HiAPI
OverviewModels MarketAPI KeysUsage StatisticsCall LogsBillingReferralPlaygroundStorageChangelogContact UsSettings
Display unit
N
Powered by hiapi
Settings

Welcome

Contact Us

Try Kling 3.0 Turbo text-to-video in the HiAPI Playground. Compare real 720p results, copy tested prompts, review 3–15 second parameters and pricing, then call POST /v1/tasks.

Provider: Kuaishou

Category: video generation

Endpoint: /v1/tasks

Status: Available

Cost: See live page pricing

Back to Models

Kling 3.0 Turbo Text to Video

New
by KuaishouVideo

Kling 3.0 Turbo text-to-video: the speed tier of the 3.0 family with flexible 3-15s duration and 720p/1080p output — built for volume.

Pricing

Standard Usage

260 Credits/ s

Input

0 / 2500
5s
3s1-second steps15s

Choose 3-15 seconds in 1-second steps

Estimated cost1,300 Credits260 Credits / s × 5s × 720p

Output

Ready for generation

Configure your parameters and click "Run" to see the output here.

--GPU-T4

Real API text-to-video results

From one prompt to a complete generated video

Six examples cover landscape and vertical output, five- and twelve-second clips, camera work, people, stylization, and commercial short-form. Play the full video and copy the exact prompt to reproduce or adapt the shot.

Camera revealHigh-speed trackingStylized motionVertical portrait12-second long takeVertical commercial
Camera reveal5s720p16:9

Rise from wet cobblestones into a glowing harbor

A single crane move reveals boats, lanterns, and the full marina without cutting away.

Prompt used for this verified run

Low angle on rain-slicked cobblestones in an old harbor town at dusk, then one slow continuous crane up past mooring ropes and lantern-lit fishing boats, revealing the full marina glowing under a purple and orange sky. Single unbroken rising move, no cuts, stable cinematic camera, photoreal, reflections shimmering on the wet stone.

Real API-generated video5s · 720p · 16:9
High-speed tracking5s720p16:9

Lock the camera onto a downhill rider

Tests fast lateral tracking, foreground blur, flying leaves, and stable subject framing.

Prompt used for this verified run

Low tracking camera racing alongside a mountain biker tearing down a narrow forest singletrack, roots and rocks blurring past the lens, dry leaves kicked up behind the rear wheel, sunlight strobing through the canopy. Camera stays locked on the rider the whole way down, fast and kinetic, photoreal.

Real API-generated video5s · 720p · 16:9
Stylized motion5s720p16:9

Animate a red-crowned crane in ink wash

Moves beyond photorealism with rice-paper texture, layered mist, restrained color, and slow wingbeats.

Prompt used for this verified run

Traditional Chinese ink-wash animation style. A lone red-crowned crane lifts off from a misty mountain lake at dawn, slow wingbeats rippling the water, pine silhouettes dissolving into layered mist behind it. Monochrome ink gradients on visible rice-paper texture, a single red seal-stamp accent, serene unhurried motion.

Real API-generated video5s · 720p · 16:9
Vertical portrait5s720p9:16

Direct a subtle change in expression

Keeps hands, loupe, gear, and face readable while a focused frown softens into a quiet smile.

Prompt used for this verified run

Vertical close-up portrait of an elderly watchmaker examining a tiny brass gear through a jeweler's loupe, lit by one warm workbench lamp in a dark room. His focused frown slowly relaxes into a quiet satisfied smile as the mechanism starts ticking. Shallow depth of field, photoreal skin texture, subtle handheld feel.

Real API-generated video5s · 720p · 9:16
12-second long take12s720p16:9

Choreograph a continuous move through a diner

A longer test coordinates camera travel, a moving waitress, cooks, steam, and the final plate landing.

Prompt used for this verified run

One continuous shot: the camera glides through the swinging door of a busy late-night diner kitchen, follows a waitress balancing three plates as she weaves between line cooks and drifting steam, then slides past her shoulder as the plates land on the neon-lit counter in front of a customer. Single unbroken steadicam take, no cuts, warm practical lighting, photoreal.

Real API-generated video12s · 720p · 16:9
Vertical commercial5s720p9:16

Turn a cold-brew pour into a phone-first ad

Combines macro liquid motion, condensation, window light, a locked camera, and a final whip-pan.

Prompt used for this verified run

Vertical phone-style shot, extreme close-up on dark cold brew coffee pouring in slow motion over a tall glass of ice, condensation beading on the glass, morning window light behind it. Camera holds locked-off the whole time, then the last quarter-second whip-pans up to a hand-lettered 'SMALL BATCH' label. Photoreal, shallow depth of field, warm kitchen counter background softly blurred.

