Kling Video O3 Pro Text-to-Video API by Kuaishou
kwaivgi/kling-video-o3-pro/text-to-video
Kling Omni Video O3 is Kuaishou's advanced unified multi-modal video model with MVL (Multi-modal Visual Language) technology. Professional quality with enhanced motion and detail.
Kling Video O3 Pro Text-to-Video został opracowany przez Kuaishou. Atlas Cloud (prowadzona przez Atlas Cloud AI LLC) zapewnia dostęp do modelu, ale nie jest jego właścicielem. Wszystkie znaki towarowe należą do ich odpowiednich właścicieli.
Kling Video O3 Pro Text-to-Video
Kling Video O3 Pro is Kuaishou's Kling 3.0 Omni model in Professional mode (1080P output), used here for text-to-video. Describe a scene and get cinematic video with native audio, 3–15 second duration, multi-shot storyboards and optional subject (element) references for consistent characters.
Why Choose This?
- Kling 3.0 Omni Kling's unified multimodal video model, which understands text, images, subjects and video together.
- Element references Keep up to 3 characters or objects consistent with Kling element library subjects.
- Multi-shot storyboards Up to 6 shots in one video, each with its own prompt and duration, or let the model split the shots automatically.
- Flexible duration Any length from 3 to 15 seconds.
- Native audio Sound is generated together with the video and is on by default.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Conditional | Text description of the scene, motion and camera. Max 2,500 characters. Reference subjects as <<<element_1>>>, <<<element_2>>>, … Required unless multi_shot is on with shot_type = customize, in which case it is ignored. |
| multi_shot | No | Generate a multi-shot video (default: false). |
| shot_type | Conditional | Required when multi_shot is true. customize: you define every shot in multi_prompt. intelligence: the model splits prompt into shots. |
| multi_prompt | Conditional | Required when shot_type is customize. 1–6 shots, each {index, prompt, duration}. Each shot prompt can be up to 512 characters and can mention <<<element_N>>>. Each shot lasts at least 1 second, and the shot durations must add up to duration. |
| elements | No | Up to 3 subject references (mapped to Kling element_list). Each item either points to an existing subject by element_id, or creates one inline with element_name, reference_type (image_refer / video_refer) and frontal_image + refer_images (up to 3) or refer_videos (1). |
| aspect_ratio | No | 16:9 (default), 9:16 or 1:1. |
| duration | No | Video length in seconds: any integer from 3 to 15 (default: 5). |
| sound | No | Generate native audio with the video (default: true). |
Output resolution is fixed at 1080P for Pro mode. This model has no negative_prompt. Write exclusions directly in the prompt.
How to Use
- Write your prompt — describe the scene, motion, camera movement and mood.
- Add elements (optional) — attach up to 3 subjects and mention them in the prompt as
<<<element_N>>>. - Choose single-shot or multi-shot — for multi-shot, turn on
multi_shot, pickshot_type, and (forcustomize) define 1–6 shots inmulti_prompt. - Choose aspect ratio — 16:9, 9:16 or 1:1.
- Set duration — 3 to 15 seconds.
- Set sound — leave it on for native audio, or turn it off for a silent clip.
- Run — submit and download your video.
Best Use Cases
- Character-Driven Stories — Recurring characters that stay consistent across shots via elements.
- Storyboarding — Turn a shot list into one multi-shot clip.
- Social Media & Shorts — Vertical or square videos with native audio.
- Marketing & Ads — Product or mascot videos with consistent appearance.
- Cinematic Content — Film-quality 1080P scenes from text.
Pro Tips
- Use shorter durations (3–5 s) for testing, then go longer for final output.
- Number elements in array order: the first item is
<<<element_1>>>, the second is<<<element_2>>>, and so on. - Keep prompt syntax simple. Short, clear sentences work better than long nested descriptions.
- Draft with O3 Std to save cost, then render the final version with O3 Pro.
Notes
- Duration accepts any integer from 3 to 15 seconds.
- Prompt is limited to 2,500 characters, and each multi-shot shot prompt to 512 characters.
- Multi-shot supports up to 6 shots, and the shot durations must add up exactly to
duration. - Up to 3 elements per request.
Related Models
- Kling Video O3 Std Text-to-Video — Same model in Standard mode (720P) at lower cost.
- Kling Video O3 Pro Image-to-Video — Animate a start frame with Kling 3.0 Omni.
- Kling Video O3 Pro Reference-to-Video — Generate from reference images and an optional reference video.
- Kling Video O3 Pro Video Edit — Edit existing videos with natural-language instructions.
