kwaivgi/kling-v3-video ❓📝🔢🖼️✓ → 🖼️

⭐ Official ▶️ 25.2K runs 📅 Feb 2026 ⚙️ Cog 0.16.11

image-to-video-with-audio text-to-video-with-audio

About

Kling Video 3.0: Generate cinematic videos up to 15 seconds with multi-shot control, native audio, and improved consistency

Example Output

Prompt:

"First-person POV of a roller coaster plunging into the mouth of an erupting volcano. The track spirals down through rivers of glowing orange lava, sparks and embers flying past the camera. The coaster banks hard around a pillar of molten rock, then launches upward through a vent, bursting out of the volcano's crater into a dazzling sunset sky above the clouds. Wind roaring, riders screaming with excitement, the deep rumble of the volcano."

Output

Performance Metrics

532.17s Prediction Time

532.18s Total Time

All Input Parameters

{
  "mode": "pro",
  "prompt": "First-person POV of a roller coaster plunging into the mouth of an erupting volcano. The track spirals down through rivers of glowing orange lava, sparks and embers flying past the camera. The coaster banks hard around a pillar of molten rock, then launches upward through a vent, bursting out of the volcano's crater into a dazzling sunset sky above the clouds. Wind roaring, riders screaming with excitement, the deep rumble of the volcano.",
  "duration": 15,
  "aspect_ratio": "16:9",
  "generate_audio": true
}

Input Parameters

mode Default: pro: 'standard' generates 720p, 'pro' generates 1080p.
prompt (required) Type: string: Text prompt for video generation. Max 2500 characters.
duration Type: integerDefault: 5Range: 3 - 15: Video duration in seconds.
end_image Type: string: Last frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px.
start_image Type: string: First frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1.
aspect_ratio Default: 16:9: Aspect ratio. Ignored when start_image is provided.
multi_prompt Type: string: JSON array of shot definitions for multi-shot mode. Each shot: {"prompt": "...", "duration": N}. Max 6 shots, min 1s per shot, total must equal duration.
generate_audio Type: booleanDefault: false: Generate native audio for the video.
negative_prompt Type: stringDefault:: Things you do not want to see in the video. Max 2500 characters.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using model: kling-v3 in pro mode
Generating video...
Generated video in 516.8sec
Generated video ID: 852471893944451147
Downloading 48957899 bytes
Downloaded 46.69MB in 11.39sec

Version Details

Version ID: 4a8ba2743bd9dc2b487e0c4319988aacd658d33c2d064b8a420f4ee1732c30bd
Version Created: February 16, 2026

Run on Replicate →