Gemini Omni API
Voice, character, and multimodal video generation resources for narration, dialogue, and agent media workflows.
curl -X POST https://runapi.ai/api/v1/gemini_omni/create_audio \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"audio_id": "achernar",
"name": "Acher Narrator",
"voice_description": "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks.",
"example_dialogue": "Hello, I am achernar"
}'import { GeminiOmniClient } from "@runapi.ai/gemini-omni";
const client = new GeminiOmniClient();
const result = await client.createAudio.run({
audio_id: "achernar",
name: "Acher Narrator",
voice_description: "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks.",
example_dialogue: "Hello, I am achernar",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\GeminiOmni\GeminiOmniClient;
$client = new GeminiOmniClient();
$result = $client->createAudio->run([
'audio_id' => 'achernar',
'name' => 'Acher Narrator',
'voice_description' => 'Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks.',
'example_dialogue' => 'Hello, I am achernar',
]);require "runapi/gemini_omni"
client = RunApi::GeminiOmni::Client.new
result = client.create_audio.run(
audio_id: "achernar",
name: "Acher Narrator",
voice_description: "Create a 1080p neon city tracking shot with a reusable character walking through rain while a calm narrator speaks.",
example_dialogue: "Hello, I am achernar"
)npx skills add runapi-ai/gemini-omni -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorGemini Omni creates reusable voice resources, reusable character resources, and multimodal videos that can combine prompts, reference images, audio IDs, character IDs, and a source video clip.
- 多種變體可對應不同速度／品質等級
- Model skill 包含文件、schema 與 setup 備註
- 支援 app-focused coding workflows
- 生成失敗不收費
比較所有 API 變體
為 app 開發安裝 Gemini Omni skill
將模型文件、schema、價格備註與 setup 步驟載入 coding workspace。
# Install the model skill for app development workflows
npx skills add runapi-ai/gemini-omni -gInstall the Gemini Omni skill for this app: 1. Add runapi-ai/gemini-omni with the skills installer. 2. Load SKILL.md in this workspace. 3. Use its docs, schemas, pricing notes, and setup steps when adding model features. 4. Confirm the install path when done.
從 model skill 到第一次結果，只要四步
選擇模型
挑選符合輸出類型、品質門檻與延遲目標的模型與變體。
設定
設定 RunAPI key，並在 coding workspace 安裝 model skill。
開發
使用 skill 指引，在你的 app 內加入模型功能。
接收
透過 task ID 查詢、在支援時串流，或處理 webhook callback。
什麼是 Gemini Omni API？
Gemini Omni belongs to the Google catalog on RunAPI and shares the same SDK package, CLI namespace, and billing surfaces across audio, character, and video variants.
為什麼透過 RunAPI 使用 Gemini Omni API
一組驗證，全部供應商通用
一把 RunAPI 金鑰就能開通整個目錄。無需分開註冊帳戶，也不用為每個整合各自輪替金鑰。
統一價格與計費
以美元按次計費，每月結帳。失敗的生成不收費。
內含 schema 的 skill
型別化 schema 與 setup 備註打包在 model skill 內，讓實作從正確契約開始。
常見問題
What can Gemini Omni create?
It can create reusable audio resources, reusable character resources, and multimodal videos that combine prompts with image, audio, character, or source-video references.
When should I create a character resource?
Create a character resource when multiple videos need the same visual identity; pass the returned character ID into video requests that should reuse that subject.
How do audio resources work?
Audio resources capture a preset voice choice and can be referenced by video requests that need narration or dialogue with consistent voice selection.
What affects Gemini Omni video pricing?
Video price depends on the request mode, duration, resolution, and whether source media changes the effective billed clip length.
Can one video request mix several reference types?
Yes. Gemini Omni video can combine prompt text with reference images, audio IDs, character IDs, and a source video, within the documented reference limits.
我應該先從哪個版本開始？
先選擇符合你品質標準中最便宜的版本。大多數團隊會先用快速版本，之後再升級到專業版用於正式上線。
有免費方案嗎？
新帳戶可在每個模型上免費使用首次呼叫。之後則按次計費。
你們支援串流結果嗎？
只要該功能可用，RunAPI 會提供端到端串流。
失敗的請求如何計費？
生成失敗不會收費。
輸出結果有快取嗎？
生成結果會儲存，並可透過任務 ID 取回。輸入內容不會快取。
可以商業使用嗎？
可以——除非模型授權明確限制，否則每個版本都包含商業使用權；若有例外，會在版本頁面標示。
速率限制怎麼算？
每個金鑰的速率限制會依使用等級而提升。最新限制請參考定價頁面。
如果遇到問題，要去哪裡回報？
請在公開的 GitHub repo 開 issue，或寄信給支援。