Create videos from text or images with Kling 3.0 Pro, with generated audio.
Use Kling 3.0 Pro to create character actions, short dialogue and scenes with sound. Start from text or a photo and describe how the subject and camera should move.
Kling 3.0 Pro supports 3–15s clips at 1080p in 16:9/9:16/1:1; generated audio Supported; end frame Supported.
See how each example uses framing, movement or sound, then try the prompt with your own material.
Watch the character’s expression, spoken dialogue and sound timing in this VIDEO 3.0 example.
Manufacturer demonstration · Kling AI · 1920×1080
VIDEO 3.0 family example: about 10 seconds, 1080p, with sound. The source does not identify the Pro version.
View original sourceA cafe host rings a bell and says a short line. This simple sequence makes the physical action, sound event and mouth movement easy to compare.
A single continuous medium shot in a quiet sunlit cafe. One adult host stands behind a wooden reception counter beside a small brass service bell. The host gently presses the bell once with one finger; a clear single ding sounds exactly at contact. Then the host looks up, smiles naturally and says in English, "Your table is ready." Keep the face and speaking mouth clearly visible. A locked camera, realistic hands, natural warm light, quiet room ambience. No other people, no cuts, no music, no captions or logos.
AIVG test recording · 5.041667s · 2026-09-08 · Current quote: 200 credits
1080p · 5s · 16:9
Input: Text prompt only.
What to check: Listen for the bell at contact and compare the spoken line with the mouth. Inspect the finger, bell and face throughout; a successful render does not establish perfect synchronization.
Use a real composition as the first frame, then describe the movement. Compare the input and output before using the result.
A plain cobalt blue ceramic cup rests on a pale wooden table beside a window. Soft morning light, gentle steam rising, one slow camera push-in. No people, no lettering, no logos. Keep the cup shape and tabletop stable.
AIVG test recording · 5.041667s · 2026-09-06 · Current quote: 200 credits
1080p · 5s · 16:9
Input: One starting photograph you own or have permission to use.
What to check: This take keeps a largely fixed composition while the steam changes. Compare the starting frame and cup details; the requested push-in is not pronounced.
How to
Describe a new scene or upload one clear starting image. Keep the subject and composition simple for the first take.
Name the subject, one main action and one camera movement. Use the examples below as a starting point, then adapt the instructions.
Review the exact quote before submitting. Play the complete result in your creation, inspect the important details and reuse the inputs for another take.
Cost
Kling 3.0 Pro pricing by configuration: 5s 1080p · Generate audio: Off = 135 · 5s 1080p · Generate audio: On = 200. The exact quote for your settings is shown before you generate.
You always see the exact credit quote for your settings before anything is charged.
Capabilities
Example 1080p · audio off / 5s: 135 credits, equivalent to $2.6865 USD using the 100-credit / $1.99 USD pack. Credits are purchased in packs; check the exact quote for your settings before generating.
AIVG does not provide an API, unlimited credits or watermark removal; official account matters go to Kuaishou.
Related models
| Model | Baseline credits | Highest resolution | Longest duration | Native audio | Modes |
|---|---|---|---|---|---|
| Kling 3.0 Pro | 135 credits · 1080p · audio off / 5s | 1080p | 15s | Supported | Text to Video / Image to Video |
| Kling 2.6 | 100 credits · model output · audio off / 5s | decided by the model | 10s | Supported | Text to Video / Image to Video |
| Kling 2.1 Master | 285 credits · model output / 5s | decided by the model | 10s | Not available | Text to Video / Image to Video |
| H3 Max Multi Angle | 125 credits · 480P / 5s | 1080P | 15s | Not available | Image to Video |
Commercial use follows each model's own terms — confirm them before publishing.
Watermark and export permissions depend on your plan and selected model.
When a generation job reaches a failed state, the credits charged for it are returned to your balance.
Exact quote before every run.
The 5-second 1080p example costs 135 credits with the settings shown. Change the duration, quality or sound to compare prices before generating.
New accounts receive 100 credits. Compare your balance with the price shown for your selected settings.
This page generates a new video from text or one starting image. It does not offer source-video editing or motion transfer. Open AI video editing for supported editing models.
Each example includes its source and settings. Use these to compare the input and result; your own generation may differ.
Kling 3.0 Pro creates new video from text or a starting image. Kling O3 and Motion Control are different model options; choose the one that matches your task.
Related models
Exact quote before every run.
