We use cookies to enhance your experience, provide personalised content, and analyse our traffic; see our Cookie Policy.
kuaishou/kling-v3Videos with believable motion, from 720p to 4K
Kling V3 is the 3.0 generation of Kuaishou's video model, launched on 6 February 2026. It generates clips of 3 to 15 seconds at 720p, 1080p or 4K, with optional native audio: dialogue, sound effects and music aligned to the picture.
Kuaishou focused on consistency, photorealism and shot control. Handy for advertising, music videos, short films and any scene where people move. You can pin the first and last frame, and steer away from flaws with a negative prompt.
On Tchavi you pay with mobile money, no bank card and no KYC. One account and one API key open 80+ models, video, image and text together, and your credits never expire.
Three quality levels, from draft to delivery
Set the duration down to the second
Dialogue, sound effects and music aligned to the scene
Lock the first or last frame to a reference image
Steer away from unwanted concepts or artefacts
Landscape, vertical or square for every network
An afrobeat dancer on a Cotonou rooftop at sunset, slow tracking shot circling her, her wrap swirling, street ambience and distant percussion.
Close-up of coffee pouring into a glass in slow motion, steam, splashes and warm light reflections, shallow depth of field, crisp liquid sound.
Kling V3 goes up to 4K, runs 3 to 15 seconds and accepts square format. Veo 3.1 (model: "veo-3.1") stays at 4–8 seconds in 720p or 1080p, in 16:9 or 9:16. For a long or 4K clip, Kling; for a short, polished shot, Veo.
Seedance 2 (model: "seedance-2") takes reference images, videos and audio to pin a character, but stops at 720p. Kling V3 goes up to 4K and offers a negative prompt. Character reference: Seedance; top image quality: Kling.
Duration: 3 to 15 seconds. Resolutions: 720p, 1080p or 4K. Formats: 16:9, 9:16 or 1:1. With a start image, the format follows it. Audio is on by default; generate_audio: false turns it off.
Yes: send image_url for the first frame and last_frame_image_url for the last, and the model fills in the motion between them. Useful to animate a product photo or close a shot.
Send a POST to /v1/videos/generations with your Tchavi key and model: "kling-v3", then prompt, duration, resolution ("720p", "1080p" or "4K") and aspect_ratio. The fields are the same for every video model on Tchavi.
Yes. Top up your Tchavi account with Orange Money, MTN MoMo, M-Pesa or another mobile money operator. No bank card is needed. Credits land as soon as the payment is confirmed and are deducted as you use them.
Yes. Keep your current OpenAI SDK, just change the base URL to Tchavi's (shown in the API tab) and use your Tchavi key. The rest of your code stays the same.
import Tchavi from '@tchavi/sdk';
const client = new Tchavi({ apiKey: 'API_KEY' });
const job = await client.videos.generations.create({
"model": "kling-v3",
"prompt": "A cinematic shot of a cat astronaut floating in space",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "16:9",
"generate_audio": true
});
console.log('Job id:', job.id);
console.log('Credits used:', job.tchavi.credits_used);
// Poll for completion
let result = await client.videos.generations.retrieve(job.id);
while (result.status === 'pending' || result.status === 'processing') {
await new Promise((r) => setTimeout(r, 2000));
result = await client.videos.generations.retrieve(job.id);
}
console.log('Video URL:', result.output?.video_url);Every parameter this model accepts on the API. Check the SDK for full typings.
modelRequiredID of the video model (e.g. `kling-v3`).
promptRequiredText description of the video to generate.