Google Vids API examples (useapi.net): Gemini Omni 1.1 Flash video with voiced AI avatars

Runnable examples for the Google Vids API by useapi.net: make Gemini Omni 1.1 Flash video in Google Vids with voiced avatars, your own reference images, extends up to about 41 seconds and a 1080p upscale, through a REST API that runs on your own Google AI plan. Vids has its own monthly allowance, separate from Google Flow's credits, and asks for no captcha.

| Example | What it does | Tutorial | Tutorial date | |---|---|---|---| | influencer-avatars/ | Two voiced avatars (one from a portrait, one from a description) present a product in a 10-second clip, extended to 30 seconds, with the first 20 seconds upscaled to 1080p. Node.js and Python | How to Make AI Influencer Videos with Avatars via the Google Vids API | October 7, 2026 | | skills/google-vids-video/ | Agent skill for Claude Code, Codex and other coding agents: ask for a clip and the agent makes it with Omni 1.1 Flash in Vids (voiced AI avatars, reference images, extend, 1080p upscale, edit) and downloads the .mp4, never paying twice for a request. Install: npx skills add useapi/google-vids-api --skill google-vids-video. Bash, curl, jq | SKILL.md | October 8, 2026 | | n8n/ | Ready-to-import n8n app: describe or pick a presenter, choose a voice, write the lines, and get a talking avatar video of up to 40 s with an optional 1080p upscale. No code | n8n template #20704 | October 12, 2026 | | watermark-remover/ | Removes the visible Gemini ✦ sparkle from Vids videos by reverse alpha blending, in all four Vids formats, for clips as generated and their upscales (not extended or edited clips). Python | Google Vids API › Watermark | October 8, 2026 |

Quick start

You need Node.js v21 or newer or Python 3.x (no dependencies to install), a useapi.net API token, and a Google account on a paid Google AI plan connected with the Google Vids setup.

git clone https://github.com/useapi/google-vids-api.git
cd google-vids-api/influencer-avatars
node ./influencer-avatars.mjs <API_TOKEN> <EMAIL>
# or, equivalently, with Python:
python3 ./influencer-avatars.py <API_TOKEN> <EMAIL>

To take the ✦ off a downloaded clip (needs numpy and ffmpeg):

cd google-vids-api/watermark-remover
pip install numpy
python3 vids_watermark_remover.py my-clip.mp4    # → my-clip_clean.mp4

Each example's README lists its options. Every endpoint is documented in the Google Vids API reference.

MCP server

useapi.net also runs a hosted Model Context Protocol server for Google Vids, so an AI assistant such as Claude Code, Cursor or VS Code Copilot can use it on your own account. It has 16 tools: Gemini Omni 1.1 Flash clips (3–10 s, 720p or 1080p, with sound and speech) from text, a start image or up to 3 references; extend, upscale and edit; images in 7 styles; uploads; and voiced avatars with 30 voices that speak the lines in your prompt. Nothing to install or run locally.

• Endpoint: https://api.useapi.net/v1/google-vids/mcp
• Transport: Streamable HTTP
• Authorization: your useapi.net API token in the Authorization: Bearer … header, and an account connected with the Google Vids setup
• Listed in the official MCP Registry as net.useapi/google-vids

Claude Code:

claude mcp add --transport http useapi-google-vids https://api.useapi.net/v1/google-vids/mcp --header "Authorization: Bearer YOUR_API_TOKEN"

Cursor, VS Code, Windsurf and the full tool list: Google Vids MCP server docs. useapi.net is a third-party API, not affiliated with Google.

Use with Claude Code

This repo is also a Claude Code plugin marketplace. The plugin adds the hosted Google Vids MCP server and the google-vids-video agent skill, and reads your token from the USEAPI_TOKEN environment variable, so set it before you start Claude Code:

export USEAPI_TOKEN=user:12345-...      # your useapi.net API token

Then, inside Claude Code:

/plugin marketplace add useapi/google-vids-api
/plugin install google-vids@useapi-google-vids

On Claude Code 2.1.275 or later, /plugin install google-vids --marketplace useapi/google-vids-api does both in one step. Run /mcp to check that useapi-google-vids is connected.

