{"slug":"omni-flash-video","title":"omni-flash-video","summary":"Generate AI video with Google's Omni 1.1 Flash (Gemini Omni Flash, audio-native video with spoken dialogue and voices) or Veo 3.1 through the useapi.net Google Flow API, on the user's own Google AI plan. Supports text-to-video, reference images of people or products, start and en","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-10-17T09:06:55.521386Z","repo":{"url":"https://github.com/useapi/google-flow-api","stars":44,"forks":12,"license":"MIT","updatedAt":"2026-10-17T06:54:17Z"},"bodyHtml":"

Omni 1.1 Flash video: an agent skill

\n

An Agent Skill that lets Claude Code, Codex and other coding agents make AI video with Google's Omni 1.1 Flash (Gemini Omni Flash, audio-native: spoken dialogue, preset voices, reference images of people and products, video-to-video edits) or Veo 3.1, and download the .mp4. Ask your agent \"make a 6-second portrait clip of the woman in presenter.jpg holding up our mug and saying it's the best coffee she's had\" and it runs the scripts in this folder.

\n

It calls the Google Flow API by useapi.net, a third-party REST API that runs on your own Google Flow account. Each clip spends Flow credits from your Google AI plan.

\n

Install

\n

With the skills CLI (asks which agents to install for):

\n
npx skills add useapi/google-flow-api --skill omni-flash-video\n# add -g to install for your user instead of the current project\n
\n

Or copy the folder yourself:

\n
git clone https://github.com/useapi/google-flow-api.git\ncp -r google-flow-api/skills/omni-flash-video ~/.claude/skills/     # Claude Code, every project\ncp -r google-flow-api/skills/omni-flash-video .claude/skills/       # Claude Code, this project only\ncp -r google-flow-api/skills/omni-flash-video ~/.codex/skills/      # Codex\n
\n

Then give the agent your token in the environment it runs in:

\n
export USEAPI_TOKEN=user:12345-...      # your useapi.net API token\nexport USEAPI_EMAIL=you@gmail.com       # optional: which connected Google account to use\n
\n

You need:

\n
    \n
  1. A useapi.net API token. One $15/month subscription covers every useapi.net API.
    2. \n
  2. A Google account with a Google AI Plus, Pro or Ultra plan, connected with the Google Flow setup. An 8-second 720p Omni clip costs 12 Flow credits, a 360p draft about half.
    3. \n
  3. bash, curl and jq.
    4. \n
\n

Use it without an agent

\n

The scripts work on their own too:

\n
./scripts/video.sh \"The woman in @referenceImage_1 holds up the mug and says: 'Best coffee I've had all year.'\" \\\n  referenceImage_1=./presenter.jpg referenceAudio_1=Kore aspectRatio=portrait duration=6\n
\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ScriptWhat it does
scripts/video.shEverything below in one command: prompt and local files in, .mp4 out
scripts/upload.shUpload an image (PNG, JPEG, WebP) or video (MP4), print its asset id
scripts/generate.shStart a generation, print the job id
scripts/wait-job.shPoll the job until it is done, print the final record
scripts/download.shDownload the finished .mp4 file(s)
\n

SKILL.md is what the agent reads: the options, credit costs, prompting rules that work with Omni, and what to do on each error. The full API reference is at useapi.net/docs/api-google-flow-v1.

\n","files":[{"path":"README.md","sizeBytes":3514,"isText":true},{"path":"scripts/_common.sh","sizeBytes":4782,"isText":true},{"path":"scripts/download.sh","sizeBytes":714,"isText":true},{"path":"scripts/generate.sh","sizeBytes":1663,"isText":true},{"path":"scripts/upload.sh","sizeBytes":1207,"isText":true},{"path":"scripts/video.sh","sizeBytes":1397,"isText":true},{"path":"scripts/wait-job.sh","sizeBytes":846,"isText":true},{"path":"SKILL.md","sizeBytes":7660,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-10-17T09:06:58.526696Z","sha256":"31EFE31B8743DA853A8FB73CAFAA60650C181C734939F644E7A11158D1ABE3FC","sizeBytes":11316},"review":null,"source":{"repositoryUrl":"https://github.com/useapi/google-flow-api","path":"skills/omni-flash-video","license":"MIT","commit":"fcad2846be84cd358f00258b8115a4070eec10fc","subtreeSha":"6CCEE9840C17CCF107C116FB008F84AC4EF1B068B1C94566383A9EA18D4A09B4","lastSyncedAt":"2026-10-17T09:06:55.518495Z"},"reviewedAt":"2026-10-17T09:07:03.236596Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/useapi/google-flow-api/tree/main/skills/omni-flash-video"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install useapi-google-flow-api@llmmart"},{"target":"git","command":"git clone https://github.com/useapi/google-flow-api.git"}]}