Kling 2.6
Established text and image generation with motion and audiovisual output.
Read model historyKling 3.0 is available
Make cinematic AI video with Kling 3.0.
Create from text or an image, direct multiple shots, preserve important subjects, and generate native audio in one video workflow.
Text to videoImage to videoUp to 15 secondsNative audio
Native audioNative dialogue
Kling model lineup
From generation to directed storytelling.
Choose a workflow by the control you need. Kling30 is centered on the latest Kling 3.0 generation path.
Kling O1
Reference-led creation and editing for more specific visual direction.
Explore official guidesKling 3.0
Native audio, multi-shot narratives, stronger element consistency, and flexible duration.
Generate with Kling 3.0Multi-shot direction
Plan a sequence, not just a moving frame.
Describe shot order, framing, camera movement, and transitions in one prompt. Kling 3.0 can use that structure to build a short scene with more deliberate coverage.
- Write shots in the order they should appear
- Set a clear camera purpose for each shot
- Keep subject and travel direction consistent
Camera control
Direct how the audience sees the action.
Use tracking, push-in, orbit, point-of-view, and aerial directions to shape the rhythm and reveal of a scene.
- Choose one primary movement per shot
- Match camera speed to subject movement
- Use framing changes to advance the story
Visual consistency
Keep the important details recognizable.
Use a clean reference and focused motion direction when a person, product, outfit, or composition needs to carry through the shot.
Made for real creative work
View the full showcaseFrom first concept to campaign asset.
Cinematic concepts
Previsualize mood and camera language
Turn a written scene into a visual reference before committing to production.
Brand content
Test motion, layouts, and visible text
Explore product moments and campaign directions with faster visual iteration.
Social storytelling
Build short-form scenes for vertical and wide formats
Start with a focused action, then adapt the framing for the channel where the video will live.
Open the generatorText to video or image to video?
DecisionText to videoImage to videoKling 3.0
Start withA written sceneA reference imageEither input
Best forNew conceptsAnchored visualsDirected sequences
Control withPrompt structureImage + promptShots + audio
Know the workflow before you generate.
What is Kling 3.0?
Kling 3.0 is an AI video model series for generating video from text, images, and visual references. Its published capabilities include native audio, multi-shot control, longer clips, and stronger subject consistency.
Can I create both text-to-video and image-to-video?
Yes. Start with a written prompt for text-to-video, or upload a reference image to guide the subject, composition, and visual style of an image-to-video generation.
How long can a Kling 3.0 video be?
Kling's published Video 3.0 guide describes flexible generation from 3 to 15 seconds. Options available through Kling30 may vary by API mode and provider availability.
Does a failed generation consume credits?
No. Kling30 reserves the estimated credits when you submit. It finalizes the charge only after a successful result and releases the reservation if the task fails.
Is Kling30 the official Kling AI website?
No. Kling30.video is an independent creation platform and is not affiliated with Kling AI or its model provider.
Generate with Kling 3.0.
Open the generator, choose text or image, and shape the scene before signing in.