Kling 2.6 text-to-video turns a written scene into a fixed 1080p clip of 5 or 10 seconds in 16:9, 9:16 or 1:1. Switch audio on to get a generated soundtrack with the picture, or leave it off for a silent clip.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
monsoon-palace-marigold-dance Text only, with sound off. The prompt sets a monsoon dusk in an Indian palace courtyard, and the clip delivers it: rain falling over a wet marble floor, lamps burning in the carved arches, marigold petals drifting down and heaped on the stones, and drummers in white kurtas playing dhol drums around the edge. The woman in the emerald-green silk saree and cropped blouse spins with her arms raised, then turns to the camera, smiles and lets one hand settle at her waist while the low camera circles slowly. `generate_audio` is `false` and `duration_seconds` is `5`, so this is a silent 16:9 clip; the model returns it at 1920×1080.
- 16:9
- 5s
- Output5s
diner-booth-2am A four-person dialogue scene with sound on. Laughter, a jukebox and clinking cutlery all arrived synced to the scene, though the group showed less hand gesturing than the prompt asked for.
- audio
- Output5s
studio-dancer-take A silent, locked-off vertical take of one dancer, full body in frame throughout - clean enough that we reused this exact clip as the driving video for two Motion Control tests on other families.
- 9:16
This example starts at $0.069 per output second. The Playground updates the estimate when you change the settings.