_response(
"Generate captions for {video with location} and embed them in the video"
)
Run the Example
1
Set up your virtual environment
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 moviepy openai
3
Export your OpenAI API key
export OPENAI_API_KEY="your_openai_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
4
Run the example
Save the code above as
video_caption.py, then run:python video_caption.py