generate • AI Agent SDK

generate: Generate a video from a text prompt.

generate

Method

This is a method of the VideoAgent class in the video_agent module.

Generate a video from a text prompt.

Signature

def generate(prompt: str, seconds: Optional[str], size: Optional[str], input_reference: Optional[Any]) -> Any

Parameters

prompt · str · required

Text description of the desired video

seconds · Optional[str]

Video duration (e.g., “8”, “16”). Defaults to config value.

size · Optional[str]

Video dimensions (e.g., “720x1280”). Defaults to config value.

input_reference · Optional

Reference image for image-to-video (first-frame) generation **kwargs: Additional provider-specific parameters, forwarded to LiteLLM. For Veo 3.1 interpolation/reference features, pass them here (no dedicated params are added to keep the surface lightweight): - last_frame=<image> # first + last frame (Veo 3.1 only) - reference_images=[…] # up to 3 reference images

Returns

Returns · Any

VideoObject with id, status, and metadata

Usage

video = agent.generate(
        prompt="A cat playing with yarn",
        seconds="8",
        size="1280x720"
    )
    print(f"Video ID: {video.id}")
    print(f"Status: {video.status}")

    # Veo 3.1 first + last frame interpolation (via kwargs passthrough)
    veo = VideoAgent(llm="gemini/veo-3.1-generate-preview")
    veo.generate(
        prompt="Sunrise timelapse",
        input_reference=start_image,  # first frame
        last_frame=end_image,         # last frame (Veo 3.1)
    )

Uses

• to_dict
• Progress
• SpinnerColumn
• TextColumn
• progress.add_task

Used By

• CodeAgent.generate_code
• VideoAgent.start
• VideoAgent.run

Source

View on GitHub

praisonaiagents/agent/video_agent.py at line 303