Run Kling Video V3 4K Text To Video API on fal
Kling's Native 4K is the world's first AI video model with native 4K output — cinema-grade visuals generated in a single step, with no post-production upscaling or third-party tools required.
Built for: Production-ready visuals, large-screen displays, high-definition playback, and professional workflows where clarity, detail, and cinematic texture are non-negotiable.
Pricing
Kling V3.0 in 4K mode is billed per second of generated video.
| Configuration | Price per second |
|---|
| 4K mode, without native audio generation | $0.42 |
| 4K mode, with native audio generation (without voice control) | $0.42 |
A 5-second clip at 4K therefore costs $2.10; a 10-second clip costs $4.20.
Features
Kling V3 4K is the industry's first native 4K text-to-video model. It produces sharpened, detail-rich footage that meets commercial 4K standards directly from a text prompt, with no upscaling step required. Every frame is rendered with sophisticated lighting, atmosphere, and exceptional clarity, so output is ready for high-end delivery without a post pipeline. The model also maintains stable reference consistency during 4K generation — element features, stylistic expression, color, lighting, and overall mood from reference content are faithfully preserved. Native audio is generated in Chinese and English (other languages are translated to English), durations run from 3 to 15 seconds, and multi-shot storytelling is available through the multi_prompt interface. If you want to learn more visit our kling v3 page.
Default prompt template
Scene:
[where this happens, time of day, background, environment]
Subject:
[who or what is the main focus, action, motion]
Important details:
[camera movement, lens, lighting, color grade, atmosphere, pacing]
Audio:
[dialogue, ambient sound, music cues — if generate_audio is enabled]
Use case:
[cinematic trailer / product spot / music video / editorial clip / concept reel]
Constraints:
[no watermark / no logos / preserve subject identity / steady camera]
Technical Specifications
| Spec | Details |
|---|
| Architecture | Kling Video V3 (Native 4K) |
| Input Formats | Text prompt, or a list of prompts for multi-shot generation |
| Output Format | MP4 video via URL |
| Resolution | Native 4K, no post-processing upscale |
| Duration Range | 3 to 15 seconds |
| Aspect Ratios | 16:9, 9:16, 1:1 |
| Audio | Native audio generation (Chinese / English) |
| License | Commercial use via fal Partner agreement |
API Documentation
What's New in Kling V3 4K
Industry-First Native 4K
One-click export for professional-grade 4K video. Output goes straight from the model at commercial 4K resolution — no separate upscaling pipeline, no quality degradation from chained models, and no third-party tools.
Cinema-Grade Clarity
Ultra-clear visuals that faithfully capture every intricate detail. Sharpness, atmosphere, and lighting hit the bar for large-screen display and professional production workflows out of the box.
Greater Refinement
Richer color gradations and smoother transitions give footage a deeper sense of dimension. Fewer banding artifacts and cleaner highlight-to-shadow rolloff make the model suitable for cinematic grading.
More Realistic Subjects
Faithful skin textures, more natural facial expressions, and convincing material response (fabric, hair, metal, liquid). Useful where human subjects and close-ups are central to the shot.
Stable Reference Consistency
During 4K generation the model preserves element features, stylistic expression, color, lighting, and overall mood from reference content — striking a balance between high-quality output and visual consistency across shots.
Native Audio Generation
Audio is produced alongside the video in the same request. Supports Chinese and English speech with correct pronunciation; other languages are translated to English automatically. Use lowercase for conversational English and uppercase for acronyms and proper nouns.
Multi-Shot Composition
Pass a list of prompts via multi_prompt to build a sequenced clip with distinct shots and per-shot durations. Choose customize to control each shot yourself, or intelligent to let the model plan the cut.
Efficient Workflow
Skip the render → upscale → export loop. A single API call produces a delivery-ready 4K asset.
