Gemini Omni Flash 1.2

Google Gemini Omni Flash 1.2 — 3–15s video with native sound, from 360p to 4K: from text, up to 6 reference images, exact first and last frames, or a video edit. Priced per second.

Credits

Use Gemini Omni Flash 1.2 in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Gemini Omni Flash 1.2 as the model:

• Generate Video
• Generate Video Pro

Run Gemini Omni Flash 1.2 from code

Each call starts a job and returns its jobId. Poll GET /v1/jobs/:id/status, or let the SDK wait for the result. A run costs the credits on this page. API reference

With Nodaro connected to Claude, ChatGPT or Cursor, ask in plain words, or have the assistant call the tool: “Use Gemini Omni Flash 1.2 to make: A paper boat drifts down a rain-soaked street at dusk, slow dolly in”

curl -s -X POST https://app.nodaro.ai/v1/text-to-video \  -H "Authorization: Bearer $NODARO_API_KEY" \  -H "Content-Type: application/json" \  -d '{        "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",        "provider": "gemini-omni-flash-1-2",        "duration": 3      }'

import { createClient, StaticTokenAuth } from "@nodaro/sdk"const client = createClient({  baseUrl: "https://app.nodaro.ai",  auth: new StaticTokenAuth(process.env.NODARO_API_KEY!),})const output = await client.nodes.runAndWait("text-to-video", {  prompt: "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",  provider: "gemini-omni-flash-1-2",  duration: 3,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "gemini-omni-flash-1-2",    "duration": 3  }}

Prompt tips

• Google video with native sound: text-to-video, frames, reference images and video-edit through one prompt surface. Every second from 3 to 15; 360p, 720p, 1080p or 4K.
• Structure like the platform default: subject → action → scene → lighting → camera → style. Quote dialogue lines to have them spoken; describe SFX and ambience plainly.
• Only a start frame (and an end frame) wired: they are sent as exact first and last frames. With reference images wired too, frames join the image list after your references and are named in the prompt.
• Up to 6 reference images: bind them by ordinal ('the woman from @image_1'). No character or voice references on this model. Video-edit: describe the change; the output follows the source clip, up to 15s.

Similar models