VEO 3.1 Lite

VEO 3.1 Lite — most cost-effective VEO tier for high-volume generation. 4/6/8s with audio, supports first+last frame.

Credits

Use VEO 3.1 Lite in Nodaro

Add one of these nodes to your canvas, open its settings, and choose VEO 3.1 Lite as the model:

• Generate Video
• Generate Video Pro

Run VEO 3.1 Lite 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 VEO 3.1 Lite 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": "veo3_lite",        "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: "veo3_lite",  duration: 4,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "veo3_lite",    "duration": 4  }}

Prompt tips

• Structure prompts as [Cinematography] + [Subject] + [Action] + [Context] + [Style & Ambiance] — lead with the camera, not the subject (Google's official formula).
• Dialogue: quote the exact line with attribution — A woman says, "We have to leave now." (no subtitles). Cue sound as separate lines: SFX: thunder cracks; Ambient noise: quiet hum of a starship bridge.
• Multi-shot pacing via timestamp blocks: [00:00-00:02] medium shot… [00:02-00:04] reverse shot… — VEO honors per-window actions inside one 8s generation.
• Negative prompting is positive phrasing: not 'no buildings' but 'a desolate landscape with no buildings or roads'. Keep prompts under ~175 words — longer overloads the generation.
• Start+end frame: pass both and describe the transition move ('smooth 180-degree arc ending on the POV behind her'). References (ingredients) keep characters/objects consistent and DO generate audio.

Similar models