バリアント · Google / Gemini Omni

Gemini Omni gemini-omni-text-to-video API

A model variant exposed through RunAPI's unified AI API.

Operational · video · Commercial use supported

# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/gemini-omni -g

The -g flag installs globally so every project picks it up.

Or paste this prompt to your AI agent:

Install the Gemini Omni skill for me:

1. Clone https://github.com/runapi-ai/gemini-omni
2. Copy the skills/gemini-omni/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.

Switch variant

gemini-omni-audio gemini-omni-character

概要

Gemini Omni gemini-omni-text-to-video is available through the same RunAPI auth, SDKs, and agent skill workflow.

Unified endpoint
SDK snippets
Agent install path
失敗した生成は課金されません

料金

失敗した生成は課金されません

Text to video

$0.90-$3.60 / video

Input mode: video · Duration seconds: any · Output resolution: 4k $3.60

Input mode: video · Duration seconds: any · Output resolution: 720p $2.40

Input mode: video · Duration seconds: any · Output resolution: 1080p $2.40

Input mode: generated · Duration seconds: 4 · Output resolution: 4k $2.10

Input mode: generated · Duration seconds: 4 · Output resolution: 720p $0.90

Input mode: generated · Duration seconds: 4 · Output resolution: 1080p $0.90

Input mode: generated · Duration seconds: 6 · Output resolution: 4k $2.40

Input mode: generated · Duration seconds: 6 · Output resolution: 720p $1.20

Input mode: generated · Duration seconds: 6 · Output resolution: 1080p $1.20

Input mode: generated · Duration seconds: 8 · Output resolution: 4k $2.70

Input mode: generated · Duration seconds: 8 · Output resolution: 720p $1.50

Input mode: generated · Duration seconds: 8 · Output resolution: 1080p $1.50

Input mode: generated · Duration seconds: 10 · Output resolution: 4k $3.00

Input mode: generated · Duration seconds: 10 · Output resolution: 720p $1.80

Input mode: generated · Duration seconds: 10 · Output resolution: 1080p $1.80

仕様

Model ID	gemini-omni-text-to-video
プロバイダー	Google
モダリティ	video
Task type	asynchronous
課金	call
Endpoint	/api/v1/gemini_omni/text_to_video
Commercial	Yes
Status	Operational

クイックスタート

Quickstart — gemini-omni-text-to-video

runapi.ai

curl -X POST https://runapi.ai/api/v1/gemini_omni/text_to_video \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-omni-text-to-video",
  "prompt": "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks."
}'

import { GeminiOmniClient } from "@runapi.ai/gemini-omni";

const client = new GeminiOmniClient();
const result = await client.textToVideo.run({
    model: "gemini-omni-text-to-video",
    prompt: "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks.",
});

require "runapi/gemini_omni"

client = RunApi::GeminiOmni::Client.new
result = client.text_to_video.run(
    model: "gemini-omni-text-to-video",
    prompt: "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks."
)

@runapi.ai/gemini-omni v1

仕組み