Real API-generated video5s · 720p · 9:16

Related video models

Choose by input method, output specifications, control surface, and budget.

Higher-control text-to-video

Kling 3.0 Omni Text to Video

Use the Omni route when the shot needs broader controls, higher output tiers, or audio options.

Start from an image

Kling 3.0 Turbo Image to Video

Animate a specific source frame while keeping the Turbo duration and resolution structure.

Flagship alternative

Veo 3.1 Text to Video

A higher-cost option for cinematic text-to-video with 4K and native audio controls.

Compare AI video APIs

About Kling 3.0 Turbo Text to Video

Kling 3.0 Turbo Text to Video generates a three- to fifteen-second video directly from a text prompt, with no input image. It suits camera-movement studies, vertical social content, human motion, stylized animation, and longer continuous takes at 720p or 1080p.

The Playground and API use the same model ID: kling-3.0-turbo/text-to-video. It is separate from Image-to-Video, so this page does not show image upload or mix image-to-video fields into the request.

Provider
Kuaishou
Task
Pure text-to-video
Input
Text prompt
Starting price
260 Credits / second

Model specifications

These specifications reflect the current HiAPI Kling 3.0 Turbo Text to Video request contract.

Input
Text prompt
Duration
3–15s
Resolution
720p1080p
Aspect ratio
16:99:161:1
Audio field
No separate control field
API protocol
POST /v1/tasksAsync

720p is 260 Credits / second; 1080p is 320 Credits / second.

How to use Kling 3.0 Turbo Text to Video

The shared three-step shell is adapted for pure text-to-video: prompt timing, frame selection, and tiered validation, with no source-still step.

Subject
Action
Camera
01

Define subject, action, and camera

Kling 3.0 Turbo Text to Video API quickstart

This is the minimum request for an asynchronous text-to-video task. Use the API docs for task retrieval, callbacks, errors, and the complete parameter contract.

curl --request POST 'https://api.hiapi.ai/v1/tasks' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "kling-3.0-turbo/text-to-video",
  "input": {
    "prompt": "Low tracking camera racing alongside a mountain biker on a forest trail, stable subject tracking, photoreal.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}'
The create request returns a taskId; retrieve the result asynchronously.Open full API docs

Frequently asked questions

Does Kling 3.0 Turbo text-to-video require an input image?

No. This page uses the pure text-to-video model kling-3.0-turbo/text-to-video and accepts a text prompt without an image. Use the separate Kling 3.0 Turbo Image-to-Video page when a clip must start from a source frame.

Which durations, resolutions, and aspect ratios does Kling 3.0 Turbo support?

The current HiAPI contract supports 3–15 seconds at 720p or 1080p in 16:9, 9:16, or 1:1. The page cases verify 720p, five- and twelve-second clips, landscape, and vertical output. The 1080p and 1:1 options are supported contract values, not mislabeled as tested examples.

How is Kling 3.0 Turbo text-to-video priced?

Billing depends on generated duration and resolution, with separate per-second tiers for 720p and 1080p. Check the live page price and task record for the final charge.

How should I write a Kling 3.0 Turbo text-to-video prompt?

Start with subject and setting, describe action and camera movement in order, then add lighting, style, and stability constraints. For a long take, specify single continuous shot, no cuts, and the camera path. For vertical work, mention vertical composition and set aspect_ratio to 9:16.

Can I control audio in Kling 3.0 Turbo?

The current public request schema has no separate sound switch or audio field, so this page does not promise precise control of dialogue, music, or foley. A result file may contain an audio track, but production work should inspect the output and add voice, mix, and rights review in post when needed.

How do I call the Kling 3.0 Turbo text-to-video API?

Send an asynchronous task to POST /v1/tasks, set model to kling-3.0-turbo/text-to-video, and include prompt, duration, resolution, and aspect_ratio in input. The create request returns a taskId. See the API docs for retrieval, callbacks, errors, and the complete parameter contract.

Lead with subject and setting, then describe action, camera direction, and speed in time order. State no cuts for a continuous take.

Draft

5s · 720p

Final

3–15s · 1080p

02

Choose duration, quality, and frame

Validate motion and framing at five seconds and 720p. Use 9:16 for vertical or 16:9 for landscape, then increase duration or resolution.

Playground
POST /v1/tasks
03

Validate in Playground, then integrate

Check motion stability and subject consistency online, then create an asynchronous task with the same model ID: kling-3.0-turbo/text-to-video.