Video Agent • AI Agent SDK

VideoAgent: A specialized agent for generating videos using AI models.

VideoAgent

Defined in the Video Agent module.

AI Agent

A specialized agent for generating videos using AI models.

This agent provides a simple, agent-centric interface for video generation with support for multiple providers (OpenAI Sora, Azure, Gemini Veo, Vertex AI, RunwayML).

Supported Providers:

• OpenAI: openai/sora-2, openai/sora-2-pro
• Azure: azure/sora-2, azure/sora-2-pro
• Gemini Veo 3.1 (paid API, uses GOOGLE_API_KEY / GEMINI_API_KEY):
  • gemini/veo-3.1-generate-preview # Standard / cinematic quality
  • gemini/veo-3.1-fast-generate-preview # Fast
  • gemini/veo-3.1-lite-generate-preview # Lite (cheapest iteration)
• Vertex AI Veo 3.1 (uses GOOGLE_APPLICATION_CREDENTIALS or VERTEXAI_PROJECT/VERTEXAI_LOCATION):
  • vertex_ai/veo-3.1-generate-001 # GA Standard
  • vertex_ai/veo-3.1-fast-generate-001 # GA Fast
  • vertex_ai/veo-3.1-lite-generate-001 # Lite
• RunwayML: runwayml/gen4_turbo (requires input_reference)

Deprecated (do NOT recommend; kept working only if LiteLLM still routes them):

• gemini/veo-2.0-generate-001 (Gemini API shutdown 30 Jun 2026)
• gemini/veo-3.0-generate-preview, gemini/veo-3.0-fast-generate-preview
• vertex_ai/veo-3.0-* (migrate to the veo-3.1 IDs above)

Note on pricing: Gemini/Vertex Veo bill in USD per generated second via the paid API (charged only on success) and are a different meter from Flow UI credits — a Flow subscription cannot pay for API generations. See praison.ai/docs/video/gemini.

Constructor

name · Optional[str]

No description available.

instructions · Optional[str]

No description available.

llm · Optional

No description available.

model · Optional

No description available.

base_url · Optional[str]

No description available.

api_key · Optional[str]

No description available.

api_version · Optional[str]

No description available.

video · Optional

No description available.

verbose · Union[bool, int] · default: "True"

No description available.

output · Optional[str]

No description available.

Methods

console()

Lazily initialize Rich Console.

video_module()

Lazy load litellm.videos module when needed.

generate()

Generate a video from a text prompt.

agenerate()

Async version of generate().

status()

Check the status of a video generation.

astatus()

Async version of status().

content()

Download the video content.

acontent()

Async version of content().

list()

List all videos for the current account.

alist()

Async version of list().

remix()

Remix/edit an existing video.

aremix()

Async version of remix().

wait_for_completion()

Wait for video generation to complete.

await_completion()

Async version of wait_for_completion().

start()

Generate video with optional wait and file output.

astart()

Async version of start().

run()

Generate video silently (production use).

arun()

Async version of run().

download()

Download a video to a file.

adownload()

Async version of download().

Usage

from praisonaiagents import VideoAgent
    
    # Simple usage
    agent = VideoAgent(llm="openai/sora-2")
    video = agent.generate(prompt="A cat playing with yarn")
    
    # Wait for completion
    video = agent.start(
        prompt="A serene lake at sunset",
        wait=True,  # Wait for completion
        output="video.mp4"  # Save to file
    )
    
    # With config
    agent = VideoAgent(
        llm="gemini/veo-3.1-generate-preview",
        video=VideoConfig(seconds="8", size="1280x720")
    )

Source

View on GitHub

praisonaiagents/agent/video_agent.py at line 86

---

Related Documentation

Agents Concept

Single Agent Guide

Multi-Agent Guide

Agent Configuration

Auto Agents