Kling 3.0

Premium Kling 3.0 — variable 3-15s duration, native audio, 720P/1080P.

Kling 3.0 examples

Credits

Use Kling 3.0 in Nodaro

Add one of these nodes to your canvas, open its settings, and choose Kling 3.0 as the model:

• Generate Video

Run Kling 3.0 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 3.0 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-3.0",        "duration": 5      }'

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-3.0",  duration: 5,})

{  "tool": "generate_video",  "arguments": {    "prompt": "A paper boat drifts down a rain-soaked street at dusk, slow dolly in",    "model": "kling-3.0",    "duration": 5  }}

Prompt tips

• Kling speaks scripted dialogue natively with lip sync — quote the line and enable sound: [Anna: warm calm voice]: "We made it." On kling/kling-3.0 audio raises the credit cost; kling-3-omni includes it.
• Structure prompts as Scene → character/element → Motion → Audio → style. Put ALL sound in one 'Audio:' block: dialogue in quotes, then SFX and ambience described plainly ('rain tapping on glass, no music').
• Give each speaker a stable label + voice description and reuse it exactly — [Detective: low raspy voice, tired] — pronouns or renamed speakers break voice binding in multi-character scenes.
• Tone words in the bracket steer delivery (whispering, crying, fast urgent voice); pace with 'Immediately' / 'after a pause'. 2.6 voices are English/Chinese only; 3.0 adds dialects and code-switching.
• kling-3.0 wired references become @element_name mentions (handled automatically by the editor); multi-shot mode forces sound ON. Kling 2.6 prompts cap at 1000 chars — keep the Audio block tight.
• Say what should NOT sound: 'no background music, no other sounds' — otherwise Kling invents a music bed under dialogue.

Similar models