Gemini Omni Python SDK

Official Python SDK for Gemini Omni — the next-generation unified multimodal AI video generation and conversational video editing platform.

🎬 Online Studio & Generator: Experience the full web interface at https://gemini-omni.dev.

✨ Features

• Text-to-Video & Image-to-Video: Native support for multimodal video prompts.
• Cinematic Quality: 720p, 1080p, and 4K output formats with selectable aspect ratios (16:9, 9:16, 1:1).
• Character Consistency: Preserve subject identity and style using reference images.
• Zero Dependencies: Lightweight SDK using pure Python standard libraries.
• Full Type Hinting: Comprehensive typing support for IDE autocomplete.

📦 Installation

pip install gemini-omni

🚀 Quick Start

1. Generate Video from Text Prompt

from gemini_omni import GeminiOmniClient

client = GeminiOmniClient()

# Submit a cinematic video generation task
task = client.generate_video(
    prompt="Cinematic tracking shot of a futuristic neon cyber-city at dusk, high-definition reflections in rainwater, 4K resolution",
    aspect_ratio="16:9",
    resolution="1080p",
)

print(f"Task successfully submitted! Task ID: {task.get('taskId')}")

2. Check Generation Status

task_status = client.get_task(task_id="YOUR_TASK_ID")
print("Status:", task_status.get("status"))
if task_status.get("videoUrl"):
    print("Video Output URL:", task_status.get("videoUrl"))

🔗 Official Links & Resources

• Official Web Platform: https://gemini-omni.dev
• Prompt Library: https://gemini-omni.dev/prompts
• Model Specs & Benchmark: https://gemini-omni.dev/gemini-omni-1-1-flash
• Source Code & Issues: https://github.com/lidong-tools/website-gemini-omni-dev

📄 License

MIT © Gemini Omni