Kling 4.0 Flash

Kling 4.0 Flash — the faster, lower-cost Kling 4.0 at 720p, up to 20s with native audio; a start frame, reference images, videos and characters (each can carry a voice clip), or plain text.

Credits

Use Kling 4.0 Flash in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Kling 4.0 Flash as the model:

• Generate Video
• Generate Video Pro

Run Kling 4.0 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 Kling 4.0 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": "kling-4-flash",        "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: "kling-4-flash",  duration: 3,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "kling-4-flash",    "duration": 3  }}

Prompt tips

• A start frame alone is the exact opening frame (@first_frame). Beside references it joins the reference images, like kling-4.
• References: up to 10 images, 5 videos (2-20s together) and 7 characters (15 in all). Name each: @image_1, @video_1, a character's @Name.
• No standalone voice: voice clip N is the voice of wired character N, if that character has 2-4 images (else the clip is dropped); write the character, never @audio_N.
• 3-20s (default 5), 720p only, native audio always on, no end frame. Prompt cap 8,000 chars. Aspect auto / 16:9 / 9:16 / 1:1 / 21:9 (a start frame alone sets its own shape).

Similar models