Skip to content

Kling v3.0 Text-to-Video

Kling v3.0 Text-to-Video is Kling's v3.0 text-to-video model with multi-shot narrative generation, physics-aware motion, native multilingual audio, and up to 15-second output from a single prompt.

text-to-videomulti-shotaudio-generation
index.ts
import { experimental_generateVideo as generateVideo } from 'ai';


const result = await generateVideo({
  model: 'klingai/kling-v3.0-t2v',
  prompt: 'A serene mountain lake at sunrise.'
});
OverviewPlaygroundAboutProvidersThroughputLatencySimilarFAQ
Latency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.