Gemini Omni API and MCP: how to add video generation to your project

Gemini Omni is a family of video generation models. NeuralSpace offers the following models: Gemini Omni 1.1 Flash, Gemini Omni 1. They all run through a single public API, and there is a ready MCP server for AI agents. The key is issued on the API keys page. Below are the model capabilities, request examples and setup steps.

What Gemini Omni can do

Gemini Omni generates video from text and supports several references to keep a character appearance. Version 1.1 Flash accepts 360p, 720p, 1080p and 4K resolutions, while Omni 1 supports 720p, 1080p and 4K. Duration is chosen from 4, 6, 8 or 10 seconds.

API endpoint

Send a request to POST /v1/videos/generations. Example: {"model": "gemini-omni-1", "prompt": "a person walking along the embankment", "duration": 4, "resolution": "1080p"}. Authorization uses an API key in the x-api-key header. Available model ids: gemini-omni-flash-1-1, gemini-omni-1.

MCP tools

The NeuralSpace MCP server is available at POST /mcp (Streamable HTTP). To work with Gemini Omni, an agent uses the tools: generate_video, check_video, list_models, get_balance. This lets Claude Code, Cursor and other MCP clients use the site models directly.

How to connect

Sign up on NeuralSpace, open the API keys page and create an nsk-… key. Then pass it in the request header or in your MCP client settings. Full documentation is on the the /v1/docs page.

FAQ

How many references can I pass?

Several images to keep a character appearance.

Which resolutions are available?

1.1 Flash supports 360p, 720p, 1080p and 4K; Omni 1 supports 720p, 1080p and 4K.

What format is the request?

POST /v1/videos/generations with model and prompt fields.