Kling 4.0 text-to-video API turns a prompt into clips up to 30 seconds with synchronized audio, 720p or 1080p and four framings. Watch verified examples and try it online.
Provider: Kuaishou
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Kling 4.0 Text-to-Video: turn a prompt into cinematic clips up to 30 seconds, at 720p/1080p with 16:9, 9:16, 1:1 and 21:9 framing. Picture and synchronized audio are generated together.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Verified output
Tests layered steam, low golden light through pine trees, a slow lateral move and engine sound in one shot.
Original prompt
An old steam train pulls slowly out of a mountain station at dawn, thick white steam billowing into low golden sunlight, pine forest on both sides, slow lateral tracking shot, cinematic depth of field, natural engine rumble and distant birdsong
A 1080p run that checks rain highlights, neon bokeh, a slow push-in and the instrument's sound.
Original prompt
A lone violinist plays on a rain-soaked rooftop at blue hour, neon signs blurring behind her, rain droplets catching rim light, slow push-in, shallow depth of field, cinematic
Choose by input method, output specifications, control surface, and budget.
Kling 4.0 Text-to-Video turns a prompt into a three- to thirty-second clip at 720p or 1080p, with synchronized audio generated in the same pass. It fits ad tests, social shorts, storyboards and single continuous takes.
The Playground and the API use the same model ID. This route is text-only; when a specific frame has to start the clip, switch to the image-to-video model instead. kling-4.0/text-to-video
These specifications reflect the current HiAPI Kling 4.0 Text-to-Video request contract.
Validate motion at 720p first, then raise resolution or duration once the composition holds.
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
5-30s · 1080p
Validate subject motion and camera continuity with 5s · 720p, then move to 5-30s · 1080p.
Check motion stability and subject consistency online, then create an asynchronous task with the same model ID: kling-4.0/text-to-video.
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-4.0/text-to-video",
"input": {
"prompt": "An old steam train pulls slowly out of a mountain station at dawn, thick white steam billowing into low golden sunlight, pine forest on both sides, slow lateral tracking shot, cinematic depth of field, natural engine rumble and distant birdsong",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9"
}
}'No. kling-4.0/text-to-video takes a text prompt only. Use kling-4.0/image-to-video when a specific first frame has to come alive.
Any whole duration from 3 to 30 seconds at 720p or 1080p, framed at 16:9, 9:16, 1:1 or 21:9 ultrawide. The examples here show five-second landscape clips at 720p and 1080p.
Yes. Picture and audio are produced in the same pass and the MP4 ships with a soundtrack. Ambient sound and sound sources written into the prompt, such as rain, an engine or an instrument, are used by the model.
Per output second, with separate per-second tiers for 720p and 1080p. There is no minimum charge: a five-second clip costs five seconds at the tier rate. The live page price and task record show the exact amount.
Start with subject and setting, state the camera move explicitly (push-in, lateral tracking, handheld, locked-off), then add lighting and mood. Put the sound you want in the same description instead of planning to add it later.
Send an asynchronous task to POST /v1/tasks with model set to kling-4.0/text-to-video and prompt, duration, resolution and aspect_ratio in input. The create call returns a taskId used for retrieval.
HiAPI Blog
