Kling Omni Video O1 is Kuaishou's first unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinematic videos from text prompts with subject consistency, natural physics simulation, and precise semantic understanding. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Inattivo
$0.56per esecuzione·~17 / $10
EsempiVedi tutto
Cyberpunk action scene. Two cyborg samurais dash past each other on a rainy street. They strike with glowing laser katanas. A burst of blue and red sparks explodes in the center of the frame. The camera pans quickly to follow the movement. Unreal Engine 5 render, high octane.
Cinematic drone shot, aerial view gliding swiftly over a snow-capped mountain range during golden hour. The camera pushes forward through volumetric clouds to reveal a hidden valley with a glowing ancient temple. Realistic lighting, 4k, smooth motion, high fidelity.
First-person view (FPV) of an astronaut walking through a dark, abandoned spaceship corridor with a flashlight. The beam cuts through floating dust particles. Suddenly, the red emergency lights flicker on one by one down the hallway, revealing a massive alien structure at the end. Handheld camera movement, heavy atmosphere, cinematic lighting.
Extreme close-up of a texture that looks like rock. Suddenly, the 'rock' moves and an enormous dragon eye opens, the pupil contracting in the light. The camera quickly zooms out to reveal the dragon's head emerging from a misty mountain range. Debris falling, epic scale, hyper-realistic texture.
GoPro POV shot, fisheye lens. Skiing down a steep, vertical snowy mountain peak at extreme speed. Powder snow sprays into the camera lens. The sun is setting in the distance creating a lens flare. Intense speed, camera shake, wind visual effects, adrenaline rush.
Modelli correlati
README
Kling Omni Video O1 — Text-to-Video
Kling Omni Video O1 is Kuaishou's groundbreaking unified multi-modal video model, representing the world's first AI system that seamlessly integrates text, images, videos, and subject references into a single creative engine. The Text-to-Video mode transforms natural language prompts into stunning, cinematic video content.
🌟 Why Kling Video O1 Stands Out
Universal Creative Engine
Unlike traditional single-task models, Video O1 unifies multiple video generation capabilities:
- Text-to-video generation
- Image-to-video transformation
- Reference-based video creation
- Video editing and modification
- Shot extension and scene continuation
Multi-Modal Visual Language (MVL)
The model interprets your instructions through a revolutionary MVL system that understands:
- Natural language descriptions
- Visual context and references
- Subject identity and characteristics
- Scene dynamics and physics
Subject Consistency
Maintains stable character, prop, and scene features across varying shots — similar to professional directing techniques used in film production.
🎬 Core Features
- Cinematic Quality — Film-grade visual output with natural lighting and realistic motion
- Physics Simulation — Accurate real-world physics for natural movement and dynamics
- Semantic Understanding — Deep comprehension of complex prompts and creative intent
- Flexible Outputs — Multiple resolution and duration options
🚀 How to Use
- Write Your Prompt Describe the scene, action, camera movement, and mood you want.
Example: "A young woman walking through a neon-lit Tokyo street at night, rain reflecting city lights, cinematic tracking shot"
-
Set Parameters Choose your preferred duration, resolution, and aspect ratio.
-
Generate Submit your request and receive high-quality video output.
💰 Pricing
| Item | Price |
|---|---|
| Per Second | $0.112 |
Billed per second of output video duration.
💡 Pro Tips
- Use specific camera terms: "tracking shot," "close-up," "aerial view"
- Describe lighting conditions: "golden hour," "neon-lit," "soft diffused light"
- Include motion cues: "slowly walking," "rapid zoom," "gentle breeze"
- Specify mood and atmosphere for better results
Kling Video O1 Text To Video API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1/text-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Kling Video O1 Text To Video below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-video-o1/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("kwaivgi/kling-video-o1/text-to-video", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"kwaivgi/kling-video-o1/text-to-video",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"duration": 5
}
)
print(output["outputs"][0]) # → URL of the generated outputKling Video O1 Text To Video API — Frequently asked questions
What is the Kling Video O1 Text To Video API?
Kling Video O1 Text To Video is a Kuaishou model for video generation, exposed as a REST API on WaveSpeedAI. Kling Omni Video O1 is Kuaishou's first unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Text-to-Video mode generates cinematic videos from text prompts with subject consistency, natural physics simulation, and precise semantic understanding. Ready-to-use REST API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Kling Video O1 Text To Video API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-video-o1-text-to-video.
How much does Kling Video O1 Text To Video cost per run?
Kling Video O1 Text To Video starts at $0.56 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Kling Video O1 Text To Video accept?
Key inputs: `prompt`, `aspect_ratio`, `duration`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-video-o1-text-to-video.
How long does Kling Video O1 Text To Video take to generate?
Average end-to-end generation time on WaveSpeedAI is around 118 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Kling Video O1 Text To Video outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.