﻿> ## Documentation Index
>
> Fetch the complete documentation index at: https://kling.ai/document-api/llms.txt
> Use this file to discover all available pages before exploring further.

# Video Capability Map

> Source: https://kling.ai/document-api/guides/capability-map/video
> Locale: en
> Updated At: 2026-05-19
> This content is optimized for LLMs. UI-only controls are omitted.

Organized from the existing Video Models document, showing model, mode, and capability support for video APIs.

## Models

| Model | Description | Input | Generation Range | Resolution |
| --- | --- | --- | --- | --- |
| Kling 3.0 Turbo | Consistently excellent results, with even better value. | Text, Image | 3~15s | 720P, 1080P |
| Kling 3.0 | Enhanced native audio, improved element consistency, and support for multi-shot storytelling | Text, Image, Video | 3~15s | 720P, 1080P, 4K |
| Kling 3.0 Omni | All-in-one multimodal input, voice-driven characters, and native audio output with storyboards | Text, Image, Video | 3~15s | 720P, 1080P, 4K |
| Kling O1 | Unified video model with all-in-one multimodal instructions and exceptional consistency. | Text, Image, Video | 3~10s | 720P, 1080P |
| Kling 2.6 | See the sound, hear the visual | Text, Image, Video | 3~10s | 720P, 1080P |
| Kling 2.5 Turbo | Max creativity with exceptional value | Text, Image | 5s, 10s | 720P, 1080P |

## Global Capabilities

| Capability | Value | Description |
| --- | --- | --- |
| Avatar | All model versions | Generate digital human broadcast-style videos with just one photo |
| Lip Sync | All model versions | Can be combined with text or audio to drive the mouth shape of characters in the video |
| Multi-element Video Editing | All model versions | Supports marking, replacing, and adding or removing elements in videos |
| Video to Audio | All model versions | Supports adding audio to all videos generated by Kling models and user-uploaded videos |
| Text to Audio | All model versions | Supports generating audio by text prompts |

## Text to Video

| Capability | Description | Kling 3.0 Turbo | Kling 3.0 | Kling 3.0 Omni | Kling O1 | Kling 2.6 | Kling 2.5 Turbo |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Single-shot Video Generation | - | Supported | Supported | Supported | Supported: Only supports 5s or 10s duration | Supported: Only supports 5s or 10s duration; 720P supports silent videos only | Supported |
| Multi-shot Video Generation | - | Supported | Supported | Supported | Not Supported | Not Supported | Not Supported |
| Native Audio | - | Supported | Supported | Supported | Not Supported | Supported | Not Supported |
| Voice Control (Human Voice) | - | Not Supported | Not Supported | Not Supported | Not Supported | Not Supported | Not Supported |

## Image to Video

| Capability | Description | Kling 3.0 Turbo | Kling 3.0 | Kling 3.0 Omni | Kling O1 | Kling 2.6 | Kling 2.5 Turbo |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Single-shot Video Generation | - | Supported | Supported | Supported | Supported: Only supports 5s or 10s duration | Supported: Only supports 5s or 10s duration; 720P only supports silent videos | Supported |
| Multi-shot Video Generation | - | Supported | Supported | Supported | Not Supported | Not Supported | Not Supported |
| First/Last Frame | - | Not Supported | Supported | Supported | Supported | Supported: Only supports 1080P silent videos | Supported: Only supports 1080P |
| End Frame Only | - | Not Supported | Not Supported | Not Supported | Not Supported | Not Supported | Not Supported |
| Element Control | Video character + multi-image elements | Not Supported | Supported | Supported | Supported: Multi-image elements only | Not Supported | Not Supported |
| Native Audio | - | Supported | Supported | Supported | Not Supported | Supported | Not Supported |
| Voice Control (Human Voice) | - | Not Supported | Not Supported | Not Supported | Not Supported | Supported: Only supports 5s or 10s duration and 1080P videos | Not Supported |
| Motion Control | - | Not Supported | Supported: 4K is not supported | Not Supported | Not Supported | Supported | Not Supported |
| Video Reference | Feature reference + video editing | Not Supported | Not Supported | Supported | Supported | Not Supported | Not Supported |
