zen-video

Video Understanding

A video understanding model that analyzes video content frame by frame. Answers questions about video content, generates descriptions, detects actions, and reasons about temporal sequences.

This model is coming soon. Join the waitlist at hanzo.chat.

Specifications

Capabilities

• Video question answering
• Scene description and captioning
• Action detection and classification
• Temporal reasoning across frames
• Key moment extraction
• Content moderation for video

Usage

from hanzoai import Hanzo

client = Hanzo(api_key="hk-your-api-key")

# Coming soon
response = client.chat.completions.create(
    model="zen-video",
    messages=[{
        "role": "user",
        "content": [
            {"type": "video_url", "video_url": {"url": "https://example.com/video.mp4"}},
            {"type": "text", "text": "Summarize what happens in this video."},
        ],
    }],
)

See Also

• zen-director -- Text-to-video generation
• zen-video-i2v -- Image-to-video animation
• zen-omni -- Hypermodal understanding