Veo 3.1 API
High-fidelity video generation up to 4K with natively synthesized dialogue, sound effects, and ambience.
curl -X POST https://runapi.ai/api/v1/veo_3_1/text_to_video \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "veo-3.1-lite",
"prompt": "Generate an 8-second cinematic drone shot of a coastal highway at golden hour, with waves crashing below and ambient wind audio."
}'import { Veo31Client } from "@runapi.ai/veo-3-1";
const client = new Veo31Client();
const result = await client.textToVideo.run({
model: "veo-3.1-lite",
prompt: "Generate an 8-second cinematic drone shot of a coastal highway at golden hour, with waves crashing below and ambient wind audio.",
});<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Veo31\Veo31Client;
$client = new Veo31Client();
$result = $client->textToVideo->run([
'model' => 'veo-3.1-lite',
'prompt' => 'Generate an 8-second cinematic drone shot of a coastal highway at golden hour, with waves crashing below and ambient wind audio.',
]);require "runapi/veo_3_1"
client = RunApi::Veo31::Client.new
result = client.text_to_video.run(
model: "veo-3.1-lite",
prompt: "Generate an 8-second cinematic drone shot of a coastal highway at golden hour, with waves crashing below and ambient wind audio."
)npx skills add runapi-ai/veo-3.1 -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 cursorVeo 3.1 is Google DeepMind's video generation model that produces high-fidelity video clips with native audio synthesis, including ambient sound, dialogue, and music generated in sync with the visuals.
- 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
Utility endpoints
Shared endpoints for this model line, such as extension, enhancement, or conversion actions.
為 app 開發安裝 Veo 3.1 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/veo-3.1 -gInstall the Veo 3.1 skill for this app: 1. Add runapi-ai/veo-3.1 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 Veo 3.1 API？
Veo 3 is a frontier video generation model by Google DeepMind, notable for its native audio-video joint synthesis. Through RunAPI, it benefits from unified API access and shared billing across all Google models.
為什麼透過 RunAPI 使用 Veo 3.1 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
Does Veo 3.1 generate audio with the video?
Yes — Veo 3.1 natively synthesizes synchronized audio including dialogue, sound effects, and ambience in the same generation call.
What resolution does Veo 3.1 output?
Native 1080p generation with upscaling support to 4K (3840×2160). Aspect ratios include 16:9 and 9:16.
How long can generated clips be?
4, 6, or 8 seconds per generation. Scene Extension works once from a text-to-video result and cannot be chained.
Are generated videos watermarked?
All Veo outputs include an invisible SynthID watermark embedded in the pixel data, which persists through compression and resizing.
How is the audio generated?
Veo 3.1 generates native audio synchronized with the on-screen action, matching sound to the motion and events in the scene.
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。