Try MiniMax FastH3 from Fastvideo →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
Video GenerationActive

klingai / kling-v2.6

kling-v2.6

byklingai

Kling v2.6 is a unified multimodal model designed to solve the "silent video" problem of previous generations. Unlike v2.5, which focused on physical simulation, v2.6 focuses on sensory immersion. It understands the semantic link between visual motion and sound—automatically generating the sound of footsteps when a character runs, or lip-synced dialogue when a character speaks.

Text to VideoImage to Video
Model ID
kling-v2.6
Provider
klingai
Updated
1784816096
4
Comments
Average rating : 4.8 (5 users)
Providerklingai
Modelkling-v2.6
Text to VideoImage to Video
wiro playground—klingai/kling-v2.6
Reset to defaults

Resolution mode. Sound requires Professional (1080p). First + last frame always uses 1080p.

0 / 1
Maximum 1 image allowed

Optional.

0 / 1
Maximum 1 image allowed

Optional. Sound will be off. Uses 1080p (pro).

The prompt to generate the video.

Optional. Default off. If there is last image then sound will be off.

Sample outputs
Updated 1784816096

Kling v2.6 is a breakthrough multimodal generation model that introduces native audio-visual synthesis, capable of generating 1080p video with perfectly synchronized sound effects, dialogue, and background ambience in a single inference pass. Unlike previous iterations that required post-production for sound, v2.6 utilizes a unified Audio-Visual Diffusion Transformer architecture to understand the semantic relationship between motion and audio, delivering physically accurate Foley (e.g., footsteps, collisions) and precise lip-synced speech for a fully immersive, ready-to-publish cinematic output.

Example prompts

Great starting points for kling-v2.6.

The man in the orange hat and blue jacket begins to walk slowly and deliberately forward across the rocky, grassy terrain towards the distant, jagged mountain range. As he moves, three high-performance stunt planes suddenly enter the frame rapidly from the left side of the sky, streaking across the upper background. They leave thick, white smoke trails behind them as they perform a synchronized banking maneuver. The mountains and foreground landscape remain perfectly stable. Clear daylight, high fidelity, cinematic motion.Video Generation
A sweeping crane shot starting from a low angle close to the vibrant orange marigold flowers, smoothly rising upwards to a high-angle, top-down perspective. The movement reveals the vast expanse of the flower field stretching towards the horizon, with the majestic snow-capped volcano and the smaller hill under a clear blue sky now seen from above. High fidelity, expansive landscape, photorealistic cinematic motion.Video Generation
Extreme close-up of an elderly fisherman with a weathered face and a gray beard, wearing a yellow raincoat. He is standing on a boat deck in the rain. Raindrops run down his face. He looks directly into the camera with a calm, intense expression, then blinks slowly. Soft, diffused lighting, high skin detail, 85mm lens style, cinematic portrait.Video Generation
A dirty white rally car drifting aggressively around a sharp corner on a gravel forest road. Clouds of dust and dirt are kicked up into the air behind the wheels. Sunlight flickers through the pine trees. The camera tracks the car from a low angle, shaking slightly to mimic handheld footage. High speed, motion blur, photorealistic, 4k.Video Generation

API quick start

Run kling-v2.6 with a single API call.

POST https://api.wiro.ai/v1/Run/klingai/kling-v2.6
{
  "prompt": "The man in the orange hat and blue jacket…",
  "negativePrompt": "...",
  "duration": 5,
  "sound": "off"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion