Gemini Omni Flash

Google Gemini Omni Flash — faster/cheaper Omni tier: multimodal video with native audio, text/image-to-video + video-edit.

Credits

Use Gemini Omni Flash in Nodaro

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

• Generate Video
• Generate Video Pro

Run Gemini Omni Flash 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 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",        "duration": 4      }'

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",  duration: 4,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "gemini-omni-flash",    "duration": 4  }}

Prompt tips

• Multimodal Google video with native audio: text-to-video, image-to-video, and video-edit through the same prompt surface. 4/6/8/10s; 720p/1080p or 4K tier.
• Structure like the platform default: subject → action → scene → lighting → camera → style. Quote dialogue lines to have them spoken; describe SFX/ambience plainly in the prompt.
• Text-to-video REQUIRES a concrete aspect ratio (the API hard-rejects a missing one); image runs infer aspect from the input.
• Reference images ride in image_urls, your references first — bind them by ordinal ('the woman from @image_1'); a wired start frame is appended after them and bound as the opening frame. Video-edit: describe the change.

Similar models