Quick Start
Install the client
npm install --save @fal-ai/client
Set your API key
export FAL_KEY="YOUR_API_KEY"
Text to video
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/kling-video/v3/4k/text-to-video", {
input: {
prompt: "Close-up of glowing fireflies dancing in a dark forest at twilight. Soft bioluminescent particles float through the air. Shallow depth of field, bokeh lights in background. Magical atmosphere, gentle movement.",
duration: "5",
aspect_ratio: "16:9",
generate_audio: true,
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data.video.url);
Multi-shot generation
const result = await fal.subscribe("fal-ai/kling-video/v3/4k/text-to-video", {
input: {
multi_prompt: [
{ prompt: "Wide establishing shot of a Tokyo street at night, rain falling.", duration: "4" },
{ prompt: "Close-up of a neon sign reflected in a puddle.", duration: "3" },
{ prompt: "A lone figure walking away under an umbrella, warm streetlight.", duration: "5" },
],
shot_type: "customize",
aspect_ratio: "16:9",
generate_audio: true,
},
});
API Reference
| Parameter | Type | Default | Description |
|---|
prompt | string | optional | Text prompt for video generation. Either prompt or multi_prompt must be provided, not both |
multi_prompt | array | optional | List of per-shot prompts with individual durations for multi-shot generation |
duration | enum | "5" | Video duration in seconds. One of "3"–"15" |
generate_audio | boolean | true | Generate native audio alongside the video |
shot_type | enum | "customize" | customize (user-defined shots) or intelligent (model-planned cut) |
aspect_ratio | enum | "16:9" | 16:9, 9:16, or 1:1 |
negative_prompt | string | "blur, distort, and low quality" | Attributes to avoid |
cfg_scale | float | 0.5 | Prompt adherence strength, range 0–1 |
Output
{
"video": {
"file_name": "output.mp4",
"content_type": "video/mp4",
"url": "https://v3b.fal.media/files/...",
"file_size": 8062911
}
}
Use Cases
Commercial and advertising -- Delivery-ready 4K spots and product films without an external upscaling stage.
Cinematic and short-form content -- Trailers, concept reels, and stylized sequences with multi-shot composition via multi_prompt.
Large-screen and broadcast -- Content mastered for high-definition playback, cinema projection, and professional production pipelines.
Music and social video -- 9:16 and 1:1 formats for vertical platforms with native audio baked into the render.
Editorial and branded storytelling -- Multi-shot narratives where each beat has its own prompt and duration, with stable reference consistency across cuts.
Multilingual campaigns -- Native Chinese and English speech generation, with automatic translation for other source languages.
Long-Running Requests
Video generation is a long-running job. Use the Queue API to submit asynchronously and retrieve results via webhook or polling.
const { request_id } = await fal.queue.submit("fal-ai/kling-video/v3/4k/text-to-video", {
input: { prompt: "..." },
webhookUrl: "https://your-server.com/webhook",
});
const status = await fal.queue.status("fal-ai/kling-video/v3/4k/text-to-video", {
requestId: request_id,
logs: true,
});
const result = await fal.queue.result("fal-ai/kling-video/v3/4k/text-to-video", {
requestId: request_id,
});
Notes
- Provide exactly one of
prompt or multi_prompt — not both
- For English speech in
generate_audio, use lowercase for regular words and uppercase for acronyms and proper nouns
- Non-English / non-Chinese audio prompts are translated to English automatically
cfg_scale trades prompt adherence against motion freedom; lower values allow more creative variation- When running client-side code, never expose your
FAL_KEY. Use a server-side proxy instead
cURL
curl --request POST \
--url https://fal.run/fal-ai/kling-video/v3/4k/text-to-video \
--header "Authorization: Key $FAL_KEY" \
--header "Content-Type: application/json" \
--data '{
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight.",
"duration": "5",
"aspect_ratio": "16:9",
"generate_audio": true
}'
Python
import fal_client
def on_queue_update(update):
if isinstance(update, fal_client.InProgress):
for log in update.logs:
print(log["message"])
result = fal_client.subscribe(
"fal-ai/kling-video/v3/4k/text-to-video",
arguments={
"prompt": "Close-up of glowing fireflies dancing in a dark forest at twilight.",
"duration": "5",
"aspect_ratio": "16:9",
"generate_audio": True,
},
with_logs=True,
on_queue_update=on_queue_update,
)
print(result)
fal-ai/kling-video/v3/4k/text-to-video