Use with Gemini CLI

This repo is also a Gemini CLI extension with the same MCP server and the google-vids-video agent skill:

gemini extensions install https://github.com/useapi/google-vids-api

The install asks for your useapi.net API token and keeps it in the system keychain. Change it later with gemini extensions config useapi-google-vids, and check the connection with gemini mcp list. The google-vids-video skill's scripts read USEAPI_TOKEN from your shell, so export it as well if you use the skill.

Common questions

<!-- Official API figures in these answers, verified 2026-10-18: https://ai.google.dev/gemini-api/docs/pricing (Omni 1.1 Flash ~$0.10/s at 720p = ~$1.01 per 10 s). Vids figure: Ultra $199 = 10,000 s/month = ~$0.20 per 10 s. -->

• Does Google Vids have an API? Yes, through useapi.net. Google doesn't offer an API for Vids, a Google Workspace app (as of October 2026), so useapi.net drives your own Google account in Vids, and clips come out of the monthly Vids allowance of your Google AI plan. A 10-second Omni 1.1 Flash clip uses about $0.20 of a Google AI Ultra $199 plan, against about $1.01 at 720p on the metered Gemini API, where Omni 1.1 Flash costs about $0.10 per second.
• How much can I make? Google meters Vids per month: Google AI Pro gets 500 seconds of video, Ultra 5x 2,500 seconds and Ultra 20x (Ultra $199) 10,000 seconds, about 1,000 ten-second clips. A free Google account gets no video or images, but can still make avatars. See plans and allowances.
• What does it cost? A flat $15/month to useapi.net, which covers every useapi.net API, plus the Google AI plan you already have. There is no per-clip charge from us. A 10-second clip works out to about $0.20 on Ultra $199, against about $1.01 at 720p on Google's metered Gemini API (as of October 2026).
• Google Vids or Google Flow? Both make Omni 1.1 Flash video on the same Google AI plan, from separate allowances, so one Google account connected to both APIs gets both. Vids extends Omni clips and needs no captcha; Flow also has Veo 3.1 and Nano Banana images. Flow examples: useapi/google-flow-api.
• Is the video watermarked? Every Vids clip has an invisible SynthID watermark and a visible Gemini ✦ in the corner. watermark-remover/ removes the visible sparkle from clips as generated and their upscales (not from extended or edited clips); SynthID is untouched.
• Connecting an account by hand? The Google Account Setup scripts open a clean, single-use browser profile, so the session you copy keeps working.

中文说明

这是 useapi.net 的 Google Vids API 示例代码。通过 REST API 在 Google Vids 中调用 Gemini Omni 1.1 Flash 生成视频，支持带配音的虚拟形象（avatar）、参考图片、视频延长（最长约 41 秒）和 1080p 放大。

• 使用你自己的 Google 账号和付费 Google AI 订阅，按 Vids 每月额度（视频秒数和图片数）计算，与 Google Flow 的积分分开。
• 无需验证码（captcha），无需 Google Cloud 项目或 API Key。
• 价格：useapi.net 每月 15 美元（含所有 API），加上你已有的 Google AI 订阅。
• watermark-remover/ 可去除视频右下角可见的 Gemini ✦ 标记，不改动不可见的 SynthID 水印。

中文教程（数字人、视频延长、无需验证码，含 curl 示例）：如何通过 Google Vids API 用 Gemini Omni 1.1 Flash 生成会说话的数字人视频。完整文档：Google Vids API。

About useapi.net

useapi.net is an experimental REST API for AI services. The Google Vids API drives your own Google account on your Google AI plan, so you spend your plan's monthly Vids allowance instead of paying metered developer-API prices.

Visit our Discord Server or Telegram Channel for any support questions and concerns.

We regularly post guides and tutorials on the YouTube Channel.

License

The example code in this repository is released under the MIT License. It covers the example scripts only, not the useapi.net service or API.